Graphite vs cubic

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to cubic
   Graphite~partialprobed5/10

   The standard llms.txt at the root domain returns 404, but probes show agent-friendly markdown docs (docs/get-started.md returns 200) that point to a Mintlify-hosted llms index, meaning an agent could be pointed at machine-readable docs via an indirect path rather than a canonical llms.txt. Missing for 10: a working llms.txt at the expected root URL, and clear first-party documentation advertising this llms/agent-doc endpoint as a supported entry point.

   • [probe] “PROBE llms.txt: HTTP 404 at https://graphite.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 200 at https://graphite.com/docs/get-started.md > ## Documentation Index > Fetch the complete documentation index at: ht…”

   proof ↗⚑ flag

   cubic✓fullprobed9/10

   cubic hosts a live llms.txt (HTTP 200) and .md-suffixed agent-friendly docs pages that link back to the llms.txt index, confirming an agent can be pointed at these docs and navigate them. missing for 10: no independent/community confirmation of an agent actually consuming llms.txt successfully in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.cubic.dev/llms.txt # cubic documentation > cubic reviews code on GitHub and in local coding workfl…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.cubic.dev/ai-review/introduction.md > ## Documentation Index > Fetch the complete documentation inde…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to cubic
   Graphite~partialprobed4/10

   Graphite's CLI is git-compatible and configurable (gt config, gt commands) and is scriptable in principle, and features like merge queue/automations suggest some CI-style automation, but there is no explicit documentation of headless/non-interactive CLI flags, CI pipeline examples, or a documented automation API for running Graphite entirely without a human in CI. missing for 10: explicit CI/headless mode docs, non-interactive flag examples, dedicated automation/CI integration guide.

   • [claimed-docs] “The Graphite CLI is fully compatible with git—just install it on an existing repository and begin using our suite of gt commands.”
   • [claimed-docs] “Run gt config to open an interactive menu which lets you configure your Graphite CLI.”
   • [claimed-docs] “The Graphite CLI is a tool to help you break up large engineering tasks into a series of small, incremental code changes directly from the c…”
   • [claimed-docs] “Unlimited AI Reviews * AI Review customizations * Automations * Merge Queue”
   • [probe] “official CLI documented at https://graphite.com/docs/install-the-cli”

   proof ↗⚑ flag

   cubic~partialprobed6/10

   cubic's core review flow is already headless — it auto-reviews PRs on open with no manual step (cubic-docs-1, cubic-docs-47), and the cubic CLI can review local changes before a push (cubic-docs-7, cubic-probe-5), which is plausible to script into CI. However there is no explicit documentation of a CI/pipeline integration mode, exit codes for pass/fail gating, or GitHub Actions/other CI examples. Missing for 10: explicit CI pipeline integration docs, non-interactive/exit-code behavior for automation gating, and independent confirmation of CLI use in CI.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”
   • [claimed-docs] “The AI automatically scans every pull request for a wide range of issues, including logic errors, style inconsistencies, and potential secur…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round drawn
   Graphite—none0/10

   Evidence shows Graphite ships its own 'GT MCP' server so that external AI agents can call Graphite's tools (graphite-docs-30, graphite-probe-4), which is the reverse direction of the story — Graphite acting as an MCP server, not as a client that lets users plug external MCP servers into Graphite's own agents/chat. There is no evidence that Graphite's Agents or Chat features can consume third-party MCP servers' tools.

   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”
   • [probe] “official MCP server documented at https://graphite.com/docs/gt-mcp”
   • [claimed-docs] “Describe what you want built or fixed in plain language, and Agents will pull context from your repository, generate the changes, and open a…”
   • [claimed-docs] “Make direct code changes right from your PR page. Click Agent on the right side of the PR to get started.”

   proof ↗⚑ flag

   cubic—none0/10

   Cubic's MCP-related evidence is all about cubic exposing its own MCP server for other coding agents to consume (cubic-docs-8, cubic-probe-4) — the reverse of this story, which asks whether the AI-native user can plug external MCP servers into cubic so cubic can use their tools. No evidence shows cubic acting as an MCP client consuming third-party MCP servers; integrations like Jira/Linear/Notion (cubic-docs-37, cubic-docs-61) appear to be native integrations, not MCP-based tool consumption.

   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [claimed-docs] “Connect to Jira, Linear, Asana, and Notion”
   • [claimed-docs] “Add page context from Notion to make AI reviews understand your requirements and generate accurate PR descriptions.”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to cubic
   Graphite✓fullprobed6/10

   Graphite documents an official MCP server at /docs/gt-mcp, directly matching the story of connecting an agent via an official MCP server, and Graphite is a dev-tool/platform (not itself an agent) so this axis applies. However, the evidence pack only confirms the page exists (probe) without excerpting its content, and there is no independent/hands-on corroboration of using it to connect an agent. Missing for 10: detailed docs content describing the MCP server's tools/capabilities, and community or hands-on confirmation of successful agent connection.

   • [probe] “official MCP server documented at https://graphite.com/docs/gt-mcp”
   • [claimed-docs] “Install the Graphite CLI using either Homebrew or npm”

   proof ↗⚑ flag

   cubic✓fullprobed8/10

   cubic documents an official MCP server that lets coding agents read review findings/codebase context, request PR reviews, triage issues, and even manage subscription/seats without leaving the MCP client, with a dedicated docs page (cubic-probe-4) and integration guidance across Cursor, Claude Code, VS Code, Codex, Gemini CLI, etc. missing for 10: independent/hands-on verification that the MCP server works reliably in practice beyond first-party docs.

   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”
   • [claimed-docs] “Install and connect cubic in Cursor, Claude Code, VS Code, Codex, Gemini CLI, or another coding tool.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Graphite
   Graphite✓fullprobed9/10

   Graphite ships a well-documented official CLI (`gt`) installable via npm/Homebrew, fully git-compatible, with configuration (`gt config`) and a full command reference, and this is corroborated by extensive hands-on community use praising the CLI workflow. It also integrates with AI agent workflows via GT MCP for stacked PR creation, reinforcing agentic use. Missing for 10: no independent benchmark of CLI performance/reliability beyond anecdotal community reports (e.g., some bug reports on rebase/signing edge cases).

   • [claimed-docs] “Install the Graphite CLI using either Homebrew or npm”
   • [claimed-docs] “The Graphite CLI is fully compatible with git—just install it on an existing repository and begin using our suite of gt commands.”
   • [claimed-docs] “Run gt config to open an interactive menu which lets you configure your Graphite CLI.”
   • [claimed-docs] “The Graphite CLI is a tool to help you break up large engineering tasks into a series of small, incremental code changes directly from the c…”
   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”
   • [probe] “official CLI documented at https://graphite.com/docs/install-the-cli”
   • [community] “Ive been using it since mote than a year and it has become part of my toolbelt. Especially the cli that allow to seemlessly rebase multiple …”
   • [community] “The main thing I found to be an improvement is that Graphite maintains all the stacking metadata in git refs. With the other tools, I did no…”

   proof ↗⚑ flag

   cubic✓fullprobed8/10

   cubic ships an official CLI (documented at /ide/cli-review) that reviews local changes before push, finds bugs, and generates prompts for coding agents to fix them, fitting the ai-native/agentic workflow theme. Missing for 10: independent hands-on verification of the CLI's usage/UX beyond first-party docs, and more detail on CLI command surface/options.

   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

6. ai-native userDrive the product through a documented public API

   weight 3 · round to cubic
   Graphite~partialprobed5/10

   Graphite offers a documented CLI (gt commands) and an MCP server (gt-mcp) that let AI/agentic tooling drive the product, but there is no public REST/GraphQL/OpenAPI API — probes for openapi.json/swagger.json all 404. missing for 10: a documented general-purpose public API (REST/GraphQL) with endpoint reference, authentication scopes, and independent/hands-on corroboration of programmatic API usage beyond CLI/MCP.

   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”
   • [probe] “official MCP server documented at https://graphite.com/docs/gt-mcp”
   • [probe] “official CLI documented at https://graphite.com/docs/install-the-cli”
   • [claimed-docs] “Install the Graphite CLI using either Homebrew or npm”
   • [claimed-docs] “The Graphite CLI is fully compatible with git—just install it on an existing repository and begin using our suite of gt commands.”
   • [claimed-docs] “Run gt config to open an interactive menu which lets you configure your Graphite CLI.”

   proof ↗⚑ flag

   cubic~partialprobed6/10

   cubic exposes some programmatic surfaces — a documented Analytics API for PR-level metrics (cubic-docs-16), an official MCP server for agents to request reviews/triage issues (cubic-docs-8, cubic-probe-4), and a CLI for local review (cubic-probe-5) — which together let an AI-native user drive parts of the product programmatically. However, a probe for a general public REST/OpenAPI spec returned 404 on all standard paths, indicating no comprehensive documented public API beyond these narrower interfaces. Missing for 10: a full OpenAPI/REST API spec covering core product actions (not just analytics), independent hands-on verification of the Analytics API and MCP server working as documented.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round drawn
   Graphite—none0/10

   No evidence describes scoped or least-privilege API credential/token issuance for agents; authentication is via GitHub App installation (org-wide) or MCP setup, with no mention of granular permission scoping for AI agent credentials. missing for 10: scoped/least-privilege credential issuance mechanism, token/permission granularity controls, any documentation of credential scoping for agents.

   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization.”
   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization”
   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”

   proof ↗⚑ flag

   cubic—none0/10

   cubic documents role-based access control for human team members managing subscriptions/settings (cubic-docs-56) and offers an MCP server/Analytics API, but there is no evidence of any mechanism to issue scoped or least-privilege API credentials/tokens specifically for an agent's use.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings. Every team member has…”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Graphite
   Graphite~partialprobed6/10

   Graphite ships an official CLI (gt) with npm/Homebrew install and documented config, plus a documented MCP server (gt-mcp), giving AI-native users official tooling to build against. However, there is no evidence of a general-purpose SDK (e.g., Python/JS client library) or public API/OpenAPI spec — probes for openapi.json all 404'd. missing for 10: official SDK/client libraries beyond the CLI, public API reference/OpenAPI spec, independent developer corroboration of building against these interfaces.

   • [claimed-docs] “Install the Graphite CLI using either Homebrew or npm”
   • [claimed-docs] “The Graphite CLI is fully compatible with git—just install it on an existing repository and begin using our suite of gt commands.”
   • [claimed-docs] “Run gt config to open an interactive menu which lets you configure your Graphite CLI.”
   • [probe] “official MCP server documented at https://graphite.com/docs/gt-mcp”
   • [probe] “official CLI documented at https://graphite.com/docs/install-the-cli”
   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”

   proof ↗⚑ flag

   cubic—none0/10

   Cubic documents an MCP server, CLI, and Analytics API, but the evidence pack shows no official client SDKs (e.g., Python/JS libraries) for building against cubic, and explicit probes for an OpenAPI/swagger spec returned 404s, indicating no formal SDK surface is published.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Graphite—none0/10

   The only webhook-related evidence describes Graphite *receiving* GitHub webhooks for CI/mergeability updates (graphite-docs-24), not Graphite exposing its own webhook subscription system for external/AI-native consumers to receive events. No documentation of an outbound webhook API, event types, or subscription mechanism is present.

   • [claimed-docs] “Receive GitHub webhooks for real-time updates on CI status, mergeability, and push events.”

   proof ↗⚑ flag

   cubic—none0/10

   No evidence of a webhook subscription mechanism; cubic offers an Analytics API, MCP server, and GitHub comment interactions but nothing about outbound event webhooks. OpenAPI/webhook probes returned 404s, and no docs mention webhook subscriptions.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to cubic
   Graphite✓fullcommunity8/10

   Graphite ships AI Reviews that automatically analyze PRs and suggest fixes, a Graphite Chat that summarizes changes, suggests fixes, and explains code context, plus a dedicated 'Insights' feature to measure and optimize developer productivity — all directly generating AI insights/suggestions from repo data. Community feedback largely praises the stacking workflow with only general skepticism about AI additions, not a concrete failure of the insight/suggestion features themselves. Missing for 10: independent hands-on validation specifically of the Insights analytics dashboard and richer detail on what data-driven suggestions it surfaces beyond code review.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “InsightsMeasure and optimize your team's developer productivity.”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”
   • [claimed-docs] “Ask Graphite to explain what changed in a pull request, highlight potential issues, or provide context about specific code sections.”
   • [claimed-docs] “Get help understanding and implementing feedback from your teammates and reviewers.”
   • [community] “This is annoying, Graphite's core feature of stacked PRs is really good despite all the AI things they've added around their review UI. I do…”
   • [community] “i mentioned a few months ago that it was a shame where graphite was headed re: AI... this appears to be the final nail in the original produ…”

   proof ↗⚑ flag

   cubic✓fullcommunity9/10

   cubic delivers extensive AI-generated insights: automated PR review comments flagging bugs/security issues, AI-generated PR summaries, an AI wiki that indexes the codebase into diagrams/docs, analytics dashboards (AI coding, AI review, delivery) with PR-level insight data, and issue-analysis that checks PRs against linked Jira/Linear tickets. A community reviewer corroborates the quality of these AI-generated technical explanations as more useful than generic LLM output. Missing for 10: independent large-scale benchmarking of insight accuracy beyond one HN anecdote.

   • [claimed-docs] “Spots bugs and improvements: Comments on bugs and improvements in pull requests”
   • [claimed-docs] “PR summaries: Generates PR descriptions based on code changes”
   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “cubic can automatically analyze your pull requests to see if they meet the requirements from your linked Linear or Jira issues.”
   • [claimed-docs] “The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to cubic
   Graphite~partialclaimed6/10

   Graphite documents automation that runs without manual intervention: AI review agent automatically reviews all new PRs once enabled (graphite-docs-18, graphite-docs-19) and a stack-aware merge queue that lands PRs in the background (graphite-docs-10), plus Agents that autonomously generate PRs from a prompt (graphite-docs-12). This is real background automation, but scoped narrowly to PR review/merge events rather than a general-purpose 'set up any automation' framework with custom triggers/scheduling. Missing for 10: evidence of configurable triggers/schedules beyond PR events, and independent/hands-on confirmation that these automations reliably run unattended over time.

   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “Our stack-aware merge queue lands PRs in order and keeps branches green, helping you gain momentum.”
   • [claimed-docs] “Describe what you want built or fixed in plain language, and Agents will pull context from your repository, generate the changes, and open a…”

   proof ↗⚑ flag

   cubic✓fullclaimed8/10

   cubic automatically reviews every new PR without manual trigger, runs codebase-wide scans deploying many agents, can auto-fix issues and auto-approve PRs, and continuously learns from feedback—all happening in the background once installed, per docs-1, docs-4, docs-6, docs-12, docs-29, docs-52. This matches the story of autonomous background automation for code review workflows. Missing for 10: independent/hands-on verification that these automations run reliably unattended over time, and clearer detail on scheduling/triggers beyond PR events.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “Enable auto-approval to let cubic approve PRs that meet your review policy.”
   • [claimed-docs] “cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [claimed-docs] “cubic automatically learns when you: Reply to its comments... React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noi…”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Graphite
   Graphite✓fullcommunity8/10

   Graphite documents two built-in AI assistant surfaces: 'Graphite Agents' that take plain-language task descriptions, pull repo context, generate changes, and open a draft PR (graphite-docs-12, graphite-docs-22), and 'Graphite Chat' that can be asked to summarize PRs, suggest/apply fixes, and diagnose CI failures (graphite-docs-6/7/8/15/21) — directly matching task delegation to a built-in assistant. Community evidence shows real usage of Graphite generally but is skeptical/critical of the AI additions rather than confirming hands-on success (graphite-comm-10, graphite-comm-13), so independent corroboration of the delegation flow itself is thin. Missing for 10: independent/hands-on verification that Agents reliably complete delegated tasks end-to-end, and detail on failure modes.

   • [claimed-docs] “Describe what you want built or fixed in plain language, and Agents will pull context from your repository, generate the changes, and open a…”
   • [claimed-docs] “Make direct code changes right from your PR page. Click Agent on the right side of the PR to get started.”
   • [claimed-docs] ““Summarize the changes in this PR””
   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “Diagnose and resolve failing checks directly from your PR page with full context from your CI results.”
   • [claimed-docs] “Find related files, understand dependencies, and get context from other PRs without switching tabs.”
   • [claimed-docs] “Ask Graphite to explain what changed in a pull request, highlight potential issues, or provide context about specific code sections.”
   • [community] “This is annoying, Graphite's core feature of stacked PRs is really good despite all the AI things they've added around their review UI. I do…”
   • [community] “i mentioned a few months ago that it was a shame where graphite was headed re: AI... this appears to be the final nail in the original produ…”

   proof ↗⚑ flag

   cubic✓fullcommunity7/10

   cubic acts as a built-in AI teammate that users can direct with explicit commands (e.g. '@cubic-dev-ai review this PR', triggering ultrareview, asking it to generate and push a fix, replying for clarification, enabling auto-approval, or running codebase scans that deploy AI agents), and a community reviewer corroborates that it does more than basic checks. Missing for 10: independent/hands-on verification of these delegated actions actually completing end-to-end, and evidence of broader (non-review) task delegation beyond the code-review domain.

   • [claimed-docs] “To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
   • [claimed-docs] “Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes,…”
   • [claimed-docs] “cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “Reply to a review comment to ask for clarification:”
   • [claimed-docs] “Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round drawn
   Graphite✓fullclaimed7/10

   Graphite Chat lets users ask natural-language questions and request fixes ('Summarize the changes', 'Ask for suggested fixes and apply them in one click'), and Graphite Agents let users 'describe what you want built or fixed in plain language' to generate a draft PR — both are documented natural-language interaction surfaces layered on top of the core git/CLI workflow. Missing for 10: independent/hands-on corroboration that NL commands reliably work in practice (community evidence focuses on the CLI stacking workflow, not the NL chat/agent features) and clarity on how much of daily operation still requires explicit `gt` CLI commands rather than NL.

   • [claimed-docs] ““Summarize the changes in this PR””
   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “Diagnose and resolve failing checks directly from your PR page with full context from your CI results.”
   • [claimed-docs] “Describe what you want built or fixed in plain language, and Agents will pull context from your repository, generate the changes, and open a…”
   • [claimed-docs] “Ask Graphite to explain what changed in a pull request, highlight potential issues, or provide context about specific code sections.”
   • [claimed-docs] “Make direct code changes right from your PR page. Click Agent on the right side of the PR to get started.”
   • [claimed-docs] “With Graphite Chat, you can ask for context on code changes, get instant feedback, and make edits directly from the chat interface without l…”

   proof ↗⚑ flag

   cubic✓fullclaimed7/10

   cubic supports natural-language interaction: commenting `@cubic-dev-ai review this PR`, replying to review comments to ask clarification or trigger fixes, and requesting an Ultrareview, plus MCP server integration letting a coding agent issue natural-language requests (review, triage, manage subscription) on cubic's behalf. This covers command-like NL operation across PR comments and agent tooling. missing for 10: independent/hands-on verification of NL command robustness beyond documented examples, and no evidence of a broader conversational/chat interface beyond structured comment triggers.

   • [claimed-docs] “To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
   • [claimed-docs] “Reply to a review comment to ask for clarification:”
   • [claimed-docs] “@cubic-dev-ai review this PR”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues. You can tag `@cubic-dev-ai` directly, or reply to cubi…”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”
   • [claimed-docs] “When a pull request needs extra scrutiny, you can ask cubic for an Ultrareview.”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Graphite—none0/10

   No evidence of an interactive API reference or runnable examples; OpenAPI/swagger probes returned 404 and no such documentation is mentioned anywhere in the pack.

   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”

   proof ↗⚑ flag

   cubic—none0/10

   There is an Analytics API mentioned but no evidence of an interactive API reference or runnable examples; probes explicitly show no OpenAPI/swagger spec found (all candidate paths 404), indicating no interactive API documentation exists.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Graphite—none0/10

   Probe explicitly found no OpenAPI/swagger spec at any standard path and no llms.txt, and no documentation references a machine-readable API spec download; only an MCP server and CLI are documented.

   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://graphite.com/llms.txt”

   proof ↗⚑ flag

   cubic—none0/10

   cubic has an Analytics API but there is no documented machine-readable OpenAPI spec or equivalent; a direct probe for openapi.json/swagger.json at standard paths returned 404 across all candidates.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   proof ↗⚑ flag

3. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Graphite—none0/10

   No evidence of any versioned API, API changelog, or documented deprecation policy — OpenAPI probes return 404 and no docs reference API versioning or deprecation practices.

   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”

   proof ↗⚑ flag

   cubic—none0/10

   There is an Analytics API mentioned, but no evidence of versioning scheme or a documented deprecation policy; the openapi probe returned 404s across all candidate paths, indicating no discoverable API spec/versioning docs.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   proof ↗⚑ flag

Ai authored

1. ai-native userThe reviewer holds the line on AI-generated PRs — it verifies agent-authored code at a volume no human team could review

   weight 2 · round to cubic
   Graphite~partialcommunity6/10

   Graphite's AI reviews automatically scan every PR with no configuration, offer custom rules/comment exclusions, and GT MCP explicitly supports breaking large AI-agent-generated changes into reviewable stacked PRs — directly addressing reviewing agent-authored code. However, evidence is entirely first-party docs with no independent benchmarking of review accuracy/volume specifically for AI-generated code, and community commentary shows some skepticism about the direction of AI features (though not a concrete failure report). Missing for 10: independent/hands-on validation of review quality at scale on AI-authored PRs specifically, and any metrics on catch-rate or false-positive rate.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “AI reviews powered by Graphite Agent help your team build better software by automatically reviewing pull requests and catching bugs before …”
   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”
   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [community] “i mentioned a few months ago that it was a shame where graphite was headed re: AI... this appears to be the final nail in the original produ…”

   proof ↗⚑ flag

   cubic✓fullcommunity8/10

   cubic is explicitly built to auto-review every PR, run deep Ultrareview/codebase scans deploying 'thousands of AI agents,' auto-fix and auto-approve, and surface analytics specifically tracking AI-authored code volume — directly matching the story of scaling review beyond human capacity. Community feedback (cubic-comm-1) corroborates real-world value, though cubic-comm-2 raises a substantive critique that YAML-based rules are less robust than code-based checks, a minor caveat rather than a contradiction of the core capability. Missing for 10: independent large-scale benchmark/study proving review quality holds at massive AI-PR volume, and more than two community data points.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “Flex capacity keeps GitHub PR AI reviews running after your workspace uses its included reviewed-line capacity.”
   • [claimed-docs] “The AI coding tab shows how AI assistants contribute to merged pull requests in your repositories.”
   • [claimed-docs] “The AI automatically scans every pull request for a wide range of issues, including logic errors, style inconsistencies, and potential secur…”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

Checks

1. ai-native userI define custom agentic pre-merge checks in plain language — 'docs updated', 'tests cover new paths' — that run on every PR

   weight 2 · round to cubic
   Graphite~partialclaimed5/10

   Graphite Agent supports 'Custom rules' where users define plain-language guidelines for the AI reviewer to follow on every PR (graphite-docs-5, graphite-docs-20/28), and AI reviews run automatically on all PRs with no configuration (graphite-docs-18/19). However, these are review comments/guidelines, not documented as blocking, pass/fail 'checks' that gate merge like a CI status (e.g., 'docs updated' or 'tests cover new paths' as enforced gates) — the merge queue and check-diagnosis features are separate from these custom rules. Missing for 10: explicit documentation of custom rules acting as blocking/required pre-merge gates rather than advisory review comments, and examples matching the exact 'docs updated'/'tests cover new paths' framing.

   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should **not** leave comments.”
   • [claimed-docs] “Unlimited AI Reviews * AI Review customizations * Automations * Merge Queue”

   proof ↗⚑ flag

   cubic✓fullcommunity7/10

   cubic's 'Custom agents' feature lets teams define plain-language review rules enforcing org-specific best practices, stored in cubic.yaml, applied automatically across every PR, with a community library for adoption — directly matching the story of custom agentic pre-merge checks defined in plain language. Missing for 10: no first-party example matching the exact 'docs updated' / 'tests cover new paths' phrasing, and no independent hands-on validation of how reliably these plain-text rules enforce (one community comment raises skepticism about plain-text rule reliability vs. hard-coded checks, though this is not a concrete failure report).

   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “Custom agents: Enforce your team's coding standards”
   • [claimed-docs] “You can also adopt existing agents from the community library with a single click.”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

Fixes

1. developerI turn a review finding into an applied fix — a committed patch or an agent-generated follow-up — without leaving the PR

   weight 3 · round to cubic
   Graphite✓fullclaimed7/10

   Docs explicitly describe applying AI-suggested fixes in one click from the PR review page and making direct agent-driven code changes without leaving the PR (docs-7, docs-22), plus diagnosing/resolving failing checks in-PR (docs-8). This directly matches the story of turning a review finding into an applied fix in-place. Missing for 10: independent/hands-on corroboration of the one-click apply-fix and in-PR agent edit flow (community evidence only covers stacking, not this AI-fix feature), and no detail on how committed-patch fixes are verified/tested post-apply.

   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “Make direct code changes right from your PR page. Click Agent on the right side of the PR to get started.”
   • [claimed-docs] “Diagnose and resolve failing checks directly from your PR page with full context from your CI results.”
   • [claimed-docs] “Describe what you want built or fixed in plain language, and Agents will pull context from your repository, generate the changes, and open a…”

   proof ↗⚑ flag

   cubic✓fullclaimed8/10

   cubic lets developers turn review findings into applied fixes directly in the PR: it can generate a fix and push it to the PR branch, offers a one-click 'Fix with cubic' button, and its coding-agent/MCP integration lets an agent read findings and generate follow-up fixes without leaving the PR workflow. Auto-resolve threads and interactive PR comments reinforce that the fix loop stays within the PR. Missing for 10: independent/hands-on verification of the auto-fix push actually working in practice beyond vendor docs, and more detail on failure/edge cases of the auto-fix flow.

   • [claimed-docs] “cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Auto-resolve threads: Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “Coding agents: Generate fixes when requested, using your configured provider”

   proof ↗⚑ flag

Handoff

1. ai-native userReview findings hand off cleanly to my coding agent — copyable fix prompts or direct integration with Claude Code, Cursor, or Codex

   weight 2 · round to cubic
   Graphite~partialprobed5/10

   Graphite offers its own Agent that applies suggested fixes in one click and opens draft PRs from review feedback, plus a GT MCP server that lets external AI agents interact with Graphite to create stacked PRs — this provides a form of agent handoff. However, there is no explicit documentation of copyable fix prompts or named integrations with Claude Code, Cursor, or Codex; the flow relies on Graphite's own in-house Agent or generic MCP tooling rather than a documented direct connector to those specific coding agents. Missing for 10: explicit copyable fix-prompt format, named integration/setup docs for Claude Code/Cursor/Codex, and independent evidence such handoffs work in practice.

   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “Make direct code changes right from your PR page. Click Agent on the right side of the PR to get started.”
   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”
   • [probe] “official MCP server documented at https://graphite.com/docs/gt-mcp”

   proof ↗⚑ flag

   cubic✓fullprobed8/10

   cubic explicitly supports both hand-off paths: the CLI reviews local changes and 'generates a prompt that your coding agent can use to fix them' (cubic-docs-7), and cubic's MCP server lets you 'connect cubic's MCP server to your coding agent' with named support for Cursor, Claude Code, VS Code, Codex, and Gemini CLI (cubic-docs-8, cubic-docs-35). PR-level auto-fix ('Fix with cubic') that pushes fixes directly to the branch (cubic-docs-4, cubic-docs-29, cubic-docs-53) and coding-agent skills (cubic-docs-17) further reinforce clean hand-off to agents. Missing for 10: independent/hands-on confirmation that the generated prompts or MCP flow work smoothly in practice, and no community evidence specifically validating the agent hand-off UX.

   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “Install and connect cubic in Cursor, Claude Code, VS Code, Codex, Gemini CLI, or another coding tool.”
   • [claimed-docs] “cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic skills give your coding agent instructions for reviewing code, handling PR comments, and using your team's codebase context.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Graphite
   Graphite~partialcommunity6/10

   Graphite's CLI and stacking model let users manipulate many branches/PRs at once (community confirms 'rebase multiple branches at the same time'), the merge queue lands multiple PRs in order, and cross-repo PR tracking/AI review runs across all PRs in a repo automatically. However, the AI/agent features (Graphite Agent, chat, fix suggestions) are documented as per-PR actions, not as a bulk/batch operation across many items simultaneously. Missing for 10: explicit bulk AI-agent operations (e.g., batch-generate or batch-fix across many PRs/repos in one command), and independent evidence of scale beyond git-stack rebasing.

   • [claimed-docs] “Our stack-aware merge queue lands PRs in order and keeps branches green, helping you gain momentum.”
   • [claimed-docs] “Stay up-to-date with PRs across many repos using custom filters and rules.”
   • [community] “Ive been using it since mote than a year and it has become part of my toolbelt. Especially the cli that allow to seemlessly rebase multiple …”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”

   proof ↗⚑ flag

   cubic~partialclaimed5/10

   cubic supports some bulk-scale automation — codebase scans that 'deploy thousands of AI agents to find bugs and vulnerabilities across your repository' (cubic-docs-12) and an Analytics API that aggregates PR-level data across many PRs (cubic-docs-16, cubic-docs-59) — but there is no evidence of user-triggered bulk operations like batch-fixing, batch-approving, or batch-triaging many PRs/items at once beyond per-PR auto-approval and auto-fix. Missing for 10: explicit bulk/batch action UI or API (e.g., select-many-and-fix, bulk approve across PRs), evidence of scale/performance at bulk volume, and independent confirmation of the codebase-scan bulk claim.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can chec…”
   • [claimed-docs] “Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   Graphite~partialclaimed5/10

   Graphite ships some rule/event-driven automation: AI review auto-triggers on new PRs with no configuration (docs-19, docs-18), custom rules constrain when the review agent comments (docs-5, docs-20, docs-28), and a named 'Automations' feature appears in pricing (docs-33) alongside webhook-driven CI/merge event handling (docs-24) and stack-aware merge queue automation (docs-10). However, there is no dedicated documentation describing a general-purpose rules engine where a user defines arbitrary event→action triggers beyond PR-review and merge behaviors. Missing for 10: dedicated docs for the 'Automations' feature explaining supported trigger events/actions, evidence of custom/arbitrary action definitions beyond review-comment suppression, and independent confirmation of automation reliability.

   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should **not** leave comments.”
   • [claimed-docs] “Unlimited AI Reviews * AI Review customizations * Automations * Merge Queue”
   • [claimed-docs] “Receive GitHub webhooks for real-time updates on CI status, mergeability, and push events.”
   • [claimed-docs] “Our stack-aware merge queue lands PRs in order and keeps branches green, helping you gain momentum.”

   proof ↗⚑ flag

   cubic~partialcommunity5/10

   cubic supports event-triggered automation within its code-review domain: PRs auto-trigger reviews, custom agents enforce rules on PRs, auto-approval and auto-fix run on policy conditions, and cubic.yaml configures behavior — but this is domain-specific (PR/code-review events) rather than a general-purpose rules engine for arbitrary events/actions that an AI-native user could define. Missing for 10: evidence of a generalized rule/trigger builder spanning arbitrary event sources and actions beyond PR review workflows, and independent hands-on validation of custom-agent rule reliability (community feedback questions robustness of YAML-based rules).

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
   • [claimed-docs] “Enable auto-approval to let cubic approve PRs that meet your review policy.”
   • [claimed-docs] “cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

3. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Graphite
   Graphite~partialclaimed5/10

   Graphite's AI Agents and GT MCP generate changes as ordinary PR/stack commits (graphite-docs-12, graphite-docs-22, graphite-docs-30), which are then subject to Graphite's git-based versioning, AI/human review (graphite-docs-4, graphite-docs-27) and standard git rollback (amend/rebase, graphite-docs-36). However there is no dedicated feature for versioning, auditing, or rolling back the automations/agent configurations themselves (e.g. custom review rules, agent settings) — the 'Automations' pricing bullet (graphite-docs-33) is undetailed. Missing for 10: explicit docs on automation config version history, audit trail of rule changes, and a rollback mechanism for automation behavior itself.

   • [claimed-docs] “Describe what you want built or fixed in plain language, and Agents will pull context from your repository, generate the changes, and open a…”
   • [claimed-docs] “Make direct code changes right from your PR page. Click Agent on the right side of the PR to get started.”
   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “AI reviews powered by Graphite Agent help your team build better software by automatically reviewing pull requests and catching bugs before …”
   • [claimed-docs] “Amend staged changes to the relevant commits in the current stack.”
   • [claimed-docs] “Unlimited AI Reviews * AI Review customizations * Automations * Merge Queue”

   proof ↗⚑ flag

   cubic~partialclaimed3/10

   cubic's configuration (custom agents, review policies) lives in a `cubic.yaml` file at the repo root, which implies it inherits standard git version control (commit history, diff, revert) for review and rollback, but there is no dedicated in-product versioning, audit trail, or rollback UI/feature described for cubic's automations (custom agents, auto-approval rules, etc.). Missing for 10: explicit in-product version history/changelog for custom agents or review policies, a documented rollback mechanism beyond generic git, and any review workflow specifically for automation configuration changes.

   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “Custom agents: Enforce your team's coding standards”

   proof ↗⚑ flag

Context

1. engineering leadThe reviewer understands changes that span multiple repositories or a large monorepo and reviews them coherently

   weight 2 · round to cubic
   Graphite~partialclaimed4/10

   Graphite offers cross-repo PR tracking with custom filters (docs-11) and a codebase-aware AI reviewer that pulls related files/dependencies/context from other PRs (docs-15, docs-16), which helps a lead follow changes broadly, but there is no evidence of explicit monorepo-scale review tooling, cross-repo stack visualization, or dependency mapping across repositories in a single coherent review flow. Missing for 10: monorepo-specific review features, cross-repo diff/stack visualization, and independent evidence that reviewers actually use it to understand large or multi-repo spans coherently.

   • [claimed-docs] “Stay up-to-date with PRs across many repos using custom filters and rules.”
   • [claimed-docs] “Find related files, understand dependencies, and get context from other PRs without switching tabs.”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”

   proof ↗⚑ flag

   cubic~partialclaimed7/10

   cubic explicitly ships cross-repo reviews (link related repositories so reviews can check shared APIs/schemas/docs) and codebase-wide indexing via AI wiki and codebase scans, which support coherent understanding of changes spanning repos or large codebases. However, evidence is entirely vendor docs with no independent/hands-on validation of monorepo-scale coherence, and the cross-repo feature description is thin (only checking shared APIs/schemas, not full monorepo-scale reasoning). Missing for 10: independent/hands-on evidence of multi-repo review coherence at scale, explicit monorepo support details, and any case study of large/complex spanning changes reviewed successfully.

   • [claimed-docs] “Link related repositories so reviews can check shared APIs, schemas, docs, or release work.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can chec…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”

   proof ↗⚑ flag

2. developerReview comments reflect the whole repository — call sites, related modules, existing conventions — not just the changed hunks

   weight 3 · round to Graphite
   Graphite✓fullclaimed7/10

   Graphite's AI review docs explicitly claim a 'codebase-aware AI code review agent' (docs-16) and Graphite Chat can 'find related files, understand dependencies, and get context from other PRs without switching tabs' (docs-15) plus explain code sections and highlight issues with repo context (docs-21), directly supporting whole-repo-aware review beyond the diff. Missing for 10: independent/hands-on validation that reviews actually surface call sites and existing conventions (not just vendor claims), and no explicit mention of 'existing conventions' detection.

   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”
   • [claimed-docs] “Find related files, understand dependencies, and get context from other PRs without switching tabs.”
   • [claimed-docs] “Ask Graphite to explain what changed in a pull request, highlight potential issues, or provide context about specific code sections.”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”

   proof ↗⚑ flag

   cubic~partialclaimed7/10

   cubic's docs describe repo-wide context mechanisms beyond the diff: it auto-detects context files (README, AGENTS.md, .cursorrules), links related repositories for cross-repo reviews of shared APIs/schemas, runs codebase scans across the whole repo, builds an AI wiki index of the codebase, and learns 'unwritten rules' from senior engineers' historical reviews and team feedback — all suggesting reviews draw on broader repository knowledge, not just changed hunks. However, no evidence explicitly confirms it traces call sites or cross-references unrelated modules within a single-repo review, and there's no independent/hands-on corroboration of this specific behavior. Missing for 10: explicit call-site/dependency-tracing evidence, independent verification that review comments actually cite non-hunk code.

   • [claimed-docs] “cubic automatically detects and uses context files in your repository, including `README.md`, `context.md`, `AGENTS.md`, `.cursorrules`”
   • [claimed-docs] “cubic automatically detects and uses context files in your repository, including `README.md`, `context.md`, `AGENTS.md`, `.cursorrules`, age…”
   • [claimed-docs] “Link related repositories so reviews can check shared APIs, schemas, docs, or release work.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can chec…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [claimed-docs] “cubic learns your team's unwritten rules from two sources: direct feedback on its comments, and patterns extracted from your senior engineer…”

   proof ↗⚑ flag

Memory

1. ai-native userThe reviewer builds a persistent memory of my team's conventions and past review decisions and applies it to future PRs

   weight 2 · round to cubic
   Graphite~partialclaimed4/10

   Graphite lets teams define persistent 'custom rules' and comment exclusions that the AI reviewer follows across future PRs, which is a form of encoded team convention (graphite-docs-5, graphite-docs-20), and AI reviews run automatically without reconfiguration per PR (graphite-docs-19). However, there is no evidence this memory is built from or updates based on past review decisions/outcomes—rules must be manually authored, not learned—so the 'past review decisions' half of the story is unsupported. missing for 10: evidence of automatic learning from historical review decisions, evidence of memory evolving over time without manual rule-writing, independent confirmation that custom rules persist and are applied consistently across many PRs.

   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”

   proof ↗⚑ flag

   cubic✓fullcommunity8/10

   cubic explicitly documents persistent memory: it learns from replies/reactions to its comments and from patterns in senior engineers' historical reviews, storing conventions in cubic.yaml and custom agents that persist across PRs and repos (cubic-docs-10,32,33,54,9,11,34). This directly matches the ai-native persona's desire for a reviewer that builds team-convention memory over time. Missing for 10: independent/hands-on verification that learned rules actually persist and improve accuracy over many PRs (one community comment questions whether YAML-based rules are robust vs. hard failures, cubic-comm-2), and no quantitative data on learning effectiveness.

   • [claimed-docs] “cubic automatically learns when you: Reply to its comments... React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noi…”
   • [claimed-docs] “Reply to its comments: Type a response explaining what cubic should do differently, and it remembers for next time”
   • [claimed-docs] “React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noise for your specific codebase”
   • [claimed-docs] “cubic learns your team's unwritten rules from two sources: direct feedback on its comments, and patterns extracted from your senior engineer…”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

Chat

1. developerI reply to the reviewer in the PR thread to ask questions, get explanations, or issue commands — and it answers in context

   weight 2 · round to cubic
   Graphite✓fullclaimed7/10

   Graphite Chat is documented to let developers ask questions, get explanations of changes, request suggested fixes, get help implementing reviewer feedback, and diagnose CI issues directly from the PR page in context — matching the interaction story closely (graphite-docs-6,7,8,15,21,29,35). Missing for 10: independent/hands-on user testimony specifically validating Graphite Chat's conversational quality (community evidence covers CLI/stacking, not chat interactions), and no detail on command-issuing reliability via replies.

   • [claimed-docs] ““Summarize the changes in this PR””
   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “Diagnose and resolve failing checks directly from your PR page with full context from your CI results.”
   • [claimed-docs] “Find related files, understand dependencies, and get context from other PRs without switching tabs.”
   • [claimed-docs] “Ask Graphite to explain what changed in a pull request, highlight potential issues, or provide context about specific code sections.”
   • [claimed-docs] “With Graphite Chat, you can ask for context on code changes, get instant feedback, and make edits directly from the chat interface without l…”
   • [claimed-docs] “Get help understanding and implementing feedback from your teammates and reviewers.”

   proof ↗⚑ flag

   cubic✓fullcommunity8/10

   Docs explicitly describe replying to cubic's PR comments to ask questions, get clarifications, issue fix commands, or trigger reviews/Ultrareview, with cubic responding in-thread and even learning from replies. This is well documented across multiple pages (interactive-comments, memory-and-learning, quickstart) and corroborated by a community user noting cubic gives deeper technical explanations than plain LLMs. missing for 10: independent hands-on verification of multi-turn contextual follow-up quality/accuracy in real threads.

   • [claimed-docs] “Reply to a review comment to ask for clarification:”
   • [claimed-docs] “Reply to a review comment to ask for clarification”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues. You can tag `@cubic-dev-ai` directly, or reply to cubi…”
   • [claimed-docs] “Reply to its comments: Type a response explaining what cubic should do differently, and it remembers for next time”
   • [claimed-docs] “When a pull request needs extra scrutiny, you can ask cubic for an Ultrareview.”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

Control

1. developerI control when reviews run — skip drafts, trigger on demand, filter by branch or label — so the bot shows up only when wanted

   weight 1 · round drawn
   Graphite~partialclaimed4/10

   Graphite lets teams turn AI review on per selected repository and use custom rules/comment exclusions to shape what the Agent flags (graphite-docs-19, graphite-docs-5, graphite-docs-20), giving some control over when/where the bot comments. However there is no documented ability to skip draft PRs, trigger a review on demand, or filter specifically by branch or label as the story requires. Missing for 10: draft-PR skip toggle, on-demand/manual trigger command, and branch/label-based filtering rules.

   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should **not** leave comments.”

   proof ↗⚑ flag

   cubic~partialclaimed4/10

   cubic clearly supports on-demand triggering (@cubic-dev-ai review this PR, Ultrareview on demand) and configurable behavior via cubic.yaml (ignore patterns, review behavior), giving developers some control over when reviews run. However there is no explicit evidence of skipping draft PRs or filtering by branch/label — cubic.yaml's 'ignore patterns' are documented generically, not tied to draft/branch/label filters. Missing for 10: explicit draft-PR skip setting, branch-based trigger rules, label-based filtering documentation.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
   • [claimed-docs] “When a pull request needs extra scrutiny, you can ask cubic for an Ultrareview.”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes a…”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to cubic
   Graphite~partialprobed4/10

   Graphite ships a git-compatible CLI (`gt` commands) covering the core stacking workflow and an MCP server that lets AI agents create stacked PRs programmatically, but there is no documented public REST/GraphQL API (openapi probe returned 404 on all candidate paths) covering UI-only features like AI review customization, Insights, merge queue configuration, or Graphite Chat — these appear web/GUI-only. missing for 10: a documented general-purpose API or OpenAPI spec exposing AI reviews, custom rules, insights, and merge queue equivalently to the UI; evidence that MCP/CLI cover the full breadth of UI functionality rather than just stacking.

   • [claimed-docs] “The Graphite CLI is fully compatible with git—just install it on an existing repository and begin using our suite of gt commands.”
   • [claimed-docs] “The Graphite CLI is a tool to help you break up large engineering tasks into a series of small, incremental code changes directly from the c…”
   • [claimed-docs] “GT MCP allows AI agents to automatically create stacked PRs, breaking down large AI-generated changes into smaller, reviewable stacked pull …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”
   • [probe] “official MCP server documented at https://graphite.com/docs/gt-mcp”
   • [probe] “official CLI documented at https://graphite.com/docs/install-the-cli”
   • [claimed-docs] “InsightsMeasure and optimize your team's developer productivity.”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”

   proof ↗⚑ flag

   cubic~partialprobed5/10

   cubic exposes some programmatic surfaces beyond the UI — an Analytics API for PR-level metrics, an official MCP server for review findings/PR reviews/triage/subscription management, and a CLI for local review — but there is no general public REST/OpenAPI covering full platform functionality (probe found openapi.json/swagger.json all 404), so many UI features (wiki, custom agents config, integrations, analytics dashboards) lack documented API parity. missing for 10: a comprehensive public API/OpenAPI spec covering all UI capabilities, evidence that wiki/integrations/custom-agent configuration can be done via API, and confirmation that Analytics API + MCP together achieve full UI parity.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Graphite
   Graphite~partialcommunity4/10

   Graphite stores stacking metadata directly in git refs and its CLI is fully git-compatible, meaning core stack/branch data is inherently portable and not locked in a proprietary format (graphite-docs-3, graphite-comm-6), and community members have in fact migrated away to alternatives like git-spice/jujutsu without apparent data-loss complaints (graphite-comm-13). However, there is no explicit documented export feature for other Graphite-held data (AI review comments, insights/analytics, custom rules configs) in open formats. Missing for 10: a documented data-export tool/API for non-git data (reviews, insights, settings), explicit open-format guarantees, and hands-on confirmation of a full account data export.

   • [claimed-docs] “The Graphite CLI is fully compatible with git—just install it on an existing repository and begin using our suite of gt commands.”
   • [community] “The main thing I found to be an improvement is that Graphite maintains all the stacking metadata in git refs. With the other tools, I did no…”
   • [community] “i mentioned a few months ago that it was a shame where graphite was headed re: AI... this appears to be the final nail in the original produ…”

   proof ↗⚑ flag

   cubic—none0/10

   Cubic is a code review/analysis platform whose data (review findings, PR comments, analytics, wiki) lives in GitHub, Jira, Notion, etc.; there is no evidence of a data export feature for users to download their cubic-generated data in open formats. The Analytics API (cubic-docs-16) offers programmatic access to some metrics but this is not documented as a full data export/portability mechanism, and no evidence addresses exporting AI wiki content, review history, or memory/learning data.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round drawn
   Graphite—none0/10

   No evidence indicates Graphite's source code is published under an open license; Graphite is a commercial SaaS/CLI product with docs, pricing, and GitHub App integration, but nothing about an open-source repository or license.

   ⚑ flag

   cubic—none0/10

   No evidence indicates cubic's source code is open or under an open license; cubic appears to be a closed, commercial SaaS product with SOC2 compliance and privacy policies but no public repository or license mentioned.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Graphite—none0/10

   Graphite is a cloud SaaS product (CLI + hosted review/merge queue service) with no evidence of a self-hostable server/core; docs describe hosted authentication via GitHub App, cloud-based AI review, and pricing tiers, none of which mention on-prem or self-hosted deployment options.

   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization.”
   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization”
   • [claimed-docs] “Unlimited AI Reviews * AI Review customizations * Automations * Merge Queue”
   • [probe] “PROBE openapi: all candidate paths 404 (https://graphite.com/openapi.json, https://graphite.com/swagger.json, https://graphite.com/api/opena…”

   proof ↗⚑ flag

   cubic—none0/10

   cubic is presented entirely as a hosted SaaS (GitHub app, cloud-based review engine, subscription/seats, analytics API); there is no evidence of a self-hosted/on-prem deployment option, Docker image, or open-source core anywhere in the docs.

   ⚑ flag

Platforms

1. developerThe reviewer installs as a GitHub/GitLab app and posts reviews as native inline comments on my pull requests within minutes

   weight 3 · round to cubic
   Graphite~partialcommunity6/10

   Graphite documents GitHub App installation, automatic AI reviews on all new PRs with no configuration needed and quick 'few clicks' setup (graphite-docs-9, graphite-docs-18, graphite-docs-19), and comment exclusion rules imply it posts comments directly on PRs. However, there is no GitLab app support — community evidence explicitly notes Graphite lacks GitLab integration (graphite-comm-4) — and no explicit confirmation that comments are rendered as native inline PR comments or evidence of real-world review latency. Missing for 10: GitLab app support, explicit inline-comment rendering confirmation, independent verification of 'within minutes' turnaround.

   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization.”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [community] “I've followed Graphite for a while, and I just wish they supported GitLab. I know why they don't, but my current employer uses it and I've g…”

   proof ↗⚑ flag

   cubic✓fullcommunity8/10

   Docs confirm installation as a GitHub/GitLab app with automatic reviews on new PRs, inline PR comments (@cubic-dev-ai, interactive comments, Fix with cubic), and a quickstart flow explicitly framed as 'minutes' with a free trial. Community feedback corroborates real-world usefulness of PR-level comments. Missing for 10: independent third-party confirmation of install speed and hands-on GitLab app usage (most evidence is first-party docs).

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Spots bugs and improvements: Comments on bugs and improvements in pull requests”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Get started with cubic AI code review in minutes.”
   • [claimed-docs] “Post this comment on GitHub to start a review: text theme={null} @cubic-dev-ai review this PR ”
   • [claimed-docs] “7 days free, no credit card required.”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

Suggestions

1. developerReview comments include committable suggested diffs I can apply with one click

   weight 3 · round drawn
   Graphite✓fullclaimed7/10

   Graphite's docs explicitly describe AI review suggestions with one-click apply ('Ask for suggested fixes and apply them in one click right from the review page') and AI reviews that 'suggest fixes instantly,' matching the story's core capability. Missing for 10: independent/hands-on confirmation that the applied fix is an actual committable diff (vs. just a chat suggestion) and no community citation validating the one-click apply UX in practice.

   • [claimed-docs] “Ask for suggested fixes and apply them in one click right from the review page.”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”

   proof ↗⚑ flag

   cubic✓fullclaimed7/10

   Cubic explicitly supports one-click fixes: reviewers can click 'Fix with cubic' and cubic generates the fix and pushes it directly to the PR branch (cubic-docs-4, cubic-docs-29, cubic-docs-53), fulfilling the core 'one-click apply' story for review comments. Missing for 10: no evidence of an inline GitHub-style suggested-diff block shown for manual approval before commit, and no independent/hands-on corroboration of this specific flow beyond first-party docs.

   • [claimed-docs] “cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Coding agents: Generate fixes when requested, using your configured provider”

   proof ↗⚑ flag

Summaries

1. developerEvery PR gets an auto-generated summary and change walkthrough so human reviewers orient fast

   weight 2 · round to cubic
   Graphite~partialclaimed6/10

   Graphite auto-runs AI reviews on every PR with no configuration needed (graphite-docs-4, graphite-docs-18, graphite-docs-19) and Graphite Chat can generate a PR summary/walkthrough on request ('Summarize the changes in this PR', 'explain what changed... highlight potential issues' — graphite-docs-6, graphite-docs-21, graphite-docs-15). However the summary/walkthrough capability appears to be a chat-driven, on-demand feature rather than an automatically-posted summary comment on every PR, and no evidence shows a structured 'walkthrough' artifact attached automatically like some competitors. Missing for 10: evidence of an automatically-posted summary/walkthrough comment on every PR (not just on-demand chat), and independent/hands-on confirmation of this specific behavior.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] ““Summarize the changes in this PR””
   • [claimed-docs] “Ask Graphite to explain what changed in a pull request, highlight potential issues, or provide context about specific code sections.”
   • [claimed-docs] “Find related files, understand dependencies, and get context from other PRs without switching tabs.”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”

   proof ↗⚑ flag

   cubic✓fullcommunity9/10

   cubic explicitly generates PR summaries/descriptions from code changes automatically on every PR (docs-21, docs-57), plus keeps the summary visible alongside the diff while scrolling for easier orientation (docs-43), and community feedback corroborates depth of explanations (cubic-comm-1). Missing for 10: independent/hands-on review specifically confirming summary accuracy or walkthrough quality at scale beyond docs and one community quote.

   • [claimed-docs] “PR summaries: Generates PR descriptions based on code changes”
   • [claimed-docs] “cubic helps your team spend less time writing PR descriptions automatically by generating clear, concise summaries.”
   • [claimed-docs] “Now, the group description stays beside the diff as you scroll, so you can read the code and its explanation together.”
   • [claimed-docs] “Spots bugs and improvements: Comments on bugs and improvements in pull requests”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

Updates

1. developerPushing new commits triggers an incremental re-review that tracks what was fixed instead of repeating old comments

   weight 2 · round to cubic
   Graphite—none0/10

   Docs confirm Graphite Agent automatically reviews all new pull requests and re-reviews on updates, but no evidence describes tracking which prior comments were resolved versus re-flagging them, or any incremental diff-aware re-review logic distinguishing fixed vs. unfixed issues.

   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “AI reviews powered by Graphite Agent help your team build better software by automatically reviewing pull requests and catching bugs before …”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic auto-reviews new PRs and auto-resolves threads when issues are fixed (cubic-docs-1, cubic-docs-20), and its memory/learning system means feedback and prior comments inform future reviews (cubic-docs-10, cubic-docs-54), which together imply incremental re-review behavior rather than repeating stale comments. However, there's no explicit documentation describing a re-review triggered specifically by new commits that diffs against prior findings or explicitly states old fixed issues won't be re-flagged. missing for 10: explicit docs on commit-triggered incremental re-review logic, confirmation that previously-flagged-and-fixed issues are suppressed on subsequent pushes, and independent/hands-on evidence of this specific workflow.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Auto-resolve threads: Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “cubic automatically learns when you: Reply to its comments... React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noi…”
   • [claimed-docs] “cubic learns your team's unwritten rules from two sources: direct feedback on its comments, and patterns extracted from your senior engineer…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Graphite—none0/10

   No evidence of data residency/region selection controls; docs cover AI opt-in/no-training privacy but never mention where data is stored or region choice.

   ⚑ flag

   cubic—none0/10

   No evidence of data residency/region selection options in cubic's documentation; privacy/security docs mention SOC 2 compliance and no third-party model training, but nothing about choosing storage region or data residency controls.

   • [claimed-docs] “Privacy & security: "No third-party model training on Customer Code — Our AI model providers (e.g., OpenAI, Anthropic) contractually commit …”
   • [claimed-docs] “Privacy & security: "cubic is SOC 2 Type 1 compliant, demonstrating our commitment to security and trust for our customers. We maintain comp…”

   proof ↗⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Graphite✓fullclaimed8/10

   Graphite's docs explicitly state AI features are opt-in, do not train on user data, and contractually prohibit its subprocessors (Anthropic, OpenAI) from training on customer data, plus an org-wide opt-out via support request. Missing for 10: independent/third-party verification of these claims and no self-serve UI toggle (requires emailing support to disable).

   • [claimed-docs] “AI privacy and security: Graphite's AI features "are opt-in and do not store or train on your data"; "Neither Graphite nor any of its subpro…”
   • [claimed-docs] “To disable AI features across your entire organization, please email support@graphite.com and request a complete block of all AI features fo…”

   proof ↗⚑ flag

   cubic✓fullclaimed8/10

   cubic's privacy/security docs explicitly state model providers contractually commit to not train on customer code, and offer a full opt-out to block AI features entirely for a workspace. missing for 10: independent/third-party audit confirming the no-training claim, and detail on how the opt-out mechanism is enforced technically.

   • [claimed-docs] “Privacy & security: "No third-party model training on Customer Code — Our AI model providers (e.g., OpenAI, Anthropic) contractually commit …”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to cubic
   Graphite—none0/10

   Evidence shows a privacy statement about not training on data (opt-in, no training), but there is no mention of data retention controls, deletion mechanisms, or user-facing settings to purge stored data — the core of this story is unaddressed.

   ⚑ flag

   cubic~partialclaimed3/10

   cubic's privacy/security docs mention no third-party model training and the ability to block AI features for a workspace, showing some data-handling controls, but there is no explicit mention of data retention periods, deletion requests, or a self-service deletion mechanism. missing for 10: explicit retention policy, user-initiated deletion process, confirmation of deletion timelines/scope.

   • [claimed-docs] “Privacy & security: "No third-party model training on Customer Code — Our AI model providers (e.g., OpenAI, Anthropic) contractually commit …”
   • [claimed-docs] “Privacy & security: "cubic is SOC 2 Type 1 compliant, demonstrating our commitment to security and trust for our customers. We maintain comp…”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Graphite—none0/10

   Evidence covers AI-feature opt-in/no-training privacy policy (graphite-supp-1) but nothing documents a telemetry/usage-tracking opt-out mechanism for the CLI or platform itself. missing for 10: explicit telemetry/usage-analytics opt-out setting or documentation, any CLI flag or config for disabling usage tracking.

   ⚑ flag

   cubic—none0/10

   Evidence covers data-training and access-control privacy commitments (no third-party model training, SOC2 compliance, ability to block AI features workspace-wide) but no documented telemetry/usage-tracking toggle or opt-out mechanism specifically for product analytics/telemetry.

   ⚑ flag

Analytics

1. engineering leadI see dashboards of findings, acceptance rates, and review coverage across my org

   weight 1 · round to cubic
   Graphite~partialclaimed3/10

   Graphite docs reference an 'Insights' feature to 'measure and optimize your team's developer productivity' and a way to track PRs across repos, suggesting some org-level visibility, but there is no documentation describing dashboards for AI-review findings, acceptance rates of suggestions, or review-coverage metrics specifically. Missing for 10: concrete dashboard screenshots/specs for findings and acceptance-rate tracking, review-coverage metrics, and any independent corroboration of the Insights feature's content.

   • [claimed-docs] “InsightsMeasure and optimize your team's developer productivity.”
   • [claimed-docs] “Measure and optimize your team’s developer productivity.”
   • [claimed-docs] “InsightsMeasure and optimize your team’s developer productivity.”
   • [claimed-docs] “Insights Measure and optimize your team’s developer productivity.”
   • [claimed-docs] “Stay up-to-date with PRs across many repos using custom filters and rules.”

   proof ↗⚑ flag

   cubic✓fullclaimed7/10

   cubic's Analytics dashboard explicitly covers PR-level findings/fixes, AI coding and AI review impact tabs, and delivery/effectiveness across repos, directly matching the engineering-lead dashboard story (cubic-docs-16, 41, 42, 59, 60). Missing for 10: explicit org-wide rollup UI screenshots, exact 'acceptance rate' terminology/metric definition, and independent/hands-on corroboration beyond vendor docs.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “The AI coding tab shows how AI assistants contribute to merged pull requests in your repositories.”
   • [claimed-docs] “The AI review tab shows whether cubic reviews are helping your team ship better code faster.”
   • [claimed-docs] “The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
   • [claimed-docs] “The Delivery and effectiveness tab focuses on how quickly PRs move from creation to merge and where bottlenecks appear.”

   proof ↗⚑ flag

Gates

1. engineering leadThe reviewer can gate merges — a required status check or blocking review that enforces resolution of critical findings

   weight 2 · round to Graphite
   Graphite~partialclaimed5/10

   Graphite offers merge queue and AI review functionality that surfaces issues, plus CI status checks via GitHub webhooks, but the evidence does not document a specific 'required status check' or 'blocking review' setting that enforces resolution of AI/critical findings before merge — the merge queue is about ordering/keeping branches green rather than gating on unresolved findings. missing for 10: explicit documentation of a required-check/blocking-review policy tied to AI review findings, admin controls to enforce this gate, and independent confirmation it blocks merges when findings are unresolved.

   • [claimed-docs] “Our stack-aware merge queue lands PRs in order and keeps branches green, helping you gain momentum.”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “Receive GitHub webhooks for real-time updates on CI status, mergeability, and push events.”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”

   proof ↗⚑ flag

   cubic—none0/10

   Cubic documents auto-approval (skipping human review for low-risk PRs) and auto-resolving comment threads, but there is no evidence of a required GitHub status check or blocking review policy that prevents merge until critical findings are resolved — the auto-approval feature actually works in the opposite direction (approving rather than blocking). Missing for full credit: documentation of a required/blocking check integration, branch-protection enforcement, or explicit 'block merge on critical findings' policy.

   • [claimed-docs] “Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
   • [claimed-docs] “Auto-resolve threads: Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”

   proof ↗⚑ flag

Detection

1. developerThe reviewer catches real bugs in my PR — logic errors, race conditions, broken edge cases — not just style nits

   weight 3 · round to cubic
   Graphite~partialcommunity4/10

   Graphite's docs claim its AI reviewer 'identifies potential issues,' 'catches bugs,' and is 'codebase-aware,' but no evidence—vendor or independent—specifically demonstrates it catching logic errors, race conditions, or edge-case bugs versus superficial/style comments. One community comment expresses skepticism that the AI review features add lasting value, but this is general sentiment, not a concrete counter-example, so it doesn't rise to disputed. missing for 10: independent/hands-on examples of the reviewer catching genuine logic/concurrency bugs, benchmark or comparison data on false-positive/style-vs-substance ratio.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [community] “This is annoying, Graphite's core feature of stacked PRs is really good despite all the AI things they've added around their review UI. I do…”

   proof ↗⚑ flag

   cubic✓fullcommunity7/10

   Cubic's docs explicitly claim to catch logic errors, bugs, and security vulnerabilities (not just style), with deep Ultrareview passes for complex refactors, and one independent HN commenter corroborates that it 'provides more technical explanations than just basic checks' and is 'really powerful.' However, race conditions and specific edge-case handling are not explicitly evidenced, and most support is vendor documentation rather than hands-on benchmarks. Missing for 10: independent benchmark/hands-on evidence of catching race conditions or subtle logic bugs specifically, broader third-party validation beyond a single HN comment.

   • [claimed-docs] “Spots bugs and improvements: Comments on bugs and improvements in pull requests”
   • [claimed-docs] “The AI automatically scans every pull request for a wide range of issues, including logic errors, style inconsistencies, and potential secur…”
   • [claimed-docs] “When a pull request needs extra scrutiny, you can ask cubic for an Ultrareview.”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes a…”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

Learning

1. developerPush back on a bad review comment and the reviewer learns — it stops repeating the same rejected feedback

   weight 2 · round to cubic
   Graphite~partialclaimed4/10

   Graphite offers 'comment exclusions' and 'custom rules' letting developers manually configure the AI reviewer to stop leaving certain kinds of comments, which can approximate 'the reviewer learns' — but this is a manual rule-writing workaround, not an automatic learning loop triggered by pushing back in a review thread. missing for 10: evidence of automatic memory/learning from in-thread pushback, evidence that a rejected comment is not repeated without manual rule creation, any hands-on/community confirmation this actually works as claimed.

   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”

   proof ↗⚑ flag

   cubic✓fullcommunity7/10

   cubic explicitly documents that replying to its comments teaches it 'what to do differently' and it 'remembers for next time,' with learning drawn from direct feedback and thumbs up/down reactions plus senior engineers' review patterns — directly matching the story of pushing back and the reviewer not repeating rejected feedback. However, this is entirely first-party documentation with no independent/hands-on confirmation that the learning actually persists or stops repeat comments in practice; one community comment expresses general skepticism about YAML-based rule interpretation but doesn't concretely show the learning failing. Missing for 10: independent hands-on verification that cubic stops repeating rejected feedback, and details on how long/broadly the learned preference applies.

   • [claimed-docs] “cubic automatically learns when you: Reply to its comments... React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noi…”
   • [claimed-docs] “Reply to its comments: Type a response explaining what cubic should do differently, and it remembers for next time”
   • [claimed-docs] “React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noise for your specific codebase”
   • [claimed-docs] “cubic learns your team's unwritten rules from two sources: direct feedback on its comments, and patterns extracted from your senior engineer…”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

Noise

1. engineering leadThe reviewer keeps noise low — few false positives, deduplicated comments, severity labels — so my team doesn't tune it out

   weight 3 · round to cubic
   Graphite~partialcommunity5/10

   Graphite lets teams reduce noise via custom rules and comment exclusions (specifying when Agent should not comment) and codebase-aware review context, which addresses false positives to some degree, but there is no documented deduplication mechanism or severity/priority labeling on comments, and community reaction (e.g. mixed sentiment about the AI review additions) is vague rather than a concrete accuracy failure. missing for 10: explicit severity/priority labeling of comments, deduplication logic across review passes, independent benchmarking or hands-on evidence of false-positive rates.

   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should **not** leave comments.”
   • [claimed-docs] “Get immediate, actionable feedback with Graphite’s codebase-aware AI code review agent.”
   • [community] “This is annoying, Graphite's core feature of stacked PRs is really good despite all the AI things they've added around their review UI. I do…”
   • [community] “i mentioned a few months ago that it was a shame where graphite was headed re: AI... this appears to be the final nail in the original produ…”

   proof ↗⚑ flag

   cubic~partialcommunity6/10

   cubic documents concrete noise-reduction mechanisms: it learns from thumbs-up/down and reply feedback to calibrate 'what's useful vs noise' (cubic-docs-10, cubic-docs-32/33), learns unwritten rules from senior engineers' historical reviews (cubic-docs-54), supports ignore patterns/custom agents via cubic.yaml (cubic-docs-11), and auto-resolves threads once issues are fixed (cubic-docs-20). One community reviewer corroborates quality/technical depth (cubic-comm-1), while another raises skepticism about YAML-based rule reliability (cubic-comm-2), though this doesn't concretely contradict the noise-reduction claims. Missing for 10: explicit severity labeling of comments, explicit deduplication-of-comments mechanism, and independent data/benchmarks on false-positive rates.

   • [claimed-docs] “cubic automatically learns when you: Reply to its comments... React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noi…”
   • [claimed-docs] “Auto-resolve threads: Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Reply to its comments: Type a response explaining what cubic should do differently, and it remembers for next time”
   • [claimed-docs] “React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noise for your specific codebase”
   • [claimed-docs] “cubic learns your team's unwritten rules from two sources: direct feedback on its comments, and patterns extracted from your senior engineer…”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

Security

1. security engineerReviews flag security problems in the diff — injection risks, leaked secrets, insecure patterns — alongside functional bugs

   weight 2 · round to cubic
   Graphite—none0/10

   Graphite's AI review docs describe catching 'bugs' and general 'potential issues' in PRs, but nothing in the evidence pack specifically claims detection of security-specific problems like injection risks, leaked secrets, or insecure coding patterns; custom rules/comment exclusions are the only customization levers mentioned, not security-focused presets.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “AI reviews powered by Graphite Agent help your team build better software by automatically reviewing pull requests and catching bugs before …”
   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”

   proof ↗⚑ flag

   cubic~partialcommunity6/10

   cubic docs explicitly claim it scans PRs for 'security vulnerabilities' alongside logic errors and style issues, and offers an 'Ultrareview' deep-pass mode explicitly recommended for security-sensitive changes, plus custom agents to enforce org-specific rules. However, there's no documented evidence of specific detection categories like secret leakage or injection-pattern examples, nor independent/hands-on evidence confirming accuracy on real security bugs (community quotes address general usefulness, not security-specific findings). Missing for 10: explicit mention of secret-scanning/injection-detection categories, and independent verification of security-finding accuracy.

   • [claimed-docs] “The AI automatically scans every pull request for a wide range of issues, including logic errors, style inconsistencies, and potential secur…”
   • [claimed-docs] “When a pull request needs extra scrutiny, you can ask cubic for an Ultrareview.”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes a…”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [community] “I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanat…”

   proof ↗⚑ flag

Cli

1. developerI run reviews from a CLI against local diffs or in CI scripts, with machine-readable output my tooling can consume

   weight 2 · round to cubic
   Graphite—none0/10

   Graphite's AI review capability is documented as PR-triggered via the GitHub App/web UI (automatically reviewing pull requests), not as a CLI command usable against local diffs or in CI scripts with machine-readable output. The `gt` CLI documented is for stack management (branch creation, submission, config) with no review subcommand or structured/JSON output format mentioned anywhere in the evidence.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization.”
   • [claimed-docs] “The Graphite CLI is a tool to help you break up large engineering tasks into a series of small, incremental code changes directly from the c…”
   • [claimed-docs] “Run gt config to open an interactive menu which lets you configure your Graphite CLI.”

   proof ↗⚑ flag

   cubic~partialprobed5/10

   cubic ships an official CLI (`cubic-docs-7`, `cubic-probe-5`) that reviews local diffs before push and outputs a prompt for a coding agent to fix issues, satisfying the 'local diff' half of the story. However there is no documented evidence of CI-specific usage (e.g., a CI mode/flag) or of structured machine-readable output (JSON/SARIF) that external tooling could consume — the CLI output is described as a natural-language prompt, not a machine-parseable format. missing for 10: CI integration docs/flags, machine-readable (JSON/SARIF) output format, examples of scripting/tooling consumption.

   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

Ide

1. developerI get the same review inside my IDE before I push, catching issues while the code is still in my editor

   weight 2 · round to cubic
   Graphite—none0/10

   Graphite's AI review (Agent) explicitly runs on pull requests after they are opened on GitHub, not inside the IDE before push; the only 'IDE' touchpoint documented is a GUI for visualizing stacks, not a pre-push review mechanism. No evidence of an IDE plugin or pre-commit hook that surfaces the same AI review before pushing.

   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”
   • [claimed-docs] “A GUI designed to make stacking visual and simple, right from your IDE.”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”

   proof ↗⚑ flag

   cubic✓fullprobed7/10

   cubic ships a dedicated CLI that "reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them" (cubic-docs-7, cubic-probe-5), plus IDE/agent integration via cubic skills and an MCP server that lets coding agents read review findings and codebase context (cubic-docs-8, cubic-docs-35, cubic-probe-4), directly matching the story of catching issues pre-push in the editor. Missing for 10: independent/hands-on validation of the CLI's pre-push review quality and no community evidence specifically confirming the IDE experience (community citations discuss PR-level review, not the local CLI).

   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “Install and connect cubic in Cursor, Claude Code, VS Code, Codex, Gemini CLI, or another coding tool.”
   • [claimed-docs] “cubic skills give your coding agent instructions for reviewing code, handling PR comments, and using your team's codebase context.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

Config

1. engineering leadI configure the reviewer with a versioned config file in my repo — path filters, per-path instructions, review profiles

   weight 3 · round to cubic
   Graphite~partialclaimed5/10

   Graphite supports custom rules and comment exclusions for the AI review agent (graphite-docs-5, graphite-docs-20), which covers per-repo instruction customization, but there is no evidence of a versioned config file checked into the repo, nor of path-based filters or multiple named review profiles selectable per path. missing for 10: evidence of a repo-committed/versioned config file format, path-level filtering rules, and support for multiple distinct review profiles.

   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “AI reviews can be enabled in just a few clicks, with no configuration required to start catching bugs in your pull requests.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”

   proof ↗⚑ flag

   cubic✓fullcommunity7/10

   cubic.yaml is documented as a versioned, repo-root config file that is the 'source of truth for AI review behavior, ignore patterns, PR descriptions, and custom agents,' directly covering path filters (ignore patterns) and review profiles (custom agents, Ultrareview). Custom context files (README.md, AGENTS.md, .cursorrules, .ai/ dirs) further support per-path/contextual instructions. missing for 10: an explicit documented example of per-path instruction syntax within cubic.yaml, and independent/hands-on verification of the config file working as described (one community comment even questions whether YAML-based rules are as robust as code-based checks).

   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “Custom agents: Enforce your team's coding standards”
   • [claimed-docs] “cubic automatically detects and uses context files in your repository, including `README.md`, `context.md`, `AGENTS.md`, `.cursorrules`”
   • [claimed-docs] “cubic automatically detects and uses context files in your repository, including `README.md`, `context.md`, `AGENTS.md`, `.cursorrules`, age…”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag

Governance

1. engineering leadI roll out org-level review defaults across hundreds of repos and manage exceptions centrally

   weight 1 · round drawn
   Graphite~partialclaimed5/10

   Graphite supports org-wide GitHub App installation and enabling AI review across 'selected repositories' with per-repo custom rules and comment exclusions, and org-wide AI-disable requires emailing support — but there is no documented centralized dashboard for setting org-level review defaults and managing per-repo exceptions at scale across hundreds of repos. missing for 10: evidence of a bulk/org-level policy management UI, audit of exceptions across many repos, and any customer testimonial about managing hundreds of repos centrally.

   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization.”
   • [claimed-docs] “Graphite Agent will now automatically review all new pull requests in the selected repositories”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should **not** leave comments.”
   • [claimed-docs] “To disable AI features across your entire organization, please email support@graphite.com and request a complete block of all AI features fo…”
   • [claimed-docs] “you'll need to authenticate by installing the Graphite App (a GitHub App) on your organization”

   proof ↗⚑ flag

   cubic~partialclaimed5/10

   cubic.yaml provides per-repo config (source of truth for review behavior, ignore patterns, custom agents) and custom agents/RBAC roles suggest some centralized governance, but evidence shows configuration is per-repository (cubic.yaml lives in each repo root) rather than an org-level policy pushed/enforced across hundreds of repos with a central exceptions dashboard. missing for 10: an org-wide policy/template propagation mechanism across many repos, a central exceptions-management UI/workflow, and independent evidence of usage at hundreds-of-repos scale.

   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings. Every team member has…”
   • [claimed-docs] “Custom agents: Enforce your team's coding standards”

   proof ↗⚑ flag

Rules

1. engineering leadI encode my team's own review guidelines — natural-language rules, AST patterns, or linked style guides — and the reviewer enforces them

   weight 2 · round to cubic
   Graphite~partialclaimed6/10

   Graphite's AI review docs confirm a 'Custom rules' feature letting teams define explicit natural-language guidelines for the review agent, plus 'comment exclusions' to tune behavior, which covers the natural-language rules part of the story. However, there is no evidence of AST-pattern-based rule definition or linking external/style-guide documents for enforcement. Missing for 10: AST pattern rule support, ability to link external style guides, and independent/hands-on confirmation that custom rules are reliably enforced.

   • [claimed-docs] “Custom rules allow you to define explicit guidelines for Graphite Agent to follow when reviewing your code.”
   • [claimed-docs] “Comment exclusions allow you to specify situations where Graphite Agent should not leave comments.”
   • [claimed-docs] “AI reviews analyze every pull request in your repositories, identifying potential issues and suggesting fixes instantly - no manual configur…”

   proof ↗⚑ flag

   cubic~partialcommunity7/10

   cubic supports engineering-lead-authored review rules via 'Custom agents' (natural-language rules enforcing team standards), a cubic.yaml as source of truth, auto-detected context files (README, context.md, AGENTS.md, .cursorrules) and cross-repo linking for shared style guides, plus adoption of community rule sets. However, there is no explicit evidence of AST-pattern-based rule authoring, and one community comment expresses skepticism that plain-text/YAML rules are a 'half-measure' versus more robust structural checks, though this is opinion rather than a documented failure. Missing for 10: explicit AST-pattern rule support, independent hands-on validation that custom agents reliably enforce guidelines in practice.

   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “Custom agents: Enforce your team's coding standards”
   • [claimed-docs] “You can also adopt existing agents from the community library with a single click.”
   • [claimed-docs] “cubic automatically detects and uses context files in your repository, including `README.md`, `context.md`, `AGENTS.md`, `.cursorrules`”
   • [claimed-docs] “cubic automatically detects and uses context files in your repository, including `README.md`, `context.md`, `AGENTS.md`, `.cursorrules`, age…”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [community] “The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to t…”

   proof ↗⚑ flag