Greptile vs Cursor Bugbot

Agent access

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

   weight 2 · round drawn
   Greptile✓fullprobed8/10

   Greptile has a confirmed llms.txt at the root (HTTP 200) plus per-page .md variants (e.g. docs/introduction.md) and a documentation index at docs/llms.txt, explicitly designed for agents to fetch; docs also explicitly invite handing pages to a coding agent to run setup. Missing for 10: independent/community confirmation that an external agent successfully consumed llms.txt end-to-end, and no evidence of an OpenAPI spec to complement it.

   • [probe] “PROBE llms.txt: HTTP 200 at https://www.greptile.com/llms.txt # Greptile > Greptile is an independent AI code validation platform for GitHu…”
   • [probe] “PROBE docs-md: HTTP 200 at https://www.greptile.com/docs/introduction.md > ## Documentation Index > Fetch the complete documentation index a…”
   • [claimed-docs] “Set up Greptile from your terminal with `greptile onboard` — or hand this page to your coding agent and have it run the setup for you.”

   proof ↗⚑ flag

   Cursor Bugbot✓fullprobed8/10

   Cursor publishes a working llms.txt index (HTTP 200) and provides machine-readable .md versions of its docs (e.g., docs/bugbot.md), directly enabling an agent to be pointed at agent-oriented documentation. Missing for 10: no evidence of llms-full.txt or explicit guidance encouraging agents to consume these docs, and no independent report of an agent successfully using this format end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://cursor.com/llms.txt # Cursor Documentation ## Get Started - https://cursor.com/docs.md - https://curso…”
   • [probe] “PROBE docs-md: HTTP 200 at https://cursor.com/docs/bugbot.md # Bugbot Bugbot reviews pull requests and identifies bugs, security issues, an…”

   proof ↗⚑ flag

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

   weight 2 · round to Greptile
   Greptile✓fullprobed8/10

   Greptile ships an official CLI (`greptile review`, `greptile onboard`) that runs headlessly against a diff in ~60 seconds and is explicitly designed for coding agents to invoke on their own code, plus automated PR-triggered reviews on GitHub/GitLab that require no human interaction — both classic CI/automation patterns. missing for 10: explicit CI pipeline example (e.g., GitHub Actions/GitLab CI YAML snippet) and independent third-party confirmation of headless CI usage

   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”
   • [claimed-docs] “Coding agents can use the greptile cli to review their own code”
   • [claimed-docs] “Set up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first …”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”
   • [probe] “official CLI documented at https://www.greptile.com/docs/code-review/greptile-cli”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed6/10

   Bugbot runs automatically on every PR update across GitHub, GitLab, Bitbucket, and Azure DevOps without manual invocation, which is inherently headless/automated behavior, and can also be triggered by PR comments (a CI-like trigger). However, there's no documented standalone CLI, API, or explicit 'run in CI pipeline' mode independent of git-host PR events. Missing for 10: a documented CLI/API for invoking Bugbot outside PR webhooks, evidence of arbitrary CI pipeline integration (e.g. as a build step), and independent confirmation of headless automation reliability.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “GitHub (including GitHub Enterprise Server): See the GitHub integration page”
   • [claimed-docs] “GitLab (including GitLab Self-Hosted): See the GitLab integration page”
   • [claimed-docs] “Cloud Agents clone your code, work on branches, and open pull requests. Bugbot reviews pull requests and posts its findings as comments.”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”

   proof ↗⚑ flag

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

   weight 3 · round to Greptile
   Greptile~partialprobed6/10

   Greptile exposes a documented MCP v2 server (fetch PR comments, apply fixes, manage patterns) and a CLI (`greptile review`, `greptile onboard`) that let an AI agent drive the product programmatically, which functions as a de-facto public API for agentic use, but explicit REST/OpenAPI documentation was probed and returned 404s, meaning no conventional public API spec is confirmed. missing for 10: a documented REST/OpenAPI-style public API, independent confirmation that the MCP/CLI interfaces are being used as a full 'public API' by third parties.

   • [claimed-docs] “Fetch PR comments - Get unaddressed Greptile feedback for any PR”
   • [claimed-docs] “Connect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.”
   • [claimed-docs] “List unaddressed Greptile comments for PR #5 in owner/repo”
   • [claimed-docs] “With MCP, you can view, search, and create patterns from your IDE.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.c…”
   • [probe] “official MCP server documented at https://www.greptile.com/docs/mcp-v2/overview”
   • [probe] “official CLI documented at https://www.greptile.com/docs/code-review/greptile-cli”
   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”
   • [claimed-docs] “Coding agents can use the greptile cli to review their own code”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   Evidence shows Bugbot is driven via PR comment triggers (`bugbot run`, `cursor review`) and VCS integrations (GitHub/GitLab/Bitbucket/Azure DevOps), not via any documented public REST/webhook API for programmatic control. No API reference, SDK, or endpoint documentation appears anywhere in the pack.

   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “GitHub (including GitHub Enterprise Server): See the GitHub integration page”
   • [claimed-docs] “GitLab (including GitLab Self-Hosted): See the GitLab integration page”
   • [claimed-docs] “Connect Bitbucket Cloud repositories to Cloud Agents and Bugbot. Connect Bitbucket Data Center repositories to Bugbot.”
   • [claimed-docs] “Cloud Agents clone your code, work on branches, and open pull requests. Bugbot reviews pull requests and posts its findings as comments.”

   proof ↗⚑ flag

4. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Greptile—none0/10

   No evidence of any webhook subscription mechanism for events; Greptile's integrations documented are MCP, CLI, and agent 'Fix with your Agent' flows, but no docs mention webhooks for subscribing to review or event notifications.

   ⚑ flag

   Cursor Bugbot—none0/10

   No evidence anywhere in the pack of webhook subscription capability for Bugbot events; it integrates via PR comments/git provider webhooks internally but exposes no user-facing webhook subscription API.

   ⚑ flag

Agentic features

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

   weight 2 · round to Cursor Bugbot
   Greptile!disputedcontradicted6/10

   Greptile's core product surfaces AI-generated insights from codebase data — review comments, 0-5 confidence scores, sequence diagrams, auto-generated tests, security findings, and a learning system that improves suggestions from feedback (greptile-docs-16/17/18/25/33, comm-1, comm-8). However, hands-on community reports document concrete failures of this insight-generation capability: repos stuck processing or erroring out, incomplete/incorrect answers on template-heavy code, and search bugs on multi-branch repos (greptile-comm-3/4/5/6/7), directly contradicting the polished vendor narrative for at least some users. Missing for 10: consistent independent verification that insights are reliably accurate across codebases, resolution of the documented processing/error failures, and more recent hands-on corroboration beyond mixed 2024 anecdotes.

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “Know how safe a PR is to merge at a glance with a 0-5 score”
   • [claimed-docs] “Parse complex changes with sequence diagrams and flowcharts generated for every PR”
   • [claimed-docs] “Automatically generate unit tests for new and changed code in every PR”
   • [claimed-docs] “Greptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [community] “Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code r…”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”
   • [community] “Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incom…”
   • [community] “Not a single repo I've tried works. A lot of them seem not to have finished processing, but even the ones that have finished don't work.”
   • [community] “Ran it on my OSS project - stuck at 99% loading for ~30 minutes, then got 'Error: Internal error while locating sources' on every query. 'Th…”
   • [community] “Loading a repo with many branches (cassandra), searching for 'vsearch' surfaced branch-named results (CNDB-8708-vsearch, DSP-23946-vsearch) …”
   • [community] “Getting 'Error: Internal error while processing request' while trying on my personal public github repo.”

   proof ↗⚑ flag

   Cursor Bugbot✓fullcommunity8/10

   Bugbot is explicitly an AI reviewer that analyzes PR diffs to generate bug, security, and code-quality insights with inline explanations and suggested fixes, directly matching the story of AI-generated insights from the product's data. Community feedback (HN) corroborates real-world value, though some users report subtly wrong or frivolous suggestions. Missing for 10: independent benchmark of insight accuracy, and resolution of the mixed community sentiment on reliability.

   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”
   • [community] “I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it'…”
   • [community] “I assume that this is the same as when Cursor spontaneously decides to show code review comments in the IDE as part of some upsell? In that …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Greptile✓fullclaimed7/10

   Greptile's core product is background automation: it automatically reviews every PR once triggers are configured (greptile-docs-1, greptile-docs-5), runs an autonomous sandboxed runtime-testing agent (TREX, greptile-docs-19), pairs static+security agents run automatically per PR (greptile-docs-25), and routes reviews to different models autonomously based on PR author (greptile-docs-27) - all without manual per-run invocation. Custom rules, strictness controls, and greptile.json let users configure how these background automations behave (greptile-docs-20, greptile-docs-21, greptile-docs-22). missing for 10: independent/hands-on confirmation that the automation runs reliably unattended over time (community evidence only covers review quality/accuracy, not background reliability), and no evidence of general-purpose scheduled/triggered automations beyond PR-review-centric events

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “Set up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first …”
   • [claimed-docs] “TREX runs your PR branch in a sandbox to find the bugs that only show up at runtime. It starts services, mocks inputs, clicks through UI flo…”
   • [claimed-docs] “Greptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.”
   • [claimed-docs] “v5 is faster, catches more bugs, and flags fewer false positives by running a swarm of narrowly scoped agents in parallel.”
   • [claimed-docs] “Greptile can now detect when a PR was authored by a coding agent and route the review to a different model. If Claude wrote it, GPT reviews …”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”

   proof ↗⚑ flag

   Cursor Bugbot✓fullclaimed7/10

   Bugbot autonomously reviews every PR update in the background without manual intervention, and supports organization-wide automation rules via Bugbot Automations, plus configurable effort levels and custom review guidelines (BUGBOT.md). missing for 10: no independent/hands-on evidence confirming the 'Bugbot Automations' feature's scope or reliability, and no detail on scheduling/triggers beyond PR events.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “With usage billing, you can now choose the effort level Bugbot uses when reviewing PRs. Users can configure Bugbot to think for longer and r…”

   proof ↗⚑ flag

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

   weight 3 · round to Cursor Bugbot
   Greptile!disputedcontradicted5/10

   Greptile's docs strongly position it as a built-in AI agent you delegate to — it reviews PRs, generates unit tests, runs sandboxed dynamic tests (TREX), answers codebase questions, and iterates fixes (greptile-docs-1, 18, 19, 33). Community reports include successful task delegation (accurate Q&A, catching real issues in production use) but also concrete hands-on failures — repos stuck processing, 'Internal error' responses, incomplete/incorrect analysis on complex code like C++ templates — directly contradicting reliability of the delegated-task experience. Missing for 10: consistent reliability across codebases/languages, resolution of reported internal errors, and independent benchmarks confirming task success rates.

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “Automatically generate unit tests for new and changed code in every PR”
   • [claimed-docs] “TREX runs your PR branch in a sandbox to find the bugs that only show up at runtime. It starts services, mocks inputs, clicks through UI flo…”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [community] “Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code r…”
   • [community] “Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incom…”
   • [community] “Not a single repo I've tried works. A lot of them seem not to have finished processing, but even the ones that have finished don't work.”
   • [community] “Ran it on my OSS project - stuck at 99% loading for ~30 minutes, then got 'Error: Internal error while locating sources' on every query. 'Th…”
   • [community] “Getting 'Error: Internal error while processing request' while trying on my personal public github repo.”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed5/10

   Bugbot supports delegating specific tasks — manually triggering AI reviews via PR comments and delegating fixes to Cursor's Cloud Agents via 'Fix in Cursor'/'Fix in Web' links — but it is a narrow, single-purpose review/fix agent rather than a general-purpose built-in assistant you can delegate arbitrary tasks to. missing for 10: evidence of open-ended task delegation beyond PR review/fix workflows, and a conversational/general-assistant interface within Bugbot itself.

   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “Fix in Cursor links open issues directly in Cursor”
   • [claimed-docs] “Fix in Web links open issues directly in cursor.com/agents”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Cloud Agents clone your code, work on branches, and open pull requests. Bugbot reviews pull requests and posts its findings as comments.”

   proof ↗⚑ flag

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

   weight 2 · round to Cursor Bugbot
   Greptile~partialcommunity5/10

   Greptile supports natural-language interaction for codebase Q&A (comm-1 shows a user asking an English question and getting an accurate answer) and lets teams define custom review rules in plain language (greptile-docs-21), but its primary interfaces (CLI commands like `greptile review`, MCP tool calls, PR-trigger automation) are structured, not conversational commands. missing for 10: a documented chat/command interface for issuing arbitrary natural-language instructions to control reviews or agent actions, and independent verification that NL querying works reliably at scale.

   • [community] “Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code r…”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”
   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed6/10

   Bugbot can be triggered and configured via natural-language-like PR comments (e.g. `bugbot run`, `verbose=true`) and effort levels can be set via natural language instructions ('Describe in natural language when Bugbot should use low, default, or high effort'), showing some NL-driven control. However, this is limited to comment-based commands and config strings rather than full conversational/agentic natural-language operation of the tool itself. missing for 10: evidence of open-ended conversational control (e.g. chat-based instructions beyond fixed commands/effort strings), independent confirmation of NL effort-setting actually working, and broader NL command surface beyond review triggering.

   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “Comment `bugbot run verbose=true` or `cursor review verbose=true` on the pull request. Bugbot replies with a table of the rules included in …”
   • [claimed-docs] “Describe in natural language when Bugbot should use low, default, or high effort. Cursor will dynamically set effort levels based on your in…”
   • [claimed-docs] “Smart: Describe in natural language when Bugbot should use low, default, or high effort. Cursor will dynamically set effort levels based on …”
   • [claimed-docs] “Comment `cursor review verbose=true` or `bugbot run verbose=true` on the PR for detailed logs, which Bugbot rules loaded, and a request ID”

   proof ↗⚑ flag

Ai authored

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

   weight 2 · round to Greptile
   Greptile✓fullcommunity8/10

   Greptile explicitly documents detecting when a PR was AI-authored and routing it to a different model for review (docs-27), reviews every PR automatically at scale via parallel agent swarms (docs-26), runs runtime sandbox testing (TREX, docs-19), and offers an iterative 'Greplooping' fix cycle until a PR hits 5/5 confidence with zero unresolved comments (docs-13/28) — directly matching the 'holds the line on agent PRs at volume' story. Community evidence corroborates real-world catch-rate value (comm-8) though some older reports cite reliability/error issues unrelated specifically to this agent-detection feature. Missing for 10: independent hands-on verification of the specific agent-authorship detection/routing feature and concrete volume/throughput metrics.

   • [claimed-docs] “Greptile can now detect when a PR was authored by a coding agent and route the review to a different model. If Claude wrote it, GPT reviews …”
   • [claimed-docs] “v5 is faster, catches more bugs, and flags fewer false positives by running a swarm of narrowly scoped agents in parallel.”
   • [claimed-docs] “TREX runs your PR branch in a sandbox to find the bugs that only show up at runtime. It starts services, mocks inputs, clicks through UI flo…”
   • [claimed-docs] “Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Greplooping Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Greptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”

   proof ↗⚑ flag

   Cursor Bugbot!disputedcontradicted6/10

   Bugbot is explicitly built to auto-review every PR at scale (docs-1, docs-13, docs-24) with configurable effort/depth for thorough review (docs-8, docs-26) and project-specific rules (docs-6) — squarely matching the 'verify AI-authored code at volume' story. However, hands-on community reports are mixed: some engineers report it catches genuine bugs reliably at scale (comm-2, comm-4), while others report it producing 'subtly wrong' comments or flip-flopping on its own fix recommendations, leading them to disable auto-review (comm-1, comm-3) — a concrete contradiction of the 'holds the line' claim in real usage. Missing for 10: independent benchmark data on bug-catch/false-positive rates at scale, and resolution of the reliability inconsistency reported by users.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “With usage billing, you can now choose the effort level Bugbot uses when reviewing PRs. Users can configure Bugbot to think for longer and r…”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [claimed-docs] “High: Bugbot spends more time reasoning. Reviews are more expensive and take longer, but Bugbot may find more bugs.”
   • [community] “I've witnessed numerous instances where either the cursor bugbot or Claude has found a bug and recommended a reasonable fix. The fix has bee…”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”
   • [community] “I assume that this is the same as when Cursor spontaneously decides to show code review comments in the IDE as part of some upsell? In that …”
   • [community] “I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it'…”

   proof ↗⚑ flag

Checks

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

   weight 2 · round drawn
   Greptile~partialclaimed6/10

   Greptile supports custom, team-defined rules in plain language ('Create custom rules that catch team-specific issues') configured via greptile.json, and these run automatically on every PR alongside a confidence score/unresolved-comment gate that can act as a de facto merge check (docs-21, docs-22, docs-13). However, there's no explicit evidence of a dedicated 'pre-merge check' construct with pass/fail CI status gating, nor examples matching the story's specific phrasing (e.g., 'docs updated', 'tests cover new paths') as discrete named checks. Missing for 10: explicit merge-blocking/CI-status-check integration tied to named custom checks, and concrete examples/documentation of plain-language check definitions beyond generic 'custom rules'.

   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed6/10

   Bugbot lets teams define custom, natural-language review guidelines via `.cursor/BUGBOT.md` and org-wide rules via Bugbot Automations, and it runs automatically on every PR, closely matching the 'plain language custom check' idea. However, the evidence describes it purely as a commenting/review bot (posts findings, suggested fixes) rather than a pass/fail pre-merge gate tied to specific check names like 'docs updated' or 'tests cover new paths', and there's no evidence of blocking merges or exposing check results as CI status checks. Missing for 10: explicit support for named custom checks that gate/block merges, documentation of specific check definitions beyond general review guidelines, and evidence of merge-blocking behavior.

   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”

   proof ↗⚑ flag

Fixes

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

   weight 3 · round to Greptile
   Greptile✓fullclaimed8/10

   Docs describe a complete in-PR fix loop: each review comment has a 'Fix with your Agent' button that sends file paths/lines/suggested code to Claude Code, Codex, Cursor, or Devin, a 'Fix All' button for batch fixes, MCP integration to fetch/resolve comments from the IDE, and 'Greplooping' to iteratively fix until a perfect review score—all without leaving the PR context. Missing for 10: independent/hands-on evidence confirming the fix-apply workflow works reliably in practice (community evidence in the pack addresses general review quality/accuracy, not this specific fix-application flow).

   • [claimed-docs] “Every review comment includes a Fix with your Agent button that sends the issue — with file paths, line numbers, and suggested code — straig…”
   • [claimed-docs] “A Fix All button in the review summary sends every issue at once.”
   • [claimed-docs] “Launch any agent in one click with a Greptile comment, full context, and suggested fix.”
   • [claimed-docs] “Access Greptile review comments, apply fixes, and manage coding patterns directly from your agent of choice.”
   • [claimed-docs] “Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Fetch PR comments - Get unaddressed Greptile feedback for any PR”
   • [claimed-docs] “Greplooping Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”
   • [claimed-docs] “Every Greptile review comment includes a **Fix with your Agent** button. Click it, and the issue gets sent straight to your coding agent wit…”

   proof ↗⚑ flag

   Cursor Bugbot~partialcommunity6/10

   Bugbot findings include 'Fix in Cursor' and 'Fix in Web' links that launch an agent to generate the fix directly from the PR comment, and community reports confirm fixes get implemented from its suggestions (though with some friction/reverts noted). However, the docs describe these as links that open a separate Cursor/agents interface rather than an in-PR one-click apply/commit, so it's not fully 'without leaving the PR' and reliability is debated. Missing for 10: evidence of a native in-PR commit/apply button, and stronger independent confirmation that agent-generated fixes are reliably applied back to the PR without manual intervention.

   • [claimed-docs] “Fix in Cursor links open issues directly in Cursor”
   • [claimed-docs] “Fix in Web links open issues directly in cursor.com/agents”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [community] “I've witnessed numerous instances where either the cursor bugbot or Claude has found a bug and recommended a reasonable fix. The fix has bee…”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”

   proof ↗⚑ flag

Handoff

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

   weight 2 · round to Greptile
   Greptile✓fullclaimed9/10

   Greptile documents a 'Fix with your Agent' button on every review comment that sends file paths, line numbers, and suggested code directly to Claude Code, Cursor, Codex, Devin, or Conductor, plus a 'Fix All' button for batch handoff, and an MCP v2 server letting agents fetch/resolve unaddressed comments with OAuth support for Cursor/Claude Code/VS Code/Codex. This directly matches the story's clean hand-off requirement with both one-click integration and MCP-based programmatic access. Missing for 10: independent/hands-on community verification that the 'Fix with your Agent' handoff works reliably in practice (only vendor docs cited).

   • [claimed-docs] “Every review comment includes a Fix with your Agent button that sends the issue — with file paths, line numbers, and suggested code — straig…”
   • [claimed-docs] “A Fix All button in the review summary sends every issue at once.”
   • [claimed-docs] “Launch any agent in one click with a Greptile comment, full context, and suggested fix.”
   • [claimed-docs] “Access Greptile review comments, apply fixes, and manage coding patterns directly from your agent of choice.”
   • [claimed-docs] “View and resolve review comments directly from Claude Code.”
   • [claimed-docs] “Fetch PR comments - Get unaddressed Greptile feedback for any PR”
   • [claimed-docs] “Connect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”
   • [claimed-docs] “Every Greptile review comment includes a **Fix with your Agent** button. Click it, and the issue gets sent straight to your coding agent wit…”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed6/10

   Bugbot provides direct one-click handoff into Cursor's own agent ("Fix in Cursor" and "Fix in Web" opening cursor.com/agents) and posts inline PR comments with suggested fixes, satisfying the core 'review findings hand off cleanly' need for Cursor itself. However, there's no evidence of copyable fix prompts formatted for external tools, nor any direct integration with Claude Code or Codex as named in the story. missing for 10: explicit copyable fix-prompt format, direct integration/handoff to Claude Code, direct integration/handoff to Codex.

   • [claimed-docs] “Fix in Cursor links open issues directly in Cursor”
   • [claimed-docs] “Fix in Web links open issues directly in cursor.com/agents”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”

   proof ↗⚑ flag

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

   weight 2 · round to Greptile
   Greptile~partialclaimed6/10

   Greptile documents a 'Fix All' button that sends every issue in a review at once to a coding agent, and `greptile onboard` can enable multiple repositories and import existing AI rules files in one command — both genuine bulk operations. However, evidence doesn't show bulk actions across many PRs, repos, or reviews simultaneously (e.g., batch-reviewing multiple PRs, mass-applying custom rules across repos), and there's no independent/hands-on confirmation of these bulk features working at scale. missing for 10: cross-PR/cross-repo bulk review or fix operations, evidence of bulk custom-rule application across an org, independent verification of Fix All/onboard at scale.

   • [claimed-docs] “A Fix All button in the review summary sends every issue at once.”
   • [claimed-docs] “Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Greplooping Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Bugbot automatically reviews every PR update and lets team admins set organization-wide rules via Bugbot Automations, which gives some cross-item automation, but there's no documented capability to trigger or manage reviews in bulk across many PRs/repos at once from a single user action. missing for 10: explicit bulk/batch trigger across multiple PRs or repos, any UI/API for multi-item selection, evidence of bulk fix application beyond per-PR 'Fix in Cursor/Web' links.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”

   proof ↗⚑ flag

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

   weight 3 · round to Cursor Bugbot
   Greptile~partialclaimed5/10

   Greptile lets users configure review triggers, custom standards/rules (greptile.json, custom-standards docs), strictness/noise control, and automated actions like Fix with your Agent triggered on review events, which is a form of rule-based automation tied to PR events. However, this is scoped to code review workflows only (triggering on PR open/comment events) rather than a general-purpose event/rule engine for arbitrary automation actions. missing for 10: evidence of a broader/generic rules engine spanning multiple event types beyond PR review, user-defined conditional logic beyond review strictness/custom standards, and independent confirmation these triggers work reliably as described.

   • [claimed-docs] “Set up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first …”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”
   • [claimed-docs] “Every Greptile review comment includes a **Fix with your Agent** button. Click it, and the issue gets sent straight to your coding agent wit…”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed6/10

   Bugbot supports automatic triggers on PR updates, manual triggers via comments, custom repo-level guidelines (BUGBOT.md), and org-wide rules via Bugbot Automations — showing genuine rule-based automation tied to events. However, the evidence doesn't detail a broad general-purpose 'if X event then Y action' rules engine beyond PR review triggers and effort-level configuration. missing for 10: documentation of the full scope/flexibility of 'Bugbot Automations' rules (what events/actions are configurable beyond PR-triggered reviews), independent hands-on verification of automation rule customization beyond BUGBOT.md.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”
   • [claimed-docs] “Describe in natural language when Bugbot should use low, default, or high effort. Cursor will dynamically set effort levels based on your in…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Greptile—none0/10

   Greptile's automation is event-triggered (runs on every PR, via CLI or CI), not evidence of user-defined recurring/scheduled jobs or cron-like workflows; no docs mention scheduling, cron triggers, or periodic batch runs.

   ⚑ flag

   Cursor Bugbot—none0/10

   Bugbot's docs describe event-triggered reviews (automatic on PR update, or manual comment trigger) and org-wide 'Automations' rules, but there is no evidence of true recurring/scheduled job execution (e.g., cron-like or time-based triggers) as opposed to PR-event triggers.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”

   proof ↗⚑ flag

Context

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

   weight 2 · round drawn
   Greptile—none0/10

   Greptile's evidence covers per-PR review, codebase-wide Q&A, and self-hosted deployment for large dev teams, but there is no documentation or feature description addressing coherent review of changes spanning multiple repositories or explicit monorepo-scale review orchestration. The only tangentially relevant community evidence (greptile-comm-6) reports a bug where searching a large, many-branch repo (Cassandra) failed to surface correct results, which does not support (and mildly undercuts) coherent large-scale/monorepo understanding.

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [community] “Loading a repo with many branches (cassandra), searching for 'vsearch' surfaced branch-named results (CNDB-8708-vsearch, DSP-23946-vsearch) …”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   Bugbot's documented behavior is per-repository PR review (diffs, inline comments, BUGBOT.md for repo-specific rules) with no evidence of coherent review across multiple linked repositories or explicit large-monorepo context handling. Missing for 10: any mention of cross-repo dependency awareness, monorepo-scale indexing, or coordinated review across repos in a single PR/change set.

   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”

   proof ↗⚑ flag

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

   weight 3 · round to Greptile
   Greptile~partialcommunity6/10

   Greptile's docs explicitly claim reviews use 'complete understanding of your codebase' (greptile-docs-1), index existing rule/convention files like AGENTS.md/cursor.rules (greptile-docs-35), and support custom team-specific rules (greptile-docs-21) that presumably span beyond the diff. A community hands-on report corroborates deep repo-level Q&A accuracy (greptile-comm-1), but other hands-on reports describe incomplete/incorrect answers on complex code (templates) and reliability failures on some repos (greptile-comm-3, greptile-comm-4, greptile-comm-5), showing the whole-repo understanding is inconsistent in practice. Missing for 10: independent verification specifically that PR review COMMENTS (not just Q&A) cite call sites/related modules beyond the diff, and resolution of the negative reliability reports.

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “Automatically index existing rule files like Claude.md, AGENTS.md, and cursor.rules for richer review context.”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [community] “Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code r…”
   • [community] “Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incom…”
   • [community] “Not a single repo I've tried works. A lot of them seem not to have finished processing, but even the ones that have finished don't work.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Docs state Bugbot "analyzes PR diffs" (docs-24) and reads PR comments for context (docs-5/14), plus BUGBOT.md lets teams encode repo-specific conventions (docs-6) — suggesting some repo-level convention awareness, but there is no explicit claim or evidence that Bugbot traces call sites or related modules beyond the changed hunks. Missing for 10: explicit documentation or examples of cross-file/call-site analysis, evidence review considers unchanged related modules, and independent confirmation that comments reference whole-repo context rather than diff-only.

   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Uses existing PR comments as context: reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior f…”

   proof ↗⚑ flag

Memory

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

   weight 2 · round to Greptile
   Greptile✓fullclaimed7/10

   Greptile documents a persistent-learning system: thumbs up/down reactions and comments train the model over weeks (docs-4, docs-33), custom rules/patterns can be created and searched via MCP (docs-21, docs-30), team conventions are codified in a `greptile.json` config that overrides defaults per-repo (docs-22), and existing rule files like CLAUDE.md/AGENTS.md/cursor.rules are auto-indexed for context (docs-35, docs-31). This directly matches the story of building and applying a persistent memory of conventions/past decisions to future PRs. Missing for 10: independent/hands-on confirmation that the learning system measurably reduces noise over time as claimed, and community evidence is mixed/dated rather than specifically validating the memory feature.

   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “With MCP, you can view, search, and create patterns from your IDE.”
   • [claimed-docs] “Automatically index existing rule files like Claude.md, AGENTS.md, and cursor.rules for richer review context.”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Bugbot supports a manually-authored `.cursor/BUGBOT.md` for team conventions and reads existing PR comments to avoid duplicating feedback, but this is static, user-maintained configuration and per-PR context — not an evolving, persistent memory that automatically learns from past review decisions across PRs. Missing for 10: evidence of automatic learning/adaptation from historical review outcomes, cross-PR memory beyond the current thread, and any feedback loop that updates conventions based on accepted/rejected suggestions.

   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Uses existing PR comments as context: reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior f…”
   • [claimed-docs] “reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior feedback”

   proof ↗⚑ flag

Chat

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

   weight 2 · round to Greptile
   Greptile~partialcommunity5/10

   Docs confirm the PR-thread reply channel exists and is used to tune reviews (👍/👎 and replies 'teach' Greptile, greptile-docs-4/33), and one community report shows Greptile answering a direct codebase question accurately (greptile-comm-1), while another notes it gives authors 'a chance to reply' during review (greptile-comm-8). However, there's no explicit documentation of replying with a question/command in-thread and receiving a contextual answer (as opposed to reaction-based learning), and other community reports show inconsistent/failed query handling (greptile-comm-3,4,5,7). Missing for 10: first-party docs explicitly describing PR-thread Q&A/command handling and consistent independent confirmation of in-context answers.

   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [community] “Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code r…”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”
   • [community] “Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incom…”
   • [community] “Not a single repo I've tried works. A lot of them seem not to have finished processing, but even the ones that have finished don't work.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Bugbot supports comment-based commands in the PR thread (`cursor review`, `bugbot run`, `verbose=true`) and reads prior PR comments to build context and avoid duplicate suggestions, showing some interactive, context-aware behavior. However, there is no evidence it supports open-ended conversational replies (answering arbitrary questions or explaining its reasoning on demand) beyond the fixed set of trigger commands. Missing for 10: evidence of free-form Q&A/explanation replies in the PR thread, examples of it responding to developer questions rather than just re-running reviews.

   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “Uses existing PR comments as context: reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior f…”
   • [claimed-docs] “Comment `bugbot run verbose=true` or `cursor review verbose=true` on the pull request. Bugbot replies with a table of the rules included in …”
   • [claimed-docs] “Comment `cursor review verbose=true` or `bugbot run verbose=true` on the PR for detailed logs, which Bugbot rules loaded, and a request ID”

   proof ↗⚑ flag

Control

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

   weight 1 · round drawn
   Greptile~partialclaimed5/10

   Greptile supports on-demand review via CLI (`greptile review`), configurable strictness/noise control, custom rules, and per-branch settings via greptile.json read from the source branch, plus generic 'configure review triggers' in quickstart — giving developers some control over when/how reviews run. However there is no explicit evidence of skipping draft PRs or filtering by label, which the story specifically calls out. Missing for 10: explicit draft-PR skip toggle, label-based filtering, and independent confirmation these controls work as documented.

   • [claimed-docs] “Set up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first …”
   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed5/10

   Bugbot supports on-demand triggering via PR comments (`cursor review`/`bugbot run`) and automatic review on every PR update, plus org-wide rules via Bugbot Automations and BUGBOT.md guidelines. However, there's no evidence of draft-PR skipping, branch/label filtering, or granular per-repo/per-branch control settings that let developers scope exactly when the bot runs. missing for 10: draft-PR skip behavior, branch/label-based filtering rules, explicit settings UI for scoping trigger conditions beyond org-wide automations.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”

   proof ↗⚑ flag

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

   weight 2 · round to Greptile
   Greptile~partialprobed5/10

   Greptile exposes significant non-UI surfaces — a CLI (`greptile onboard`, `greptile review`) and an official MCP server (fetch PR comments, apply fixes, manage patterns) — that mirror parts of the UI experience (docs-14, docs-23, docs-24, docs-31, probe-4, probe-5). However, no OpenAPI/REST API spec was found (all candidate paths 404'd, greptile-probe-3), and several admin-level settings (e.g., 'Default Coding Agents' toggle, org onboarding via dashboard) are documented as UI-only (Settings → Code Review, docs-34), suggesting incomplete API/CLI parity for configuration and org management. missing for 10: a documented general-purpose REST/GraphQL API or OpenAPI spec, and evidence that all dashboard admin settings (strictness, default agents, org config) can be set via CLI/MCP rather than only the web UI.

   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”
   • [claimed-docs] “Fetch PR comments - Get unaddressed Greptile feedback for any PR”
   • [claimed-docs] “Connect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.c…”
   • [probe] “official MCP server documented at https://www.greptile.com/docs/mcp-v2/overview”
   • [probe] “official CLI documented at https://www.greptile.com/docs/code-review/greptile-cli”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   No evidence of a public API for Bugbot; all interactions documented are via PR comments (GitHub/GitLab/Bitbucket/Azure DevOps), the Cursor IDE, or BUGBOT.md config files, not a programmatic API for triggering/configuring reviews. Absence of evidence for this applicable capability yields none.

   ⚑ flag

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

   weight 3 · round drawn
   Greptile—none0/10

   No evidence of any data export feature or open-format data portability for user data (reviews, patterns, learned rules, etc.); self-hosting only affects where data lives, not exportability. Self-hosted deployment keeps logs on customer servers, but there's no documented export mechanism or open-format dump users can take with them if they leave.

   • [claimed-docs] “Security page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as …”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   Evidence covers Bugbot's PR review features, integrations, and account deletion, but there is no mention of any data export functionality or open-format export of reviews/settings — missing for 10: any export tool, data portability feature, or open-format download of Bugbot's findings/config.

   • [claimed-docs] “Security page, certifications: "Cursor holds AIUC-1, ISO/IEC 27001:2022, and ISO/IEC 42001:2023 certifications, along with a SOC 2 Type II a…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Greptile—none0/10

   Greptile is a closed, commercial SaaS/self-hosted product (deployed via Docker Compose/Kubernetes) with no evidence of an open-source license or publicly readable source code; self-hosting means running their binaries, not accessing source.

   • [claimed-docs] “Deploy Greptile in your own infrastructure with Docker Compose. Supports AWS, GCP, Azure, air-gapped environments, and custom LLM configurat…”
   • [claimed-docs] “Docker Compose: Up to 100 developers. Single VM, simpler operations. Kubernetes: 100+ developers. Horizontal scaling, high availability.”
   • [claimed-docs] “Security page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as …”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   No evidence that Cursor Bugbot's source code is open or under an open license; it is a closed proprietary SaaS review bot with only docs, security/certification pages, and llms.txt probes present. Missing for 10: any open-source license, public source repository, or statement of code availability.

   ⚑ flag

Platforms

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

   weight 3 · round to Cursor Bugbot
   Greptile~partialcommunity7/10

   Docs clearly describe installing via GitHub/GitLab, automated PR reviews within 5 minutes (greptile-docs-5), and native review comments with actionable buttons (greptile-docs-1, greptile-docs-2, greptile-docs-36). Community testimony (greptile-comm-8) corroborates real-world use catching issues on PRs, but other community reports describe reliability issues (stuck processing, internal errors) with the underlying platform, and no independent source specifically confirms the 'minutes to install' claim or inline-comment UX end-to-end. missing for 10: independent hands-on confirmation of install speed and native inline-comment rendering, and resolution of community-reported reliability issues.

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “Every review comment includes a Fix with your Agent button that sends the issue — with file paths, line numbers, and suggested code — straig…”
   • [claimed-docs] “Set up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first …”
   • [claimed-docs] “Every Greptile review comment includes a **Fix with your Agent** button. Click it, and the issue gets sent straight to your coding agent wit…”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”
   • [community] “Not a single repo I've tried works. A lot of them seem not to have finished processing, but even the ones that have finished don't work.”
   • [community] “Ran it on my OSS project - stuck at 99% loading for ~30 minutes, then got 'Error: Internal error while locating sources' on every query. 'Th…”

   proof ↗⚑ flag

   Cursor Bugbot✓fullcommunity8/10

   Docs confirm installation via GitHub/GitLab apps that connect repos to Bugbot, automatic reviews on every PR update, and findings posted as native inline PR comments with explanations/fix suggestions; community reports corroborate it running live in orgs' PR workflows. Minor gap: no explicit evidence of the 'within minutes' setup speed or independent onboarding walkthrough, missing for 10: independent verification of install speed/time-to-first-review, edge-case reliability data beyond mixed community sentiment.

   • [claimed-docs] “GitHub (including GitHub Enterprise Server): See the GitHub integration page”
   • [claimed-docs] “GitLab (including GitLab Self-Hosted): See the GitLab integration page”
   • [claimed-docs] “The Cursor GitHub app connects your repositories so you can use features like [Cloud Agents](/docs/cloud-agent) and [Bugbot](/docs/bugbot).”
   • [claimed-docs] “The GitLab integration connects your repositories so you can use features like [Cloud Agents](/docs/cloud-agent) and [Bugbot](/docs/bugbot).”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”
   • [community] “I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it'…”

   proof ↗⚑ flag

Suggestions

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

   weight 3 · round drawn
   Greptile~partialclaimed5/10

   Greptile's review comments include a one-click 'Fix with your Agent' button that sends suggested code with file/line context to an external coding agent (Claude Code, Cursor, Codex, Devin) to apply the fix, and a 'Fix All' button for bulk sends (greptile-docs-2, greptile-docs-3, greptile-docs-36, greptile-docs-10). This is a one-click flow but requires routing through a separate coding agent to actually commit the change, rather than a native inline 'commit suggestion' diff applied directly in the PR. Missing for 10: evidence of a native GitHub-style suggested-diff with a direct 'commit suggestion' button that applies without invoking an external agent, and independent/hands-on confirmation that the agent-applied fix actually commits cleanly.

   • [claimed-docs] “Every review comment includes a Fix with your Agent button that sends the issue — with file paths, line numbers, and suggested code — straig…”
   • [claimed-docs] “A Fix All button in the review summary sends every issue at once.”
   • [claimed-docs] “Launch any agent in one click with a Greptile comment, full context, and suggested fix.”
   • [claimed-docs] “Every Greptile review comment includes a **Fix with your Agent** button. Click it, and the issue gets sent straight to your coding agent wit…”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed5/10

   Bugbot leaves inline PR comments with suggested fixes and offers 'Fix in Cursor' / 'Fix in Web' links, but these open the issue in Cursor or cursor.com/agents for the agent to implement — not a native one-click 'commit suggestion' diff applied directly in the PR review UI as the story describes. Missing for 10: evidence of a native GitHub-style committable suggestion block that can be applied with a single click directly in the PR thread, and independent confirmation of this specific commit-suggestion workflow.

   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [claimed-docs] “Fix in Cursor links open issues directly in Cursor”
   • [claimed-docs] “Fix in Web links open issues directly in cursor.com/agents”

   proof ↗⚑ flag

Summaries

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

   weight 2 · round to Greptile
   Greptile✓fullcommunity7/10

   Greptile's docs describe automatic review of every PR with full codebase context, a 0-5 merge-safety score, and auto-generated sequence diagrams/flowcharts for every PR specifically to help parse complex changes — directly matching the 'summary + walkthrough' story. Community evidence (comm-8) corroborates real-world use where Greptile catches issues before human review, giving reviewers a head start. Missing for 10: no independent verification of diagram/summary quality or accuracy, and no evidence separating 'summary' as a distinct named artifact from the diagrams/score/comments bundle.

   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “Know how safe a PR is to merge at a glance with a 0-5 score”
   • [claimed-docs] “Parse complex changes with sequence diagrams and flowcharts generated for every PR”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   Evidence shows Bugbot analyzes PR diffs for bugs, security issues, and code quality, leaving inline comments with explanations/fixes — but nothing in the docs or community evidence describes an auto-generated PR summary or change walkthrough for reviewer orientation. Bugbot's function is bug-finding, not summarization.

   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [probe] “PROBE docs-md: HTTP 200 at https://cursor.com/docs/bugbot.md # Bugbot Bugbot reviews pull requests and identifies bugs, security issues, an…”

   proof ↗⚑ flag

Updates

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

   weight 2 · round to Cursor Bugbot
   Greptile~partialclaimed7/10

   Docs describe Greptile tracking 'unaddressed' vs resolved comments and iterating until a PR reaches a perfect review (zero unresolved comments), implying it distinguishes fixed issues from outstanding ones across pushes, and the learning system adapts based on reactions to avoid repeating unwanted comments. However, there's no explicit first-party statement that a new commit push specifically triggers a fresh incremental review pass distinct from prior comments, and no independent/hands-on evidence confirming this exact re-review behavior in practice. Missing for 10: explicit doc on push-triggered incremental review mechanics, and community/hands-on confirmation that old fixed comments are not repeated after new commits.

   • [claimed-docs] “Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “Fetch PR comments - Get unaddressed Greptile feedback for any PR”
   • [claimed-docs] “Greplooping Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.”
   • [claimed-docs] “List unaddressed Greptile comments for PR #5 in owner/repo”
   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”

   proof ↗⚑ flag

   Cursor Bugbot✓fullprobed7/10

   Docs confirm Bugbot re-reviews automatically on every PR update and explicitly reads existing PR comments (top-level and inline) to avoid duplicate suggestions and build on prior feedback, which directly matches the incremental re-review story. Missing for 10: independent/hands-on confirmation that fixed issues are specifically marked resolved rather than re-flagged, and no detailed changelog of what 'tracking fixed' looks like in practice.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “Uses existing PR comments as context: reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior f…”
   • [claimed-docs] “reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior feedback”
   • [probe] “PROBE docs-md: HTTP 200 at https://cursor.com/docs/bugbot.md # Bugbot Bugbot reviews pull requests and identifies bugs, security issues, an…”

   proof ↗⚑ flag

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

   weight 2 · round to Greptile
   Greptile~partialclaimed6/10

   Greptile lets customers self-host the entire platform on their own infrastructure (AWS, GCP, Azure, or air-gapped) inside their own VPC, which effectively gives full control over where data physically resides, and logging can be disabled entirely in that mode. However, there is no documented region-selection feature for the standard hosted/SaaS offering (e.g., no EU vs US data-residency toggle) — residency is achieved only via the heavier self-hosting path, not as a first-class SaaS setting. Missing for 10: explicit hosted multi-region data residency options, third-party confirmation of self-host residency compliance (SOC2/GDPR data residency certifications).

   • [claimed-docs] “Deploy Greptile in your own infrastructure with Docker Compose. Supports AWS, GCP, Azure, air-gapped environments, and custom LLM configurat…”
   • [claimed-docs] “Docker Compose: Up to 100 developers. Single VM, simpler operations. Kubernetes: 100+ developers. Horizontal scaling, high availability.”
   • [claimed-docs] “Security page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as …”
   • [claimed-docs] “Security page, De-Identified Data and AI Training (vendor's own carve-out): "Greptile may aggregate and anonymize Customer Data ('De-Identif…”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   No evidence of data residency/region selection controls for Bugbot; only privacy-mode (no training) and certifications are mentioned, with no mention of choosing storage region. missing for 10: any documentation of regional data storage options, residency controls, or geo-specific hosting.

   ⚑ flag

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

   weight 3 · round to Cursor Bugbot
   Greptile~partialclaimed4/10

   Greptile's own security page states it may use de-identified customer data for 'AI Training and Learnings' as a standing carve-out, with no explicit toggle to opt out of this for standard hosted customers — only self-hosted deployments (with logging fully disabled and data kept in the customer's own VPC) offer a documented path to keep data out of Greptile's hands. This gives privacy-focused users a workaround (self-host) but not a clean, guaranteed 'no AI training' control for the mainstream SaaS offering. Missing for 10: an explicit opt-out/toggle for hosted customers to disable AI-training use of their (even de-identified) data, and independent confirmation that self-hosted mode fully excludes any data from training.

   • [claimed-docs] “Security page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as …”
   • [claimed-docs] “Security page, De-Identified Data and AI Training (vendor's own carve-out): "Greptile may aggregate and anonymize Customer Data ('De-Identif…”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed6/10

   Cursor's security docs explicitly state that enabling Privacy Mode means 'we will not train on your data,' and this is available to any account (free/Pro/team), which would extend to Bugbot's PR review data. However, the evidence pack contains no Bugbot-specific documentation confirming that Bugbot review data (PR diffs, comments) is covered under this toggle, nor independent corroboration of this behavior in practice for Bugbot specifically. Missing for 10: Bugbot-specific privacy/training documentation, independent verification that Bugbot respects Privacy Mode.

   • [claimed-docs] “Security page, Privacy Mode: "Privacy Mode can be enabled in settings or by a team or enterprise admin. Privacy Mode is available to anyone …”
   • [claimed-docs] “Security page, certifications: "Cursor holds AIUC-1, ISO/IEC 27001:2022, and ISO/IEC 42001:2023 certifications, along with a SOC 2 Type II a…”
   • [claimed-docs] “Runs automatic reviews on every PR update”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Greptile
   Greptile~partialclaimed5/10

   Greptile's security docs let customers self-host so logs stay only on their own servers and let customers turn off logging entirely for 100% private chats, which is meaningful retention control (greptile-supp-1). However, the same page discloses a standing carve-out that Greptile may aggregate/anonymize Customer Data for AI training even when logging is limited (greptile-supp-2), and there is no documented self-service deletion mechanism, retention period, or explicit 'delete my data' control for the standard SaaS offering. Missing for 10: explicit data-deletion API/workflow for cloud customers, documented retention windows, and clarity on how the AI-training carve-out interacts with opt-out settings.

   • [claimed-docs] “Security page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as …”
   • [claimed-docs] “Security page, De-Identified Data and AI Training (vendor's own carve-out): "Greptile may aggregate and anonymize Customer Data ('De-Identif…”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Cursor's security page (shared across products) mentions Privacy Mode ('we will not train on your data') and that accounts can be deleted anytime from Settings, which offers some data-control levers, but there is no Bugbot-specific documentation on retention periods for PR review data, comment history, or deletion of stored review artifacts. Missing for 10: Bugbot-specific data retention policy, explicit deletion/export controls for review comments and analysis data, and independent confirmation these controls apply to Bugbot's PR data.

   • [claimed-docs] “Security page, Privacy Mode: "Privacy Mode can be enabled in settings or by a team or enterprise admin. Privacy Mode is available to anyone …”
   • [claimed-docs] “Security page, certifications: "Cursor holds AIUC-1, ISO/IEC 27001:2022, and ISO/IEC 42001:2023 certifications, along with a SOC 2 Type II a…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Greptile~partialclaimed4/10

   Self-hosted deployments let customers 'turn off logging and make chats 100% private' (greptile-supp-1), but the standard/SaaS offering explicitly reserves the right to aggregate and anonymize customer data for 'AI Training and Learnings' (greptile-supp-2) with no documented opt-out mechanism for that telemetry. Missing for 10: an explicit SaaS-tier telemetry/usage-tracking opt-out toggle, and independent confirmation that opting out actually stops data collection.

   • [claimed-docs] “Security page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as …”
   • [claimed-docs] “Security page, De-Identified Data and AI Training (vendor's own carve-out): "Greptile may aggregate and anonymize Customer Data ('De-Identif…”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Cursor's security page mentions a 'Privacy Mode' that stops training on user data and account deletion options, which is adjacent to a privacy-posture ask, but there's no explicit documentation of a telemetry/usage-tracking opt-out specific to Bugbot itself. Missing for 10: explicit Bugbot-specific telemetry/usage tracking opt-out setting, documentation distinguishing telemetry from training-data usage, and any independent confirmation that tracking can be disabled.

   • [claimed-docs] “Security page, Privacy Mode: "Privacy Mode can be enabled in settings or by a team or enterprise admin. Privacy Mode is available to anyone …”
   • [claimed-docs] “Security page, certifications: "Cursor holds AIUC-1, ISO/IEC 27001:2022, and ISO/IEC 42001:2023 certifications, along with a SOC 2 Type II a…”

   proof ↗⚑ flag

Analytics

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

   weight 1 · round to Cursor Bugbot
   Greptile—none0/10

   The evidence describes per-PR review comments, strictness/noise-control settings, learning from feedback, and CLI/MCP integrations, but no org-level dashboard aggregating findings, acceptance rates, or review coverage metrics across teams/repos is documented anywhere in the pack.

   ⚑ flag

   Cursor Bugbot~partialclaimed4/10

   Docs mention that Bugbot Teams includes 'analytics and reporting' alongside code reviews on all PRs, implying some org-level reporting capability, but there is no detail on dashboard content, acceptance-rate tracking, or review-coverage metrics. missing for 10: dashboard screenshots or specifics on findings/acceptance-rate/coverage metrics, independent corroboration of the analytics feature.

   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”

   proof ↗⚑ flag

Gates

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

   weight 2 · round drawn
   Greptile—none0/10

   Greptile documents review scoring (0-5 safety score, 5/5 confidence) and comment resolution tracking, but no evidence describes a required GitHub/GitLab status check, branch-protection integration, or a blocking review mechanism that would actually prevent a merge until critical findings are resolved.

   ⚑ flag

   Cursor Bugbot—none0/10

   Evidence shows Bugbot posts PR comments/findings and supports manual/automatic triggers, but nothing describes it functioning as a required status check or blocking review that gates merges on resolution of critical findings — missing for 10: any mention of CI status check integration, merge-blocking configuration, or required-review enforcement.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”

   proof ↗⚑ flag

Detection

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

   weight 3 · round to Greptile
   Greptile~partialcommunity6/10

   Docs describe substantive bug-catching capability beyond style — TREX runtime sandbox that surfaces race conditions/logic bugs via traces and screenshots, static+AI security scanning, and v5's parallel agent swarm claiming fewer false positives and more real bugs caught. Community evidence partially corroborates real-world value (comm-8: 'catches real issues... gives author a chance to fix before human reviews') but also shows mixed accuracy experiences on complex code (comm-3: incomplete/incorrect answers on C++ templates) and reliability hiccups reported for the platform generally. Missing for 10: independent, PR-review-specific benchmarks or hands-on accounts confirming it reliably finds logic errors/race conditions (not just Q&A accuracy), and no rebuttal to the noted accuracy gaps.

   • [claimed-docs] “TREX runs your PR branch in a sandbox to find the bugs that only show up at runtime. It starts services, mocks inputs, clicks through UI flo…”
   • [claimed-docs] “Greptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.”
   • [claimed-docs] “v5 is faster, catches more bugs, and flags fewer false positives by running a swarm of narrowly scoped agents in parallel.”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”
   • [community] “Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incom…”

   proof ↗⚑ flag

   Cursor Bugbot!disputedcontradicted6/10

   Docs claim Bugbot finds real bugs, security vulnerabilities, and logic issues beyond style (docs-13, docs-24), and one HN commenter corroborates it 'finds genuine bugs most reviewers miss' (comm-2, comm-4). But other hands-on reports contradict this: one engineer says instances arose where Bugbot's own suggested fix was later contested by the LLM itself, and another says its review comments 'were all subtly wrong' (comm-1, comm-3), so accuracy in practice is inconsistent rather than uniformly reliable. Missing for 10: independent benchmark data on false-positive rate, and broader third-party validation beyond a single HN thread's mixed anecdotes.

   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [community] “I've witnessed numerous instances where either the cursor bugbot or Claude has found a bug and recommended a reasonable fix. The fix has bee…”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”
   • [community] “I assume that this is the same as when Cursor spontaneously decides to show code review comments in the IDE as part of some upsell? In that …”
   • [community] “I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it'…”

   proof ↗⚑ flag

Learning

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

   weight 2 · round to Greptile
   Greptile~partialclaimed7/10

   Docs explicitly describe a learning loop where 👍/👎 reactions and reply comments train Greptile to stop repeating feedback team members don't want, with noise control filtering repetitive comments (greptile-docs-4, greptile-docs-33, greptile-docs-32). However, this is described as a team-wide, multi-week aggregate learning process rather than an immediate per-developer 'push back once and it never repeats' guarantee, and no independent/hands-on evidence confirms the mechanism works as described. Missing for 10: independent corroboration of the learning behavior, and clarity on whether a single developer's pushback (vs. team consensus over weeks) suppresses a specific rejected comment.

   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”

   proof ↗⚑ flag

   Cursor Bugbot~partialcommunity4/10

   Docs show Bugbot reads existing PR comments (top-level and inline) to avoid duplicate suggestions and build on prior feedback, which implies some memory of prior review context within a single PR thread, and BUGBOT.md lets teams codify guidelines to steer future reviews. However, there's no evidence of a persistent learning mechanism where a developer's explicit pushback/rejection on a specific comment is remembered and stops the same feedback from recurring across PRs — community reports actually describe the opposite pattern (bot re-arguing or repeating flagged issues), and one commenter explicitly disliked its persistent review comments. missing for 10: explicit mechanism for marking a comment 'rejected' and suppressing future repeats, cross-PR memory of developer pushback, hands-on confirmation that pushback changes future behavior.

   • [claimed-docs] “Uses existing PR comments as context: reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior f…”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [community] “I've witnessed numerous instances where either the cursor bugbot or Claude has found a bug and recommended a reasonable fix. The fix has bee…”
   • [community] “I assume that this is the same as when Cursor spontaneously decides to show code review comments in the IDE as part of some upsell? In that …”

   proof ↗⚑ flag

Noise

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

   weight 3 · round to Greptile
   Greptile~partialcommunity6/10

   Greptile documents multiple noise-reduction mechanisms: adjustable strictness/nitpickiness (docs-20, docs-32), a learning system trained via 👍/👎 reactions that stops flagging things teams don't care about (docs-4, docs-33), custom rules to catch team-specific issues (docs-21), and a v5 update claiming 'fewer false positives' via parallel narrow-scope agents (docs-26). However, hands-on community evidence is mixed: one enterprise user reports Greptile is 'sometimes overzealous' even while generally catching real issues (greptile-comm-8), indicating the noise-reduction promise isn't fully realized in practice, and there's no independent data on deduplication or severity-labeling accuracy. Missing for 10: independent verification of false-positive rate reduction, evidence of comment deduplication specifically, and confirmation severity labels are reliably applied and trusted by teams.

   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [claimed-docs] “v5 is faster, catches more bugs, and flags fewer false positives by running a swarm of narrowly scoped agents in parallel.”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”

   proof ↗⚑ flag

   Cursor Bugbot~partialcommunity5/10

   Docs show dedup mechanisms (reading existing PR comments to avoid duplicate suggestions), configurable project rules via BUGBOT.md, and verbose mode showing which rules fired — all noise-reduction levers. But there's no evidence of severity labels, and community reports are split: some engineers report Bugbot is 'shockingly effective' with 'almost none of its comments frivolous or wrong', while others report frivolous/wrong comments and one lead disabled auto-review after Bugbot argued against its own fix. Missing for 10: explicit severity-label feature, and consistent independent confirmation of low false-positive rate.

   • [claimed-docs] “Uses existing PR comments as context: reads connected PR comments (top-level and inline) to avoid duplicate suggestions and build on prior f…”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Comment `cursor review verbose=true` or `bugbot run verbose=true` on the PR for detailed logs, which Bugbot rules loaded, and a request ID”
   • [community] “I've witnessed numerous instances where either the cursor bugbot or Claude has found a bug and recommended a reasonable fix. The fix has bee…”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”
   • [community] “I assume that this is the same as when Cursor spontaneously decides to show code review comments in the IDE as part of some upsell? In that …”
   • [community] “I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it'…”

   proof ↗⚑ flag

Security

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

   weight 2 · round to Cursor Bugbot
   Greptile✓fullcommunity6/10

   Greptile has a dedicated security-check feature explicitly pairing static scanning with an AI security agent to catch vulnerabilities on every PR, alongside its general review pipeline that flags functional bugs and code-quality issues in the same diff comments. However, missing for 10: independent/hands-on evidence confirming detection of specific vuln classes like injection or leaked secrets, and no community reports specifically validating security-finding accuracy (community feedback only covers general bug-catching, not security).

   • [claimed-docs] “Greptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.”
   • [claimed-docs] “Greptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.”
   • [claimed-docs] “v5 is faster, catches more bugs, and flags fewer false positives by running a swarm of narrowly scoped agents in parallel.”
   • [community] “My employer uses greptile and I'm pretty happy with it. Sometimes it can be a bit overzealous but more often than not it catches real issues…”

   proof ↗⚑ flag

   Cursor Bugbot✓fullprobed8/10

   Docs explicitly state Bugbot analyzes PRs for 'bugs, security vulnerabilities, and code quality issues' with inline comments and fix suggestions, directly matching the security-plus-functional review scope described; community evidence corroborates it catches genuine bugs (though some skepticism about accuracy exists). missing for 10: no explicit named example of catching leaked secrets or injection specifically, and no independent benchmark isolating security-issue detection accuracy.

   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [probe] “PROBE docs-md: HTTP 200 at https://cursor.com/docs/bugbot.md # Bugbot Bugbot reviews pull requests and identifies bugs, security issues, an…”
   • [community] “Do you have actual experience with bugbot? Its live in our org and is actually pretty good, almost none of its comments are frivolous or wro…”
   • [community] “I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it'…”

   proof ↗⚑ flag

Cli

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

   weight 2 · round to Greptile
   Greptile~partialprobed5/10

   Greptile ships an official CLI (`greptile review`, `greptile onboard`) that reviews local/feature-branch diffs and returns a 0-5 safety score, and docs note coding agents can invoke the CLI to review their own code, implying scriptable/automatable use. However, there is no explicit documentation of a machine-readable output format (e.g., JSON flag) or dedicated CI pipeline integration examples — only an OpenAPI/CLI probe confirming the CLI page exists with no schema found. Missing for 10: documented JSON/structured output mode, explicit CI script examples, and independent confirmation of CLI reliability in automation contexts.

   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”
   • [claimed-docs] “Coding agents can use the greptile cli to review their own code”
   • [claimed-docs] “Set up Greptile from your terminal with `greptile onboard` — or hand this page to your coding agent and have it run the setup for you.”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”
   • [probe] “official CLI documented at https://www.greptile.com/docs/code-review/greptile-cli”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.c…”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   Bugbot is documented exclusively as a PR-comment-triggered reviewer integrated with GitHub/GitLab/Bitbucket/Azure DevOps, posting inline PR comments — there is no mention of a CLI, local-diff scanning, or machine-readable (JSON/SARIF) output for CI script consumption anywhere in the evidence. Missing for 10: any CLI binary/command, local diff support, structured/machine-readable output format, or CI-script-oriented API.

   • [claimed-docs] “Manual trigger by commenting `cursor review` or `bugbot run` on any PR”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”
   • [claimed-docs] “GitHub (including GitHub Enterprise Server): See the GitHub integration page”
   • [claimed-docs] “GitLab (including GitLab Self-Hosted): See the GitLab integration page”

   proof ↗⚑ flag

Ide

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

   weight 2 · round to Greptile
   Greptile~partialprobed6/10

   Greptile's core product reviews pull requests after they are opened, but its CLI (`greptile review`) can review a feature-branch diff locally in ~60 seconds, and its MCP server lets Cursor/Claude Code/VS Code/Codex surface review comments and patterns directly in the editor, which together approximate a pre-push, in-IDE review loop. However, this is CLI/MCP-triggered rather than a live, continuous in-editor reviewer, and there is no independent/hands-on evidence confirming the pre-push workflow works as described. Missing for 10: evidence of automatic/real-time in-editor annotations (not just CLI/MCP triggered), independent user confirmation of the pre-push flow, and clarity that MCP comments are available before a PR/push exists rather than only fetching existing PR feedback.

   • [claimed-docs] “Run `greptile review`, get a review of the feature branch diff in 60 seconds.”
   • [claimed-docs] “Coding agents can use the greptile cli to review their own code”
   • [claimed-docs] “Connect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.”
   • [claimed-docs] “With MCP, you can view, search, and create patterns from your IDE.”
   • [claimed-docs] “View and resolve review comments directly from Claude Code.”
   • [probe] “official MCP server documented at https://www.greptile.com/docs/mcp-v2/overview”
   • [probe] “official CLI documented at https://www.greptile.com/docs/code-review/greptile-cli”

   proof ↗⚑ flag

   Cursor Bugbot—none0/10

   All documentation describes Bugbot as a PR-based reviewer that runs on GitHub/GitLab/Bitbucket/Azure DevOps pull requests (post-push), triggered by PR updates or PR comments, not as an in-editor pre-push check. 'Fix in Cursor' links merely open already-found PR issues in the IDE for fixing, which happens after the code has already been pushed, contradicting the story's requirement of catching issues before pushing.

   • [claimed-docs] “Runs automatic reviews on every PR update”
   • [claimed-docs] “It analyzes every pull request for bugs, security vulnerabilities, and code quality issues, leaving inline comments with explanations and su…”
   • [claimed-docs] “Fix in Cursor links open issues directly in Cursor”
   • [claimed-docs] “Bugbot analyzes PR diffs and leaves comments with explanations and fix suggestions.”

   proof ↗⚑ flag

Config

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

   weight 3 · round to Greptile
   Greptile~partialclaimed6/10

   Greptile documents a versioned `greptile.json` config file placed in the repo root that is read from the PR's source branch and overrides dashboard settings, supporting per-repo, version-controlled configuration; related settings like custom rules and strictness/nitpickiness controls are also documented as configurable dials. However, the evidence pack never explicitly confirms path-based filters, per-path instructions, or named 'review profiles' within that config schema — only that dashboard-level settings (rules, strictness) can be overridden via the file. Missing for 10: explicit greptile.json schema showing path-filter syntax, per-path instruction blocks, and named review-profile support.

   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed5/10

   Bugbot supports a versioned `.cursor/BUGBOT.md` file for project-specific review guidelines, plus org-wide rules via Bugbot Automations and natural-language effort-level instructions, giving some per-repo/per-instruction configurability. However, there's no evidence of path-based filters, distinct 'review profiles', or per-path (as opposed to per-repo) instruction targeting within the config file. missing for 10: explicit path/glob filtering, multiple named review profiles, per-path instruction scoping, independent confirmation of BUGBOT.md schema/capabilities.

   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Describe in natural language when Bugbot should use low, default, or high effort. Cursor will dynamically set effort levels based on your in…”
   • [claimed-docs] “Smart: Describe in natural language when Bugbot should use low, default, or high effort. Cursor will dynamically set effort levels based on …”

   proof ↗⚑ flag

Governance

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

   weight 1 · round to Greptile
   Greptile~partialclaimed7/10

   Docs show org-level dashboard settings that apply by default, with per-repo greptile.json files that override those defaults for exceptions (greptile-docs-22), org admin controls like Settings → Code Review → Default Coding Agents (greptile-docs-34), and CLI onboarding that creates an org, connects GitHub/GitLab, and enables repositories in bulk (greptile-docs-31). This covers the core mechanics of setting org-wide defaults and per-repo exceptions, but there's no direct evidence of managing hundreds of repos at scale, bulk exception dashboards, role-based admin permissions, or audit/reporting tools for centralized governance. Missing for 10: explicit multi-repo/org-scale management UI, RBAC for admins, and evidence of exception tracking across hundreds of repos.

   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “Org admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.”
   • [claimed-docs] “`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — th…”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “Create custom rules that catch team-specific issues”

   proof ↗⚑ flag

   Cursor Bugbot~partialclaimed5/10

   Cursor supports org/team-level rollout via Bugbot Teams (all-PR reviews, analytics, effort controls) and 'organization-wide rules' via Bugbot Automations, plus per-repo BUGBOT.md guideline files, giving a centralized-defaults mechanism. However there's no evidence of exception management at scale (e.g., per-repo overrides, exemption lists, staged rollout across hundreds of repos) or admin tooling for auditing/enforcing defaults across a large repo fleet. Missing for 10: documented per-repo exception/override workflow, evidence of scaling to hundreds of repos, and admin audit/reporting on rule adherence across the org.

   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “You can enable usage-based billing for reviews on all PRs.”

   proof ↗⚑ flag

Rules

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

   weight 2 · round to Greptile
   Greptile✓fullclaimed8/10

   Greptile supports custom rules for team-specific issues, a greptile.json config file that overrides dashboard settings, indexing of existing rule files (Claude.md, AGENTS.md, cursor.rules), strictness/noise-control tuning, and a learning system that adapts from emoji reactions/comments — collectively covering natural-language rules, linked style-guide-like imports, and reinforcement learning of preferences. Missing for 10: explicit documentation of AST-pattern-based rule authoring and independent/community validation that custom rules are reliably enforced in practice.

   • [claimed-docs] “Create custom rules that catch team-specific issues”
   • [claimed-docs] “Place `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.”
   • [claimed-docs] “Automatically index existing rule files like Claude.md, AGENTS.md, and cursor.rules for richer review context.”
   • [claimed-docs] “Control how strict Greptile is about leaving comments with the strictness setting (1–3).”
   • [claimed-docs] “With noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.”
   • [claimed-docs] “Greptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and…”
   • [claimed-docs] “Your 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.”

   proof ↗⚑ flag

   Cursor Bugbot✓fullclaimed7/10

   Bugbot supports project-specific natural-language review guidelines via .cursor/BUGBOT.md files, org-wide rules via Bugbot Automations, and verbose mode to show which rules were applied. missing for 10: no evidence of AST-pattern-based rule definitions, no support for linking external style guide documents, and no independent/hands-on verification of how well custom guidelines are actually enforced in practice.

   • [claimed-docs] “Create `.cursor/BUGBOT.md` files in your repository to give Bugbot project-specific review guidelines.”
   • [claimed-docs] “Comment `bugbot run verbose=true` or `cursor review verbose=true` on the pull request. Bugbot replies with a table of the rules included in …”
   • [claimed-docs] “Team admins can also create organization-wide rules in [Bugbot Automations](https://cursor.com/automations/from-cursor/bugbot).”
   • [claimed-docs] “Comment `cursor review verbose=true` or `bugbot run verbose=true` on the PR for detailed logs, which Bugbot rules loaded, and a request ID”
   • [claimed-docs] “Bugbot Teams includes code reviews on all PRs, analytics and reporting, effort level controls, and advanced rules and settings.”

   proof ↗⚑ flag