Aider vs cubic

Agent access

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

   weight 2 · round to cubic
   Aider—none0/10

   Probes explicitly show no llms.txt (404) and no machine-readable docs endpoints (404s for .md docs and openapi), and no evidence of agent-oriented docs formats elsewhere in the pack.

   • [probe] “PROBE llms.txt: HTTP 404 at https://aider.chat/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://aider.chat/docs/usage.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://aider.chat/openapi.json, https://aider.chat/swagger.json, https://aider.chat/api/openapi.jso…”

   proof ↗⚑ flag

   cubic✓fullprobed9/10

   cubic hosts a dedicated llms.txt file at docs.cubic.dev/llms.txt (confirmed via live probe returning HTTP 200 with a documentation summary), directly enabling agents to be pointed at agent-oriented docs; this is reinforced by MCP server and CLI docs designed for agent consumption. Missing for 10: no independent/community confirmation of an agent successfully using llms.txt 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] “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 userRun the product headlessly / in CI for automation

   weight 2 · round to Aider
   Aider✓fullcommunity8/10

   Aider's scripting docs explicitly support headless/non-interactive use: `--message` for one-shot instructions that apply edits and exit, plus a Python API (`Coder.create`/`coder.run`) for programmatic/CI integration, alongside config via CLI switches, env vars, or .aider.conf.yml which suits automation pipelines. Community evidence corroborates interest in scriptable use (e.g., chaining PR review agents) though notes it's less commonly used that way. Missing for 10: no first-party CI/CD example (e.g., GitHub Actions workflow) or independent case study of Aider running fully unattended in a pipeline.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [community] “I only use Aider interactively, but I really should consider Aider in the 'scriptable' sense more... I might add another step after each PR …”

   proof ↗⚑ flag

   cubic~partialprobed6/10

   cubic automatically reviews PRs once installed (headless, event-triggered automation on GitHub) and ships a standalone CLI (`cubic review`) that can run local/pre-push checks, which could be scripted into CI. However, there's no explicit documentation of a CI/CD pipeline integration (e.g., GitHub Actions workflow, exit codes, non-interactive flags) confirming true headless CI usage beyond the GitHub-app webhook flow. missing for 10: explicit CI pipeline integration docs/examples, confirmation of non-interactive/exit-code behavior for CLI in automated pipelines.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [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] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Aider—none0/10

   No evidence in the pack that Aider supports connecting to MCP servers or using MCP-provided tools; its documented extensibility is via slash commands, scripting API, linters/tests, and web/voice input, not MCP.

   ⚑ flag

   cubic—none0/10

   All MCP-related evidence describes cubic acting as an MCP *server* that other coding agents/clients connect to (cubic-docs-15, cubic-docs-3, cubic-probe-3) — the reverse of this story, which asks whether a user can plug external MCP servers into cubic so it can consume their tools. No evidence shows cubic itself connecting to or invoking external MCP servers/tools.

   • [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…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   Aider—none0/10

   Aider is a coding agent itself (a CLI/chat tool that edits code), which per the rules places serving as an MCP server outside its natural role; however no evidence shows it running as an MCP server or exposing an official MCP endpoint. Evidence only covers Aider's own commands, scripting API, and integrations (voice, browser, web scraping) — none about MCP.

   ⚑ flag

   cubic✓fullprobed8/10

   cubic documents an official MCP server that lets a coding agent read review findings, codebase context, request PR reviews, triage issues, and even manage subscription/seats without leaving the MCP client, confirmed by a dedicated docs page (probe) and quickstart references. Missing for 10: independent/hands-on community confirmation that the MCP server works as described (all evidence is vendor 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…”
   • [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 Aider
   Aider✓fullprobed9/10

   Aider is itself a CLI tool, installed via pip/curl and driven entirely through command-line invocation, flags, scripting (--message), and config files/env vars, making it a native fit for AI-native, agentic workflows. missing for 10: independent third-party benchmarking of CLI robustness/versioning beyond docs and forum mentions.

   • [claimed-docs] “python -m pip install aider-install aider-install”
   • [claimed-docs] “curl -LsSf https://aider.chat/install.sh | sh”
   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an .aider.conf.yml file... Or by setting…”
   • [probe] “official CLI documented at https://aider.chat/docs/usage.html”

   proof ↗⚑ flag

   cubic✓fullprobed8/10

   cubic ships an official CLI (`cubic review`) that reviews local/uncommitted changes and generates fix prompts for coding agents, documented explicitly and confirmed by a docs probe; it also integrates with agent workflows via MCP. Missing for 10: independent hands-on verification of the CLI itself (community evidence covers other product aspects, not CLI usage) and broader CLI command documentation beyond the single review command.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [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 your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [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 drawn
   Aider~partialprobed6/10

   Aider documents a scriptable Python API (Coder.create/coder.run) and a CLI --message mode for programmatic, non-interactive driving, which serves as a public API surface for AI-native automation. However, probes confirm there is no REST/OpenAPI-style API or llms.txt (404s across all candidate endpoints), so 'documented public API' is limited to the Python scripting library and CLI flags rather than a formal service API. Missing for 10: a REST/HTTP or OpenAPI-documented API, and independent/hands-on validation of the scripting API in production use beyond docs.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”
   • [probe] “PROBE llms.txt: HTTP 404 at https://aider.chat/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://aider.chat/docs/usage.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://aider.chat/openapi.json, https://aider.chat/swagger.json, https://aider.chat/api/openapi.jso…”

   proof ↗⚑ flag

   cubic~partialprobed6/10

   cubic documents an MCP server (cubic-docs-15, cubic-probe-3) that lets an AI agent request PR reviews, read findings, and triage issues, plus an Analytics API (cubic-docs-20) for PR-level data and a CLI (cubic-probe-4) for local reviews — all documented, agent-drivable surfaces. However, probes for a formal public API spec (openapi/swagger) all returned 404 (cubic-probe-2), so there's no evidence of a comprehensive documented public REST/GraphQL API beyond these narrower interfaces. Missing for 10: a full public API reference/spec, broader programmatic control beyond analytics/MCP/CLI, and independent confirmation of API usage.

   • [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.”
   • [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 userBuild against official SDKs

   weight 2 · round to Aider
   Aider~partialclaimed5/10

   Aider ships a documented Python scripting interface (Coder.create/coder.run) and a --message CLI mode that let developers build automation on top of it, which functions as a de facto SDK for AI-native workflows. However, there's no dedicated multi-language SDK, versioned package for third-party integration, or independent corroboration of building products atop it beyond docs. missing for 10: dedicated SDK package/versioning beyond scripting.html snippet, independent developer reports of building against it, multi-language SDK support.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”

   proof ↗⚑ flag

   cubic—none0/10

   cubic documents an MCP server, CLI, and an Analytics API, but there is no evidence of official language SDKs (e.g., Python/JS client libraries) for building against cubic programmatically; the OpenAPI probe also returned 404s across candidate paths, suggesting no formal SDK/API spec is published.

   • [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…”
   • [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

Agentic features

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

   weight 2 · round to Aider
   Aider✓fullcommunity7/10

   Aider provides AI-generated code understanding, suggestions, and edits directly from the user's codebase via /ask, /architect, repo-map, and chat-based Q&A, with community reports confirming it effectively surfaces insights about unfamiliar codebases. missing for 10: no dedicated analytics/insights dashboard, no proactive suggestion surfacing beyond chat-driven queries, and independent evidence is limited to a single HN thread rather than broad corroboration.

   • [claimed-docs] “**/ask** Ask questions about the code base without editing any files.”
   • [claimed-docs] “**/map** Print out the current repository map”
   • [claimed-docs] “Aider uses a **concise map of your whole git repository** that includes the most important classes and functions along with their types and …”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “Aider can answer questions I can't search for via LSP, like 'what code would process the following URL' and similar.”

   proof ↗⚑ flag

   cubic~partialcommunity6/10

   Cubic generates AI-driven insights from a user's own code/PR data via automated reviews, Ultrareview, AI-powered codebase scans, an AI wiki that indexes the codebase, and an analytics dashboard summarizing AI coding/review impact (cubic-docs-4,13,18,20,21,22). However, community hands-on feedback is mixed, with several users noting a large share of AI-generated comments are irrelevant or low-value (cubic-comm-3,9), tempering claims of consistently useful insights. Missing for 10: independent benchmarking of insight accuracy, and confirmation that analytics/wiki insights are broadly praised rather than just described in docs.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [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] “The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
   • [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] “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…”
   • [community] “I've tried something similar in the past. The concept is cool, but so far the solutions I've seen are not so useful in terms of comments qua…”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”

   proof ↗⚑ flag

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

   weight 2 · round to cubic
   Aider~partialcommunity4/10

   Aider is fundamentally an interactive/scriptable pair-programming CLI, not a background automation scheduler; it can be invoked via --message or Python API for one-shot scripted runs, and community reports mention an experimental 'navigator-mode' adding autonomy akin to Claude Code, but there is no documented persistent background daemon, scheduler, or trigger-based autonomous execution. missing for 10: no first-party support for scheduled/triggered background jobs, no persistent autonomous loop or daemon mode, no evidence of unattended multi-step task execution without a human invoking a command each time.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [community] “I only use Aider interactively, but I really should consider Aider in the 'scriptable' sense more... I might add another step after each PR …”
   • [community] “Over the last two days, I've built out support for autonomy in Aider (a lot like Claude Code) that hybridizes with the rest of the app, uplo…”
   • [community] “It's... decidedly expensive to run an LLM this way right now (Gemini 2.5 Pro is your best bet) with Aider's navigator/autonomy mode, but cos…”

   proof ↗⚑ flag

   cubic✓fullclaimed8/10

   cubic ships several autonomous background automations: it auto-starts PR reviews on install (cubic-docs-4, cubic-docs-41), can auto-approve clean PRs under policy (cubic-docs-12, cubic-docs-35), runs codebase scans deploying many AI agents (cubic-docs-21), keeps an AI wiki current via rolling PRs (cubic-docs-23), does cross-repo checks (cubic-docs-37), and auto-purchases flex capacity to keep reviews running (cubic-docs-24) — all without manual triggering. Missing for 10: evidence of user-defined scheduled/cron-style custom automations beyond PR-triggered events, and independent hands-on confirmation that these autonomous flows run reliably unattended.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [claimed-docs] “cubic can approve clean pull requests automatically when your repository policy allows it. Start in shadow mode to see which PRs cubic would…”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”

   proof ↗⚑ flag

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

   weight 3 · round to Aider
   Aider✓fullcommunity9/10

   Aider's entire product is built around delegating coding tasks to an LLM assistant via chat commands (/ask, /architect, /run, /test), CLI --message scripting, and a scriptable Python API (coder.run), with community confirming real-world delegation use (codebase Q&A, autonomous 'navigator mode'). Missing for 10: more independent benchmarking of task delegation reliability beyond anecdotal HN comments.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “**/ask** Ask questions about the code base without editing any files.”
   • [claimed-docs] “**/architect** Enter architect/editor mode using 2 different models. If no prompt provided, switches to architect/editor mode.”
   • [claimed-docs] “/ask Ask questions about the code base without editing any files. If no prompt provided, switches to ask mode.”
   • [claimed-docs] “You can configure aider to run your test suite after each time the AI edits your code using the --test-cmd <test-command> and --auto-test sw…”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “I revisited Aider a couple of days ago, after going in circles with AutoGPT - which seemed to either forget or go lazy after a few prompts. …”
   • [community] “Over the last two days, I've built out support for autonomy in Aider (a lot like Claude Code) that hybridizes with the rest of the app, uplo…”

   proof ↗⚑ flag

   cubic✓fullclaimed7/10

   Cubic ships a built-in AI chat/assistant experience where users can delegate tasks — asking chat to 'tour this PR', adding code to AI chat for contextual Q&A, requesting one-click fixes ('Fix with cubic') that get generated and pushed automatically, and interacting via PR comments to trigger reviews or fixes. This is a genuine in-product assistant, not just an external agent integration. Missing for 10: independent/hands-on validation specifically of the chat-delegation UX (community evidence only covers review-comment quality, not the assistant/chat delegation flow), and no detail on task-completion reliability or scope limits of delegated tasks.

   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “The chat sidebar helps you quickly understand and navigate your pull requests (PRs) with intelligent, context-aware assistance directly with…”

   proof ↗⚑ flag

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

   weight 2 · round to Aider
   Aider✓fullcommunity8/10

   Aider is fundamentally natural-language driven: users type plain-English instructions in chat, via --message CLI flag, via voice command, or via #AI comments in watched files, and it executes edits accordingly, with community reports confirming real-world natural-language usage. missing for 10: no independent third-party benchmark of NL command robustness across edge cases, and some community reports note inconsistent quality/laziness in following instructions.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “Use the in-chat `/voice` command to start recording, and press `ENTER` when you’re done speaking. Your voice coding instructions will be tra…”
   • [claimed-docs] “AI! triggers aider to make changes to your code.”
   • [claimed-docs] “Rather than using /add to add a file inside the aider chat, you can simply put an #AI comment in it and save the file.”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “I revisited Aider a couple of days ago, after going in circles with AutoGPT - which seemed to either forget or go lazy after a few prompts. …”
   • [community] “Aider is the only tool I use for coding now with ChatGPT... It still suffers from ChatGPT laziness sometimes, you can see it retrying severa…”

   proof ↗⚑ flag

   cubic✓fullclaimed7/10

   cubic supports natural-language interaction via PR comments and chat: users can type commands like '@cubic-dev-ai review this PR', ask chat to 'tour this PR', reply to comments for clarification, request fixes, and connect an MCP server so a coding agent can trigger reviews and manage settings conversationally. Missing for 10: independent/hands-on evidence validating the quality and reliability of these NL interactions, and no evidence of broader free-form command coverage beyond the documented set of trigger phrases.

   • [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] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Post this comment on GitHub to start a review: text theme={null} @cubic-dev-ai review this PR ”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “The chat sidebar helps you quickly understand and navigate your pull requests (PRs) with intelligent, context-aware assistance directly with…”
   • [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…”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Aider—none0/10

   Aider is a CLI coding tool, not an API service, but the story asks about a downloadable machine-readable API spec; probes explicitly confirm no OpenAPI/swagger spec exists at any expected path and no llms.txt is served.

   • [probe] “PROBE llms.txt: HTTP 404 at https://aider.chat/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://aider.chat/docs/usage.html.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://aider.chat/openapi.json, https://aider.chat/swagger.json, https://aider.chat/api/openapi.jso…”

   proof ↗⚑ flag

   cubic—none0/10

   The probe explicitly checked common OpenAPI spec locations and all returned 404, and there is no other evidence of a downloadable machine-readable API spec for cubic's Analytics API or other endpoints; only an llms.txt is present, which is not an OpenAPI/API spec equivalent.

   • [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] “PROBE llms.txt: HTTP 200 at https://docs.cubic.dev/llms.txt # cubic documentation > cubic reviews code on GitHub and in local coding workfl…”
   • [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

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

   weight 2 · round to cubic
   Aider~partialclaimed5/10

   Aider's scripting API lets an AI-native user drive repeated `coder.run()` calls or `--message` invocations across many files/instructions programmatically, and multiple files can be added to a single chat session for combined edits, but there is no documented native bulk/batch command (e.g., apply-to-all, multi-repo loop) built into the CLI — bulk operation requires the user to write their own looping script. missing for 10: a first-party bulk/batch command or documented pattern for applying one operation across many items automatically, and independent evidence of successful large-scale bulk runs.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”
   • [claimed-docs] “To edit files, you need to “add them to the chat”. Do this by naming them on the aider command line. Or, you can use the in-chat `/add` comm…”
   • [claimed-docs] “If you run aider with `--watch-files`, it will watch all files in your repo and look for any AI coding instructions you add using your favor…”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic supports some bulk-like operations — codebase scans that 'deploy thousands of AI agents to find bugs across your repository' (cubic-docs-21), cross-repo reviews that check for related changes across multiple repos (cubic-docs-37/46), and analytics/CSV exports of PR-level data across a team (cubic-docs-19, cubic-docs-20) — but these are review/scan/export operations, not a general-purpose bulk-action capability (e.g., batch-fixing or batch-approving many PRs/items at once) with independent confirmation of scale. Missing for 10: explicit documentation of a bulk-action command/API for acting on many PRs, issues, or files simultaneously, and independent/hands-on evidence corroborating the 'thousands of agents' claim at scale.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [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] “You can export team member data as CSV from both [AI coding](/analytics/ai-coding#csv-export) and [De”
   • [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 userDefine rules that trigger actions automatically on events

   weight 3 · round to cubic
   Aider~partialcommunity5/10

   Aider offers some built-in event-triggered automation: --watch-files lets AI!/AI? comments in files trigger actions, and --auto-test/--auto-lint automatically run after edits. However, these are fixed, predefined triggers rather than a general user-definable rules/automation engine (e.g., no custom event types, schedules, or webhook triggers). Missing for 10: user-defined custom rule/event definitions, broader trigger types beyond file-watch and post-edit, and independent evidence of reliability for these triggers.

   • [claimed-docs] “If you run aider with `--watch-files`, it will watch all files in your repo and look for any AI coding instructions you add using your favor…”
   • [claimed-docs] “AI! triggers aider to make changes to your code.”
   • [claimed-docs] “AI? triggers aider to answer your question.”
   • [claimed-docs] “Rather than using /add to add a file inside the aider chat, you can simply put an #AI comment in it and save the file.”
   • [claimed-docs] “You can configure aider to run your test suite after each time the AI edits your code using the --test-cmd <test-command> and --auto-test sw…”
   • [community] “Aider has a web mode and a 'watch mode', where you can use your normal editor and if you leave a comment like '# make this darker ai!', Aide…”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic supports several rule-based automated actions triggered by events within its code-review domain: auto-review on new PR (cubic-docs-4/41), auto-approval of clean PRs per repository policy (cubic-docs-12/35), auto thread resolution when an issue is fixed (cubic-docs-27), custom agents enforcing org rules across PRs (cubic-docs-34), and a spend-limit trigger that auto-purchases extra capacity (cubic-docs-24/48), all configurable via cubic.yaml (cubic-docs-16/36). These are genuine user-defined rule→action automations, but they are scoped to the code-review/PR lifecycle rather than a general-purpose event/rule engine for arbitrary triggers and actions. Missing for 10: a generic rules/automation builder spanning non-review events, explicit UI for defining custom trigger conditions beyond built-in policies, and independent confirmation these automations behave reliably at scale.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic can approve clean pull requests automatically when your repository policy allows it. Start in shadow mode to see which PRs cubic would…”
   • [claimed-docs] “Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”
   • [claimed-docs] “Flex capacity keeps GitHub PR AI reviews running after your workspace uses its included reviewed-line capacity. You set a monthly spend limi…”
   • [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] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Aider—none0/10

   Aider offers one-shot scripting (--message, Python API) but there is no evidence of any built-in scheduler, cron-like trigger, or recurring workflow orchestration feature; users would need external tooling (e.g., cron) not documented as part of Aider itself.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”

   proof ↗⚑ flag

   cubic—none0/10

   cubic is a code review/PR automation tool triggered by PR events, webhooks, or manual commands (e.g., @cubic-dev-ai review, cubic review CLI), but no evidence describes scheduling recurring jobs or workflows on a time-based cadence (cron-like automation). Codebase scans and wiki updates appear event/PR-triggered, not user-schedulable recurring jobs.

   ⚑ flag

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

   weight 1 · round to Aider
   Aider✓fullcommunity8/10

   Aider auto-commits every AI edit with a descriptive commit message, tags 'aider' as the author, supports /undo, /git for raw git history management, and lets users 'go back in git history to review the changes that aider made' — directly satisfying version/review/rollback for its automations. Community feedback confirms git-based commit behavior is real but criticizes commit message quality, a minor caveat rather than a contradiction of the core capability. Missing for 10: independent hands-on verification of rollback reliability across complex multi-file changes, and richer diff/review tooling beyond git log/git commands.

   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s change…”
   • [claimed-docs] “You can always use the `/undo` command to undo AI changes that you don’t like.”
   • [claimed-docs] “`/git` will let you run raw git commands to do more complex management of your git history.”
   • [claimed-docs] “Go back in the git history to review the changes that aider made to your code”
   • [claimed-docs] “If aider authored the changes in a commit, they will have “(aider)” appended to the git author and git committer name metadata.”
   • [community] “It gets commit messages wrong. Commit messages should signal intent, not what the patch does. 'changing an enum' is a horrible commit messag…”

   proof ↗⚑ flag

   cubic~partialclaimed4/10

   cubic.yaml (the config defining review behavior and custom agents) lives in the repo root, so it inherits git's native versioning and can be reviewed like any code change (cubic-docs-16, cubic-docs-11), but there is no dedicated changelog, rollback UI, or history feature specifically for cubic's automations/config themselves. Missing for 10: explicit rollback/version-history feature for automation configs, evidence of reviewing changes to cubic.yaml itself, dedicated UI for managing automation versions.

   • [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] “Create a repository named `cubic-config` in your organization and add a `cubic.yaml` file to the root directory. cubic automatically applies…”

   proof ↗⚑ flag

Background execution

1. ai-native userHave a cloud agent build, test, and demo a feature end-to-end for my review

   weight 2 · round drawn
   Aider—none0/10

   Aider is a local CLI/library pair-programming tool run against your own repo (add files, /test, /run, scripting via Coder.run) with no evidence of a cloud-hosted agent that autonomously builds, tests, and demos a feature end-to-end for asynchronous review; even community mentions of an experimental 'navigator/autonomy mode' describe local execution, not a cloud agent with a demo/review flow.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “You can run tests with `/test <test-command>`. Aider will run the test command without any arguments. If there are test errors, aider expect…”
   • [claimed-docs] “You can use the `/run` command in the chat to run your code and optionally share the output with aider.”
   • [community] “Over the last two days, I've built out support for autonomy in Aider (a lot like Claude Code) that hybridizes with the rest of the app, uplo…”
   • [community] “It's... decidedly expensive to run an LLM this way right now (Gemini 2.5 Pro is your best bet) with Aider's navigator/autonomy mode, but cos…”

   proof ↗⚑ flag

   cubic—none0/10

   cubic is an AI code-review platform: it reviews PRs, fixes flagged issues, generates PR descriptions, and can auto-approve clean PRs, but there is no evidence it autonomously builds a feature from scratch, runs tests, and produces a demo for review — it only acts on existing diffs/PRs authored by humans or other coding agents.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic helps your team spend less time writing PR descriptions automatically by generating clear, concise summaries.”

   proof ↗⚑ flag

Parallel agents

1. ai-native userLaunch fleets of autonomous agents that work in parallel on different tasks for hours or days

   weight 2 · round drawn
   Aider—none0/10

   Aider is designed as a single-session CLI pair-programming tool driven interactively or via one-shot scripting (--message, coder.run); there is no evidence of orchestrating multiple parallel autonomous agents running for hours/days. Community mentions a third-party experimental 'navigator-mode' for autonomy, but this is not fleet/parallel multi-agent orchestration and is explicitly noted as costly/experimental, not a documented fleet-management capability.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [community] “Over the last two days, I've built out support for autonomy in Aider (a lot like Claude Code) that hybridizes with the rest of the app, uplo…”
   • [community] “It's... decidedly expensive to run an LLM this way right now (Gemini 2.5 Pro is your best bet) with Aider's navigator/autonomy mode, but cos…”

   proof ↗⚑ flag

   cubic—none0/10

   cubic is positioned as an AI code-review, codebase-scan, and wiki-generation tool, not a platform for users to launch autonomous agent fleets to work on arbitrary tasks for hours/days. 'Codebase scans deploy thousands of AI agents' (cubic-docs-21) is an internal review mechanism, not a user-directed fleet of autonomous agents working independently over long time horizons, and no evidence describes user-initiated multi-agent parallel task execution.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”

   proof ↗⚑ flag

Scheduled automation

1. ai-native userSet up always-on agents that run on schedules or triggers to maintain and fix my software autonomously

   weight 2 · round to cubic
   Aider—none0/10

   Aider offers scripting (--message, Python API), file-watch mode triggered by in-file comments, and an experimental 'navigator-mode' for autonomy, but none of this constitutes an always-on agent that runs on schedules or external triggers to autonomously maintain/fix software; it remains an interactive/one-shot CLI tool invoked by a human or script.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “If you run aider with `--watch-files`, it will watch all files in your repo and look for any AI coding instructions you add using your favor…”
   • [claimed-docs] “AI! triggers aider to make changes to your code.”
   • [community] “Over the last two days, I've built out support for autonomy in Aider (a lot like Claude Code) that hybridizes with the rest of the app, uplo…”
   • [community] “It's... decidedly expensive to run an LLM this way right now (Gemini 2.5 Pro is your best bet) with Aider's navigator/autonomy mode, but cos…”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic ships trigger-based automation — it auto-reviews every new PR, reacts to force-pushes, can auto-fix flagged issues, auto-approve clean PRs, and runs codebase-wide scans with 'thousands of AI agents' plus a self-updating wiki via rolling PRs — which covers autonomous, trigger-driven maintenance of software. However, there is no evidence of user-defined schedules (cron-like) or general-purpose 'always-on agent' configuration beyond PR/code-review events. Missing for 10: explicit schedule/cron-based agent triggers, evidence of autonomous fixes/maintenance outside the PR-review workflow, and independent confirmation these agents run continuously without human PR-based triggers.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic can approve clean pull requests automatically when your repository policy allows it. Start in shadow mode to see which PRs cubic would…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic now reviews the new changes after a force-push when it can safely compare them with a previously reviewed version.”

   proof ↗⚑ flag

Debugging

1. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to Aider
   Aider✓fullcommunity7/10

   Aider supports /ask mode for querying the codebase without editing, /run and /test to surface errors, /map to inspect repo structure, and community reports confirm it's used to understand and troubleshoot unfamiliar codebases via natural language ('what code would process this URL', faster than grep/google). missing for 10: no dedicated debugging/stack-trace-analysis workflow documented, no independent benchmark of troubleshooting accuracy, and some community reports note subtle errors requiring correction.

   • [claimed-docs] “**/ask** Ask questions about the code base without editing any files.”
   • [claimed-docs] “/ask Ask questions about the code base without editing any files. If no prompt provided, switches to ask mode.”
   • [claimed-docs] “You can use the `/run` command in the chat to run your code and optionally share the output with aider.”
   • [claimed-docs] “You can use the /run command in the chat to run your code and optionally share the output with aider.”
   • [claimed-docs] “**/map** Print out the current repository map”
   • [claimed-docs] “/map Print out the current repository map”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “Aider can answer questions I can't search for via LSP, like 'what code would process the following URL' and similar.”

   proof ↗⚑ flag

   cubic~partialcommunity6/10

   cubic supports natural-language interaction for understanding and troubleshooting issues it finds in code review — e.g., replying to review comments for clarification, asking chat to 'tour this PR', adding code to AI chat with diff/codebase context, and its MCP server lets agents 'read review findings... and triage PR or codebase scan issues.' However, this is scoped to PR-review/bug-flagging conversations rather than general-purpose debugging of runtime errors or arbitrary issues outside the review flow. Missing for 10: evidence of open-ended debugging (e.g., stack trace analysis, runtime error investigation) beyond PR/code-review context, and independent hands-on confirmation that these NL Q&A features actually resolve real bugs (community comments dispute overall comment quality/bug-catching rate).

   • [claimed-docs] “Reply to a review comment to ask for clarification”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [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 **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] “Ask follow-up questions about code changes without leaving the PR”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”

   proof ↗⚑ flag

Feature implementation

1. developerDescribe a feature or bug in plain language and have the agent implement or fix it across multiple files

   weight 3 · round to Aider
   Aider✓fullcommunity9/10

   Aider's core documented workflow is exactly this: describe a change in natural language, it edits multiple files added to chat (or auto-detects which files to edit), commits changes, and community reports confirm it works well across real codebases including multi-file navigation/modification. Missing for 10: no rigorous independent benchmark of multi-file bug-fix accuracy beyond anecdotal HN reports, and community notes occasional errors/laziness with certain models.

   • [claimed-docs] “To edit files, you need to “add them to the chat”. Do this by naming them on the aider command line. Or, you can use the in-chat `/add` comm…”
   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “You can use aider without adding any files, and it will try to figure out which files need to be edited based on your requests.”
   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s change…”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “I revisited Aider a couple of days ago, after going in circles with AutoGPT - which seemed to either forget or go lazy after a few prompts. …”
   • [community] “Big fan of Aider. We are interested in integrating Aider as a tool for Dosu to help it navigate and modify a codebase on issues.”

   proof ↗⚑ flag

   cubic~partialclaimed3/10

   Cubic is primarily a code-review platform that finds issues and can push targeted one-click fixes to specific flagged problems (docs-7, docs-44), and its CLI generates a fix prompt for external coding agents (docs-31) rather than implementing features itself. It does not document taking a plain-language feature/bug description and independently implementing changes across multiple files; that work is explicitly handed off to a separate 'coding agent' (docs-15, docs-30). Missing for 10: evidence of accepting an open-ended natural-language feature/bug description (not just a flagged review comment) and autonomously implementing multi-file changes, plus any hands-on validation of such end-to-end generation.

   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [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] “By default, cubic pushes commits directly to your PR branch.”

   proof ↗⚑ flag

Maintenance automation

1. developerHave the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me

   weight 3 · round to Aider
   Aider~partialcommunity6/10

   Aider documents linting (auto-lint after edits), running tests via /test or --test-cmd/--auto-test, and general code editing that could write tests or resolve conflicts via natural language instructions, plus dependency-related edits are plausible through general file editing. However, there is no explicit, dedicated documentation or evidence for automated merge-conflict resolution or automated dependency-version updates as distinct workflows, and community evidence notes reliability issues (subtle errors, retries) that temper confidence in unattended correctness. missing for 10: explicit merge-conflict-resolution feature/docs, explicit dependency-update workflow/docs, independent hands-on evidence confirming these four tasks (tests, lint, merge conflicts, dependency updates) work reliably end-to-end.

   • [claimed-docs] “By default, aider will lint any files which it edits.”
   • [claimed-docs] “You can run tests with `/test <test-command>`. Aider will run the test command without any arguments. If there are test errors, aider expect…”
   • [claimed-docs] “You can configure aider to run your test suite after each time the AI edits your code using the --test-cmd <test-command> and --auto-test sw…”
   • [claimed-docs] “You can use the `/run` command in the chat to run your code and optionally share the output with aider.”
   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [community] “I just tried it and it's amazingly cool, but the quality of the output just isn't there for me yet. It makes too much subtle errors to be as…”
   • [community] “Aider is the only tool I use for coding now with ChatGPT... It still suffers from ChatGPT laziness sometimes, you can see it retrying severa…”

   proof ↗⚑ flag

   cubic~partialclaimed3/10

   cubic can automatically fix issues it flags in review (e.g., 'Fix with cubic' pushes a fix commit, docs-7/44) which could cover some lint-style issues, but there is no evidence it writes tests, resolves merge conflicts, or updates dependencies — cubic is positioned as a review/fix-on-comment tool, not a general-purpose coding agent for these tasks. missing for 10: test generation, merge-conflict resolution, dependency updates, and any evidence beyond review-triggered lint/bug fixes.

   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [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] “By default, cubic pushes commits directly to your PR branch.”

   proof ↗⚑ flag

Codebase mapping

1. developerUnderstand how a codebase fits together to find where to start making changes

   weight 3 · round to Aider
   Aider✓fullcommunity9/10

   Aider builds a repo map (concise summary of key classes/functions/signatures across the whole git repo) and offers `/map` and `/ask` commands to explore and understand a codebase without editing it, which directly supports finding where to start making changes; community testimonials corroborate this working well for unfamiliar codebases and languages. Missing for 10: no independent benchmark or deeper hands-on validation of repo-map accuracy on large/complex codebases.

   • [claimed-docs] “Aider uses a **concise map of your whole git repository** that includes the most important classes and functions along with their types and …”
   • [claimed-docs] “**/map** Print out the current repository map”
   • [claimed-docs] “**/ask** Ask questions about the code base without editing any files.”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “Aider can answer questions I can't search for via LSP, like 'what code would process the following URL' and similar.”
   • [community] “Aider is one of my favorite AI agents, especially because it can work with existing codebases. We've seen a lot of good results from folks w…”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic's AI wiki auto-indexes the codebase into a searchable wiki with architecture diagrams and source-code links, and its MCP server/chat features let developers query the codebase and diffs for context (cubic-docs-22, cubic-docs-23, cubic-docs-15, cubic-docs-10), which directly supports understanding how a codebase fits together before making changes. Codebase scans (cubic-docs-21) add bug/vuln discovery but aren't about architectural navigation. Missing for 10: independent/hands-on validation that the wiki or chat actually helps developers locate where to start changes, and community evidence is silent on this specific capability (only comments on PR review quality exist).

   • [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 exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [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] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”

   proof ↗⚑ flag

2. developerHave the agent map and explain an entire unfamiliar codebase without manually selecting context files

   weight 3 · round to Aider
   Aider✓fullcommunity8/10

   Aider builds an automatic repo map of the whole git repository without requiring manual file selection, and the /map and /ask commands let developers query and understand the codebase without editing files or adding them manually. Community reports corroborate this: users describe using aider to understand unfamiliar codebases in unfamiliar tech stacks faster than manual grep/search methods. Missing for 10: independent benchmark/quantitative evidence on very large codebases and more detail on repo-map scaling limits.

   • [claimed-docs] “Aider uses a **concise map of your whole git repository** that includes the most important classes and functions along with their types and …”
   • [claimed-docs] “Aider uses a concise map of your whole git repository that includes the most important classes and functions along with their types and call…”
   • [claimed-docs] “**/ask** Ask questions about the code base without editing any files.”
   • [claimed-docs] “/ask Ask questions about the code base without editing any files. If no prompt provided, switches to ask mode.”
   • [claimed-docs] “**/map** Print out the current repository map”
   • [claimed-docs] “/map Print out the current repository map”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “Aider can answer questions I can't search for via LSP, like 'what code would process the following URL' and similar.”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic's AI wiki automatically indexes the entire codebase and produces searchable wikis with architecture diagrams and source links, and codebase scans deploy AI agents across the whole repo — both let a developer get a full-codebase map/explanation without hand-picking context files. However, this is documented only in first-party docs with no independent hands-on validation of how well it 'explains' an unfamiliar codebase, and community commentary focuses on PR-review quality rather than the wiki/codebase-scan features. Missing for 10: independent/hands-on verification of the AI wiki's accuracy and usefulness, and community evidence specifically evaluating whole-codebase explanation quality.

   • [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 exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [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] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”

   proof ↗⚑ flag

Context management

1. developerHave the agent build and recall memory automatically across sessions

   weight 2 · round to cubic
   Aider—none0/10

   Aider's docs describe repo mapping, git-commit history, and chat commands, but there is no evidence of automatic persistent memory that is built and recalled across separate sessions — chat history logs and repo maps are not the same as cross-session memory recall. No first-party or community evidence describes such a feature.

   ⚑ flag

   cubic~partialclaimed3/10

   Cubic maintains some persistent state — it compares force-pushed changes against previously reviewed versions and its AI wiki auto-indexes and keeps codebase docs current — but there's no documented feature describing agent 'memory' that is built and recalled across chat/review sessions in the way the story implies. missing for 10: explicit session-memory mechanism, evidence of recall in later interactions, independent confirmation of persistent context use.

   • [claimed-docs] “cubic now reviews the new changes after a force-push when it can safely compare them with a previously reviewed version.”
   • [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 exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”

   proof ↗⚑ flag

2. developerInclude multiple project directories in a single session for broader context

   weight 2 · round drawn
   Aider~partialcommunity4/10

   Aider's docs show you can add arbitrary files to a chat session via the CLI or `/add` command, which implicitly allows pulling files from outside the current directory, and it builds a repo map for whole-repository context. However, there is no explicit documentation or community evidence describing support for multiple separate project directories/repos in one session (e.g., cross-repo repomap or multi-root workspace). missing for 10: explicit multi-directory/multi-repo session support, evidence of repomap spanning more than one git repo, and confirmation that /add works across unrelated project roots.

   • [claimed-docs] “To edit files, you need to “add them to the chat”. Do this by naming them on the aider command line. Or, you can use the in-chat `/add` comm…”
   • [claimed-docs] “Aider uses a **concise map of your whole git repository** that includes the most important classes and functions along with their types and …”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”

   proof ↗⚑ flag

   cubic~partialclaimed4/10

   Cubic's 'cross-repo reviews' feature lets teams link related repositories so a review can check shared APIs, schemas, or docs across them, which is the closest analogue to including multiple project directories for broader context — but this is scoped narrowly to PR review consistency checks, not a general chat/agent session that loads multiple directories for open-ended Q&A. Missing for 10: evidence of a chat/agent session (e.g., MCP or CLI) that lets a developer add multiple arbitrary project directories as context, and any hands-on confirmation of cross-repo context quality.

   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [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] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”

   proof ↗⚑ flag

3. developerAdd a project instructions file to set coding standards and conventions the agent follows

   weight 3 · round to cubic
   Aider—none0/10

   The evidence pack documents aider's config file (.aider.conf.yml) for command-line options and repo-map features, but contains no mention of a dedicated project instructions/conventions file (e.g. CONVENTIONS.md or read-only context file) for setting coding standards that the agent follows. Absence of evidence for this applicable capability means it cannot be credited.

   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an .aider.conf.yml file... Or by setting…”

   proof ↗⚑ flag

   cubic~partialclaimed6/10

   cubic supports a `cubic.yaml` config file at the repo root (or a shared `cubic-config` repo) that acts as 'the source of truth for AI review behavior, ignore patterns, PR descriptions, and custom agents,' and 'Custom agents' are documented as a way to 'enforce your team's coding standards.' This is a project-level instructions/config mechanism the agent follows, though it's framed around PR review behavior rather than a general-purpose coding-standards instructions file for all agent interactions. Missing for 10: explicit documentation of a plain-text/markdown instructions file (like AGENTS.md-style) covering broader coding conventions beyond review/ignore rules, and independent confirmation that custom agents reliably enforce standards in practice.

   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”
   • [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] “Create a repository named `cubic-config` in your organization and add a `cubic.yaml` file to the root directory. cubic automatically applies…”

   proof ↗⚑ flag

Issue diagnosis

1. developerReproduce issues, narrow down root causes, and verify fixes

   weight 3 · round to Aider
   Aider~partialcommunity7/10

   Aider provides tools that support this story indirectly: `/ask` for exploring the codebase without editing, the repo-map for navigating structure, `/run` and `/test`/`--auto-test` for executing code and test suites to reproduce and verify fixes, and community reports confirm it's effective for understanding unfamiliar codebases faster than manual search. However, there's no dedicated bug-reproduction or root-cause-analysis workflow beyond these general commands, and community feedback notes subtle errors and inconsistent output quality that could undermine verification confidence. Missing for 10: dedicated debugging/tracing tooling, explicit root-cause analysis features, and independent hands-on validation specifically of fix verification.

   • [claimed-docs] “**/ask** Ask questions about the code base without editing any files.”
   • [claimed-docs] “**/map** Print out the current repository map”
   • [claimed-docs] “You can run tests with `/test <test-command>`. Aider will run the test command without any arguments. If there are test errors, aider expect…”
   • [claimed-docs] “You can use the `/run` command in the chat to run your code and optionally share the output with aider.”
   • [claimed-docs] “You can configure aider to run your test suite after each time the AI edits your code using the --test-cmd <test-command> and --auto-test sw…”
   • [claimed-docs] “Aider uses a **concise map of your whole git repository** that includes the most important classes and functions along with their types and …”
   • [community] “I've used aider to understand new codebases using technologies I don't know and it did a fantastic job; much faster than grep/find + google.”
   • [community] “Aider can answer questions I can't search for via LSP, like 'what code would process the following URL' and similar.”
   • [community] “I just tried it and it's amazingly cool, but the quality of the output just isn't there for me yet. It makes too much subtle errors to be as…”

   proof ↗⚑ flag

   cubic~partialclaimed4/10

   cubic is fundamentally an AI code-review/PR platform: it can flag bugs during review (codebase scans, PR review), generate and push fixes ('Fix with cubic'), and auto-resolve threads when issues are fixed, which covers some root-cause flagging and fix verification. However there is no evidence of actual issue reproduction (running the app/tests to trigger a bug) or root-cause debugging via execution—cubic's analysis is static/AI-review based, not a runtime debugger. Missing for 10: reproduction of bugs via execution/testing, dynamic root-cause tracing, and independent verification of fixes beyond thread auto-resolution.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”

   proof ↗⚑ flag

Marketplace

1. developerEquip the agent with custom skills to perform specialized tasks

   weight 1 · round to cubic
   Aider—none0/10

   No evidence of a skills/plugin system, custom tool definitions, or extension API in Aider's docs; it exposes built-in slash commands (/architect, /web, /run) but no mechanism for developers to add custom specialized skills.

   ⚑ flag

   cubic~partialclaimed4/10

   cubic supports 'custom agents' configured via cubic.yaml to enforce coding standards, which is a limited form of custom skill/persona equipping for the review agent, but this is scoped narrowly to code-review behavior rather than general-purpose specialized task skills. Missing for 10: documentation on creating arbitrary custom skills/tools beyond coding-standard enforcement, examples of diverse specialized tasks, and independent validation of the custom agents feature.

   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”
   • [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, …”

   proof ↗⚑ flag

2. engineering-leadIntegrate third-party partner-built agent apps into my workflows

   weight 1 · round to cubic
   Aider—none0/10

   Aider is a CLI/library coding assistant; there is no evidence of an ecosystem for integrating third-party partner-built agent apps (no plugin marketplace, app store, or partner integrations documented) beyond one community mention of someone wanting to embed Aider itself as a tool inside another product (Dosu), which is the reverse relationship. No evidence Aider itself supports plugging in external partner agent apps.

   • [community] “Big fan of Aider. We are interested in integrating Aider as a tool for Dosu to help it navigate and modify a codebase on issues.”

   proof ↗⚑ flag

   cubic~partialprobed6/10

   cubic documents concrete integrations with third-party agent apps - connecting ChatGPT Plus or Claude Code subscriptions for local reviews, exposing an MCP server so coding agents can pull review findings and request PRs, pushing fixes via coding agents, and Linear or Jira issue-analysis integration - showing real ecosystem hooks for partner-built agent tools. Missing for 10: a documented marketplace or catalog of certified partner agent apps, examples beyond the major AI vendors, and independent evidence confirming these integrations work smoothly in practice.

   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [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] “By default, cubic pushes commits directly to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic can automatically analyze your pull requests to see if they meet the requirements from your linked Linear or Jira issues.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

   proof ↗⚑ flag

Tool integration

1. developerConnect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context

   weight 3 · round drawn
   Aider—none0/10

   Aider's documented features cover file editing, git integration, web scraping, and voice input, but there is no evidence of any integration with workflow tools like Jira, Slack, or Google Drive.

   ⚑ flag

   cubic—none0/10

   cubic's documented integrations are limited to GitHub, an MCP server for coding agents, and ChatGPT/Claude Code subscriptions for local reviews; there is no evidence of connectors to Jira, Slack, or Google Drive for extending context.

   • [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] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [community] “As far as I can see, this doesn't directly integrate with github (we currently use coderabbit on github)? Is it on your timeline?”
   • [community] “Would be great to have support for GitLab also (have a project there that I would love to try this on and I can't switch it to GitHub)”

   proof ↗⚑ flag

2. developerKick off agent tasks directly from GitHub, GitLab, Linear, or Slack

   weight 2 · round to cubic
   Aider—none0/10

   No evidence of any GitHub/GitLab/Linear/Slack integration that lets users trigger Aider agent tasks from those platforms; Aider is a CLI/scriptable tool invoked locally or via its own scripting API, with no mention of issue-tracker or chat-platform triggers.

   ⚑ flag

   cubic~partialcommunity4/10

   cubic clearly supports triggering reviews and fixes from GitHub (PR comments like `@cubic-dev-ai review this PR`, 'Fix with cubic', auto-review on install) and links to Linear/Jira for issue-requirement checks, but there's no evidence of Slack integration and community comments explicitly note GitLab support is missing/requested, not confirmed. Missing for 10: documented Slack task-triggering, confirmed GitLab support, and independent corroboration that Linear integration goes beyond issue-analysis to actually kicking off agent tasks.

   • [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] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [claimed-docs] “Post this comment on GitHub to start a review: text theme={null} @cubic-dev-ai review this PR ”
   • [claimed-docs] “cubic can automatically analyze your pull requests to see if they meet the requirements from your linked Linear or Jira issues.”
   • [community] “Would be great to have support for GitLab also (have a project there that I would love to try this on and I can't switch it to GitHub)”
   • [community] “It looks like graphite.dev has pivoted into this space too, which is annoying since they still don't have gitlab support after several years…”

   proof ↗⚑ flag

Cross device continuity

1. developerStart a task on one device and continue it later from another device or browser

   weight 2 · round to cubic
   Aider—none0/10

   Aider is a local CLI/git-based tool with an experimental local browser UI, but there's no evidence of any account, session, or cloud state that would let a user resume a task on a different device/browser—chat history and repo map are local to the machine running aider. Git commits persist code changes but don't constitute a portable 'continue where I left off' session across devices.

   • [claimed-docs] “Use aider’s new experimental browser UI to collaborate with LLMs to edit code in your local git repo.”
   • [claimed-docs] “Use aider's new experimental browser UI to collaborate with LLMs to edit code in your local git repo.”
   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s change…”
   • [claimed-docs] “Aider uses a **concise map of your whole git repository** that includes the most important classes and functions along with their types and …”

   proof ↗⚑ flag

   cubic~partialclaimed3/10

   cubic's reviews, chat, and fix actions happen inside GitHub PR comments and threads (docs-29, docs-45, docs-7), which are cloud-hosted and thus technically accessible from any device/browser, but cubic never documents an explicit cross-device 'resume task' or session-continuity feature for a developer's own work-in-progress task. Missing for 10: explicit session/task persistence across CLI, IDE, and browser, documented device-handoff workflow, and any first-party or community confirmation of resuming an in-progress task on a new device.

   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [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.”

   proof ↗⚑ flag

Ide integration

1. developerChat with the coding assistant directly inside my IDE for contextual help

   weight 3 · round drawn
   Aider~partialcommunity5/10

   Aider is fundamentally a terminal/CLI chat tool, but its --watch-files mode lets developers trigger AI edits from within their own IDE/editor by leaving '# ... ai!' comments, which the docs frame as IDE-integrated workflow. There's no evidence of a native embedded chat panel or official IDE extension providing conversational context inside the editor itself. missing for 10: dedicated IDE plugin/panel for direct chat, evidence of contextual chat UI inside an IDE rather than terminal+file-watch workaround.

   • [claimed-docs] “If you run aider with `--watch-files`, it will watch all files in your repo and look for any AI coding instructions you add using your favor…”
   • [claimed-docs] “AI! triggers aider to make changes to your code.”
   • [claimed-docs] “AI? triggers aider to answer your question.”
   • [claimed-docs] “Rather than using /add to add a file inside the aider chat, you can simply put an #AI comment in it and save the file.”
   • [community] “Aider has a web mode and a 'watch mode', where you can use your normal editor and if you leave a comment like '# make this darker ai!', Aide…”

   proof ↗⚑ flag

   cubic~partialclaimed5/10

   cubic offers chat-based interaction (an 'Add to AI chat' feature with diff/codebase context, a chat sidebar for PR navigation, and an MCP server that lets coding agents in the IDE read review findings), but these are mostly scoped to reviewing PRs/code review rather than a general-purpose in-IDE chat assistant for arbitrary contextual coding help. Missing for 10: evidence of a native IDE chat panel for general coding questions (not tied to PR/diff review), and independent hands-on confirmation of in-IDE chat quality.

   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [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 chat sidebar helps you quickly understand and navigate your pull requests (PRs) with intelligent, context-aware assistance directly with…”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”

   proof ↗⚑ flag

Terminal workflow

1. developerRun a coding agent locally from my terminal

   weight 3 · round to Aider
   Aider✓fullcommunity9/10

   Aider is a terminal-based coding assistant, installed via pip/curl script and run directly from the command line with rich in-chat commands, file editing, git integration, and local model support, all extensively documented and corroborated by hands-on community reports. Missing for 10: independent benchmarking of terminal UX quality and no first-party video/demo evidence beyond docs and forum posts.

   • [claimed-docs] “python -m pip install aider-install aider-install”
   • [claimed-docs] “curl -LsSf https://aider.chat/install.sh | sh”
   • [claimed-docs] “To edit files, you need to “add them to the chat”. Do this by naming them on the aider command line. Or, you can use the in-chat `/add` comm…”
   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [community] “I revisited Aider a couple of days ago, after going in circles with AutoGPT - which seemed to either forget or go lazy after a few prompts. …”
   • [community] “Big fan of Aider. We are interested in integrating Aider as a tool for Dosu to help it navigate and modify a codebase on issues.”

   proof ↗⚑ flag

   cubic~partialprobed5/10

   cubic ships an official local CLI (`cubic review`) that runs from the terminal to review uncommitted changes before push, and can connect to Claude Code/ChatGPT subscriptions for local reviews, but this is a review agent rather than a general-purpose coding agent that writes/edits code interactively in the terminal. Missing for 10: evidence of an interactive terminal coding-agent loop (code generation/editing, multi-turn task execution) beyond review-only CLI use.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

2. developerRun the agent non-interactively in scripts for workflow automation

   weight 2 · round to Aider
   Aider✓fullcommunity8/10

   Aider has a documented scripting mode with a --message flag to run one instruction non-interactively and exit, plus a Python API (Coder.create/coder.run) for programmatic/scripted invocation, both explicitly designed for automation workflows. missing for 10: independent hands-on evidence of scripted/CI usage at scale, and more detail on exit codes/error handling for pipeline integration.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”
   • [community] “I only use Aider interactively, but I really should consider Aider in the 'scriptable' sense more... I might add another step after each PR …”

   proof ↗⚑ flag

   cubic~partialprobed5/10

   cubic ships a CLI (`cubic review`) that reviews local/uncommitted changes and automatically reviews PRs on GitHub without manual intervention, both of which suggest it can be woven into automated workflows (docs-4, docs-8, docs-31, docs-41). However, there is no explicit documentation of a non-interactive/headless mode, CI pipeline integration, exit codes, or scripting flags for the CLI. missing for 10: explicit CI/script integration docs, non-interactive mode flags, exit-code/output-format guarantees for automation, independent evidence of scripted use.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [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] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Aider~partialprobed4/10

   Aider exposes a scripting/Python API (`Coder.create`/`coder.run`) and a `--message` CLI mode for programmatic single-instruction execution, but this is far narrower than the interactive chat/browser UI, which offers many features (e.g. /architect, /voice, /web, /map, /test, /run, /model, watch-files) not exposed through the scripting API. No REST/OpenAPI surface exists (confirmed 404s), so API parity with the UI is only partial. missing for 10: programmatic access to slash-commands like /architect, /voice, /web, /map, /test, /run via the scripting API; a documented REST/OpenAPI interface; independent confirmation of API-UI feature parity.

   • [claimed-docs] “Aider takes a `--message` argument, where you can give it a natural language instruction. It will do that one thing, apply the edits to the …”
   • [claimed-docs] “coder = Coder.create(main_model=model, fnames=fnames) # This will execute one instruction on those files and then return coder.run("make a …”
   • [claimed-docs] “aider --message "make a script that prints hello" hello.js”
   • [claimed-docs] “coder.run("make a script that prints hello world")”
   • [claimed-docs] “Use aider’s new experimental browser UI to collaborate with LLMs to edit code in your local git repo.”
   • [claimed-docs] “**/architect** Enter architect/editor mode using 2 different models. If no prompt provided, switches to architect/editor mode.”
   • [claimed-docs] “**/web** Scrape a webpage, convert to markdown and send in a message”
   • [claimed-docs] “Use the in-chat `/voice` command to start recording, and press `ENTER` when you’re done speaking. Your voice coding instructions will be tra…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://aider.chat/openapi.json, https://aider.chat/swagger.json, https://aider.chat/api/openapi.jso…”

   proof ↗⚑ flag

   cubic~partialprobed4/10

   cubic exposes some functionality outside the UI — an Analytics API for PR-level data (cubic-docs-20), an MCP server for reading review findings, requesting reviews, and even managing subscriptions/seats (cubic-docs-3, cubic-docs-15), and a CLI for local reviews (cubic-docs-8, cubic-probe-4) — but there is no general-purpose public API (openapi probes 404, cubic-probe-2) covering the full UI surface (codebase scans, AI wiki, cubic.yaml config, analytics dashboard CSV exports, custom agents, auto-approve settings). Missing for 10: a comprehensive REST/GraphQL API or OpenAPI spec covering all UI features, evidence of API parity for wiki/codebase-scan/config management, and independent confirmation that MCP+CLI+Analytics API together replicate full UI functionality.

   • [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] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic 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…”
   • [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 Aider
   Aider~partialclaimed5/10

   Aider operates entirely on local files and git repos, committing all AI edits as standard git commits (plain text, open format) rather than locking data in a proprietary store, and config is a plain YAML file — so there's little vendor lock-in by design. However, there is no explicit documentation of a data-export feature, chat/session history format, or any messaging about portability/'leaving' the product. Missing for 10: explicit chat/session export documentation, statement on session data formats, and any first-party 'no lock-in/data portability' claim.

   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s change…”
   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider's change…”
   • [claimed-docs] “`/git` will let you run raw git commands to do more complex management of your git history.”
   • [claimed-docs] “/git will let you run raw git commands to do more complex management of your git history.”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an .aider.conf.yml file... Or by setting…”

   proof ↗⚑ flag

   cubic~partialclaimed4/10

   cubic offers some data portability: CSV export of team analytics (cubic-docs-19), an Analytics API for PR-level data (cubic-docs-20), and AI wiki content exported as markdown files into the repo (cubic-docs-23). However, there's no evidence of comprehensive export covering all review history, comments, configs, or account data in open formats, nor any documented account deletion/migration path for 'leaving' the platform. Missing for 10: full account/data export (reviews, comments, configs), explicit data-portability policy, independent confirmation of export completeness.

   • [claimed-docs] “You can export team member data as CSV from both [AI coding](/analytics/ai-coding#csv-export) and [De”
   • [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 exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Aider—none0/10

   The evidence pack contains only usage/feature docs and community discussion of Aider's coding capabilities; none of the citations mention a public source repository, license, or any statement about open licensing. Without evidence of an accessible, openly-licensed source, this axis cannot be credited as delivered.

   ⚑ flag

   cubic—none0/10

   No evidence in the pack indicates cubic's source code is open or available under any open license; it appears to be a closed, commercial SaaS/CLI product with only documentation exposed publicly. Missing for 10: any open-source repository, license file, or public source code reference.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Aider
   Aider✓fullclaimed7/10

   Aider is a local CLI/Python tool installed via pip or a script, runs entirely on the user's machine, and can operate with fully local LLMs (Ollama or any OpenAI-compatible local endpoint), meaning the entire core product can be self-hosted with no vendor cloud dependency. missing for 10: explicit self-hosting/deployment guide (e.g. Docker/server setup), independent confirmation of running fully offline with local models, and discussion of self-hosting a team-shared instance

   • [claimed-docs] “python -m pip install aider-install aider-install”
   • [claimed-docs] “curl -LsSf https://aider.chat/install.sh | sh”
   • [claimed-docs] “Aider can work also with local models, for example using [Ollama]”
   • [claimed-docs] “Aider can work also with local models, for example using Ollama. It can also access local models that provide an Open AI compatible API.”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”

   proof ↗⚑ flag

   cubic—none0/10

   cubic is presented as a hosted SaaS code review platform (GitHub app, cloud dashboard, analytics, flex capacity billing) with no documentation of a self-hostable core, on-prem deployment, or open-source release. Absence of any self-hosting evidence for an applicable axis (a code review tool could plausibly be self-hosted) means this is 'none'.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”
   • [claimed-docs] “Flex capacity keeps GitHub PR AI reviews running after your workspace uses its included reviewed-line capacity. You set a monthly spend limi…”
   • [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

Authentication

1. developerAuthenticate with an API key instead of an account login

   weight 2 · round to Aider
   Aider~partialclaimed6/10

   Aider's docs describe configuration via command-line switches, an `.aider.conf.yml` file, and environment variables like `AIDER_xxx`, which is the standard mechanism for supplying LLM provider API keys, and Aider has no account-login system of its own — it authenticates purely through provider API keys. However, the evidence pack never explicitly shows an API-key setup example or names an env var like OPENAI_API_KEY, so the authentication story is implied rather than directly documented. missing for 10: explicit documentation/example of setting an API key (e.g., OPENAI_API_KEY) and confirmation that no account-login alternative exists.

   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an .aider.conf.yml file... Or by setting…”
   • [claimed-docs] “Aider can work also with local models, for example using [Ollama]”
   • [claimed-docs] “Aider can work also with local models, for example using Ollama. It can also access local models that provide an Open AI compatible API.”

   proof ↗⚑ flag

   cubic—none0/10

   No evidence in the pack mentions API key authentication as an alternative to account login; cubic's docs describe GitHub app installation, roles/permissions, and subscription management but nothing about API-key-based auth for developers. The OpenAPI probe also returned 404s, suggesting no documented API surface with key auth.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”
   • [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

2. engineering-leadAuthenticate through an enterprise identity or cloud platform for compliance and scalability

   weight 2 · round drawn
   Aider—none0/10

   Aider is a local CLI coding tool with no evidence of SSO/SAML, enterprise identity provider integration, or cloud-platform authentication for compliance; only API key based LLM auth is documented, which does not address enterprise identity/compliance needs.

   ⚑ flag

   cubic—none0/10

   The evidence pack shows role-based access control for team/subscription management (cubic-docs-47) but no mention of SSO, SAML, OAuth enterprise identity provider integration, or cloud IAM authentication anywhere in the docs or community items. missing for 10: SSO/SAML support, enterprise IdP integration (Okta/Azure AD/Google Workspace), cloud IAM authentication, any compliance certification tied to auth.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”

   proof ↗⚑ flag

3. developerSign in with my existing product subscription plan to use the coding agent

   weight 2 · round to cubic
   Aider—none0/10

   Aider is a BYO-API-key CLI tool that connects to LLM providers (or local models); there's no evidence of a subscription-based sign-in (e.g., ChatGPT Plus/Claude Pro login) to use Aider itself. No mention of OAuth/subscription sign-in flow anywhere in docs or community evidence.

   ⚑ flag

   cubic~partialclaimed6/10

   cubic explicitly lets developers connect an existing ChatGPT Plus/Pro or Claude Code subscription to power local CLI reviews, which matches 'sign in with existing subscription to use the coding agent.' However, this only applies to local review via CLI, not the full agent/reviewer product, and there's no independent verification of this flow working in practice. Missing for 10: broader applicability beyond CLI reviews, and community/hands-on confirmation of the subscription linking process.

   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”

   proof ↗⚑ flag

4. developerSign in with a personal account to get free-tier access without managing API keys

   weight 1 · round drawn
   Aider—none0/10

   Aider is a local CLI tool requiring users to supply their own LLM API keys (or local models); there is no evidence of an account sign-in or free-tier hosted access mechanism. No mention of OAuth login, hosted free tier, or account-based access in any evidence.

   ⚑ flag

   cubic—none0/10

   cubic is a code-review/PR platform with team subscriptions, seats, and flex-capacity billing; no evidence describes a personal-account sign-in path granting free-tier access without API key management—this pricing/auth model story is unaddressed in the pack.

   ⚑ flag

Model choice

1. developerLet the tool automatically pick the best model for each task

   weight 1 · round drawn
   Aider—none0/10

   Aider lets users manually switch models via /model or choose two different models for architect/editor mode, but there is no evidence of any automatic selection of 'best model for each task' — the choice is always explicit and user-driven.

   • [claimed-docs] “During your chat you can switch models with the in-chat /model command.”
   • [claimed-docs] “**/architect** Enter architect/editor mode using 2 different models. If no prompt provided, switches to architect/editor mode.”
   • [claimed-docs] “/architect Enter architect/editor mode using 2 different models. If no prompt provided, switches to architect/editor mode.”

   proof ↗⚑ flag

   cubic—none0/10

   Cubic's docs describe distinct manually-invoked review modes (standard review vs. Ultrareview) and let users connect their own ChatGPT/Claude subscriptions for local reviews, but there is no evidence the tool automatically selects the best model per task based on cost or complexity — mode selection is user-driven, not automatic.

   • [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] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [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] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”

   proof ↗⚑ flag

2. developerChoose which underlying AI model powers my session from multiple providers

   weight 2 · round to Aider
   Aider✓fullcommunity8/10

   Aider explicitly supports switching models via the in-chat /model command and documents compatibility with OpenAI, Anthropic (Claude), Ollama, and other OpenAI-API-compatible local models; community threads confirm developers actively switching between GPT-4, Claude Opus, and Gemini within Aider. Minor friction is noted (e.g., a tokenizer error for a specific Claude alias, cost/latency tradeoffs across providers) but the core multi-provider capability is clearly delivered. Missing for 10: a comprehensive first-party list of all supported providers and independent benchmarking of switching reliability across the full provider set.

   • [claimed-docs] “During your chat you can switch models with the in-chat /model command.”
   • [claimed-docs] “Aider can work also with local models, for example using [Ollama]”
   • [claimed-docs] “Aider can work also with local models, for example using Ollama. It can also access local models that provide an Open AI compatible API.”
   • [community] “Have been having too many problems with the diffs from gpt-4-turbo in aider... if aider supports Opus then will switch.”
   • [community] “From the Aider blog post discussion: Claude 3 Opus and Sonnet are both slower and more expensive than OpenAI's models; you can get almost th…”
   • [community] “does anyone know how to run aider with claude 3 opus? aider --model anthropic/claude-3-opus gives ValueError: No known tokenizer for model: …”
   • [community] “It's... decidedly expensive to run an LLM this way right now (Gemini 2.5 Pro is your best bet) with Aider's navigator/autonomy mode, but cos…”

   proof ↗⚑ flag

   cubic~partialclaimed5/10

   Cubic docs state you can "connect your existing ChatGPT Plus/Pro or Claude Code subscription to use its models for local reviews" via the CLI, showing some model-provider choice, but PR reviews and Ultrareview use cubic's own proprietary 'most capable review models' with no indication of choosing among alternative providers there. missing for 10: model choice for the core PR/Ultrareview review sessions (not just local CLI), a documented list of selectable providers, and independent confirmation of the feature working in practice.

   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [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] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [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…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Aider—none0/10

   No evidence in the pack addresses data usage/training opt-outs, privacy policy, or data retention controls for Aider or the LLM providers it connects to; Aider primarily relies on third-party LLM APIs whose training-data policies aren't documented here.

   ⚑ flag

   cubic—none0/10

   No evidence in the pack addresses data usage for AI model training, opt-out policies, or data privacy commitments — cubic's docs focus entirely on code review features with no mention of training data controls.

   ⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Aider—none0/10

   The evidence pack covers usage, git integration, and LLM configuration but contains no mention of data retention, storage, or deletion policies for user code, chat history, or LLM interactions. While Aider is local-first (using git and local models), no docs address how conversation/data sent to LLM providers is retained or how a user can delete it.

   ⚑ flag

   cubic—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or privacy settings for AI-native users; docs cover review features, analytics, wiki, and pricing but nothing on retention/deletion of data. Missing for 10: any documentation on data retention periods, deletion requests, or privacy controls.

   ⚑ flag

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

   weight 2 · round drawn
   Aider—none0/10

   No evidence in the pack addresses telemetry, usage tracking, or opt-out settings for Aider; documentation covers usage, git integration, config files, and models but nothing about analytics/telemetry controls. missing for 10: any mention of telemetry collection, privacy policy, or an opt-out flag/env var.

   ⚑ flag

   cubic—none0/10

   No evidence pack item addresses telemetry opt-out or usage-tracking controls; cubic's docs cover review features, analytics dashboards, and RBAC but never mention a privacy/telemetry toggle. missing for 10: any mention of telemetry collection, opt-out settings, or privacy controls.

   ⚑ flag

Pr review

1. developerHave the agent stage changes, write commit messages, create branches, and open pull requests

   weight 3 · round drawn
   Aider~partialcommunity4/10

   Aider auto-commits every AI edit with a descriptive commit message and supports /git for raw git commands and git-history review/undo, covering the 'stage changes + commit messages' part of the story. However, there is no documented feature for creating branches or opening pull requests — these would require manual use of /git or external tools, and one community report even criticizes the quality of auto-generated commit messages. missing for 10: dedicated branch-creation workflow, native PR-opening capability, and evidence of reliable commit-message quality.

   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s change…”
   • [claimed-docs] “`/git` will let you run raw git commands to do more complex management of your git history.”
   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider's change…”
   • [claimed-docs] “Go back in the git history to review the changes that aider made to your code”
   • [claimed-docs] “/git will let you run raw git commands to do more complex management of your git history.”
   • [community] “It gets commit messages wrong. Commit messages should signal intent, not what the patch does. 'changing an enum' is a horrible commit messag…”

   proof ↗⚑ flag

   cubic~partialclaimed4/10

   cubic can push fix commits directly to an existing PR branch and auto-generate PR descriptions/summaries (cubic-docs-30, cubic-docs-44, cubic-docs-26, cubic-docs-49), but its own docs show the developer still runs the initial git workflow (checkout -b, commit, push) to create the branch and open the PR (cubic-docs-51) — cubic is a review/fix layer, not an agent that autonomously stages changes, writes original commit messages, creates branches, or opens PRs from scratch. missing for 10: evidence of cubic independently creating a new branch, staging changes, and opening a brand-new pull request without a human first running git/opening the PR.

   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “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] “you can keep using normal Git commands exactly as before (e.g., `git checkout -b my-feature`, `git commit -m "message"`, `git push`). Using …”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”

   proof ↗⚑ flag

2. developerInspect diffs and run checks to catch problems before merging

   weight 3 · round drawn
   Aider✓fullcommunity8/10

   Aider auto-commits every change with a descriptive message, letting developers review diffs via normal git tooling and use /undo or /git to inspect or roll back history; it also supports linting by default, /test and --auto-test for running test suites, and /run for executing code before accepting changes. This directly covers inspecting diffs and running checks pre-merge. Missing for 10: no built-in diff viewer/PR-style review UI (relies on external git tools) and no independent hands-on corroboration of the review workflow specifically (one community comment notes users still bolt on separate review agents).

   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s change…”
   • [claimed-docs] “Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider's change…”
   • [claimed-docs] “Go back in the git history to review the changes that aider made to your code”
   • [claimed-docs] “`/git` will let you run raw git commands to do more complex management of your git history.”
   • [claimed-docs] “/git will let you run raw git commands to do more complex management of your git history.”
   • [claimed-docs] “By default, aider will lint any files which it edits.”
   • [claimed-docs] “You can run tests with `/test <test-command>`. Aider will run the test command without any arguments. If there are test errors, aider expect…”
   • [claimed-docs] “You can configure aider to run your test suite after each time the AI edits your code using the --test-cmd <test-command> and --auto-test sw…”
   • [claimed-docs] “You can use the `/run` command in the chat to run your code and optionally share the output with aider.”
   • [community] “I only use Aider interactively, but I really should consider Aider in the 'scriptable' sense more... I might add another step after each PR …”

   proof ↗⚑ flag

   cubic✓fullcommunity8/10

   cubic provides diff-focused PR review (hiding tests, force-push re-review), a CLI (`cubic review`) to check uncommitted changes before pushing, Ultrareview for deep multi-pass checks, and auto-fix/auto-approval gating before merge — directly matching 'inspect diffs and run checks before merging'. Community feedback corroborates real-world use but also raises concerns about comment relevance and false-positive rates, tempering confidence. Missing for 10: independent quantitative validation of bug-catch accuracy and resolution of noise/false-positive concerns raised by users.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [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] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [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] “cubic now reviews the new changes after a force-push when it can safely compare them with a previously reviewed version.”
   • [claimed-docs] “Focus on implementation changes by hiding test files from the PR diff and file tree.”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [community] “I've been testing this for the last few months, and it is now much quieter than before, and even more useful.”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”

   proof ↗⚑ flag

Safe execution

1. engineering-leadControl which external tools and integrations the agent is allowed to access

   weight 2 · round drawn
   Aider—none0/10

   Aider's docs describe config files, command-line switches, and model selection, but there is no evidence of a permissions/allowlist system for controlling which external tools, plugins, or integrations (e.g., MCP servers, web scraping, code execution) the agent may access. Given Aider does have features like /web, /run, and file editing that could pose access-control concerns, an engineering-lead's ability to gate these is a fair question, but no such control mechanism is documented.

   • [claimed-docs] “Aider has many options which can be set with command line switches. Most options can also be set in an `.aider.conf.yml` file... Or by setti…”
   • [claimed-docs] “**/web** Scrape a webpage, convert to markdown and send in a message”
   • [claimed-docs] “You can use the `/run` command in the chat to run your code and optionally share the output with aider.”

   proof ↗⚑ flag

   cubic—none0/10

   Evidence shows cubic has RBAC for subscription/settings management (cubic-docs-47) and cubic.yaml config for review behavior (cubic-docs-16/36), but nothing documents an engineering-lead controlling which external tools, MCP servers, or integrations the cubic agent itself is permitted to access. Missing for 10: any admin-facing tool/integration allowlist or permission gate for the agent's external tool access.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”
   • [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] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”

   proof ↗⚑ flag

Security checks

1. engineering-leadSee license and public-code matching references for AI-suggested code

   weight 1 · round drawn
   Aider—none0/10

   No evidence that Aider provides license compliance checks or public-code/match provenance detection for AI-suggested code; the docs cover editing, git commits, linting, and testing but nothing about license or code-matching references.

   ⚑ flag

   cubic—none0/10

   cubic's evidence covers PR review, bug/vulnerability detection, custom agents, analytics, and codebase scans, but there is no mention of license compliance checking or public-code/plagiarism matching references for AI-suggested code. Missing for 10: license detection features, public-code/match provenance references, any SCA or license-compliance tooling.

   ⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round to cubic
   Aider—none0/10

   No evidence that Aider detects, explains, or auto-fixes security vulnerabilities; it is a general-purpose AI pair-programming/coding tool with linting/testing/git features, but no dedicated security-scanning or vulnerability-remediation capability is documented.

   ⚑ flag

   cubic~partialcommunity7/10

   cubic's docs show explicit support for finding vulnerabilities (codebase scans, Ultrareview for 'security-sensitive changes'), contextual explanations (chat sidebar, 'tour this PR', reply-to-comment clarification), and automatic fixes ('Fix with cubic' pushes a fix commit; CLI generates fix prompts for coding agents). However there is no vendor or independent evidence specifically validating fix quality/accuracy for security vulnerabilities, and community comments raise general skepticism about comment relevance and false-positive rates for AI review tools of this class. missing for 10: security-specific hands-on validation of fix correctness, independent benchmarking on vulnerability detection/fix accuracy.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [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] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [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] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Reply to a review comment to ask for clarification”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”
   • [community] “When I read '51% fewer false positives' followed immediately by 'Median comments per pull request cut by half' it makes me wonder how many t…”

   proof ↗⚑ flag