Skip to content

How Greptile’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score27/100

Agent-ready 39.4 × 0.30 = 11.82

API quality 8.6 × 0.20 = 1.72

Openness 27.0 × 0.20 = 5.40

Built-in AI 31.2 × 0.15 = 4.68

Automation 23.3 × 0.15 = 3.50

(11.82 + 1.72 + 5.40 + 4.68 + 3.50) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 27.11 ÷ 1.00 = 27.1

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready39.4/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [probe] https://www.greptile.com/llms.txtPROBE llms.txt: HTTP 200 at https://www.greptile.com/llms.txt # Greptile > Greptile is an independent AI code validation platform for GitHub, GitLab, local development, and coding-a
  • [probe] https://www.greptile.com/docs/introduction.mdPROBE docs-md: HTTP 200 at https://www.greptile.com/docs/introduction.md > ## Documentation Index > Fetch the complete documentation index at: https://www.greptile.com/docs/llms.txt > Use this
  • [claimed-docs] https://www.greptile.com/docs/code-review/cli-onboardingSet up Greptile from your terminal with `greptile onboard` — or hand this page to your coding agent and have it run the setup for you.

Run the product headlessly / in CI for automationweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://www.greptile.com/cliRun `greptile review`, get a review of the feature branch diff in 60 seconds.
  • [claimed-docs] https://www.greptile.com/cliCoding agents can use the greptile cli to review their own code
  • [claimed-docs] https://www.greptile.com/docs/quickstartSet up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first pull request.
  • [claimed-docs] https://www.greptile.com/docs/code-review/cli-onboarding`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — the same setup the dashboard does.
  • [probe] https://www.greptile.com/docs/code-review/greptile-cliofficial CLI documented at https://www.greptile.com/docs/code-review/greptile-cli

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/overviewFetch PR comments - Get unaddressed Greptile feedback for any PR
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/setupConnect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.
  • [probe] https://www.greptile.com/docs/mcp-v2/overviewofficial MCP server documented at https://www.greptile.com/docs/mcp-v2/overview

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/overviewFetch PR comments - Get unaddressed Greptile feedback for any PR
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/setupConnect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/auto-fix.mdList unaddressed Greptile comments for PR #5 in owner/repo
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/custom-context.mdWith MCP, you can view, search, and create patterns from your IDE.
  • [probe] https://www.greptile.com/docs/mcp-v2/overviewofficial MCP server documented at https://www.greptile.com/docs/mcp-v2/overview

Use an official CLIweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://www.greptile.com/docs/code-review/cli-onboardingSet 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] https://www.greptile.com/cliRun `greptile review`, get a review of the feature branch diff in 60 seconds.
  • [claimed-docs] https://www.greptile.com/cliCoding agents can use the greptile cli to review their own code
  • [claimed-docs] https://www.greptile.com/docs/code-review/cli-onboarding`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — the same setup the dashboard does.
  • [probe] https://www.greptile.com/docs/code-review/greptile-cliofficial CLI documented at https://www.greptile.com/docs/code-review/greptile-cli

Drive the product through a documented public APIweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/overviewFetch PR comments - Get unaddressed Greptile feedback for any PR
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/setupConnect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/auto-fix.mdList unaddressed Greptile comments for PR #5 in owner/repo
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/custom-context.mdWith MCP, you can view, search, and create patterns from your IDE.
  • [probe] https://www.greptile.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.com/api/openapi.json, https://www.greptile.com/.well-known/openapi.json)
  • [probe] https://www.greptile.com/docs/mcp-v2/overviewofficial MCP server documented at https://www.greptile.com/docs/mcp-v2/overview
  • [probe] https://www.greptile.com/docs/code-review/greptile-cliofficial CLI documented at https://www.greptile.com/docs/code-review/greptile-cli
  • [claimed-docs] https://www.greptile.com/cliRun `greptile review`, get a review of the feature branch diff in 60 seconds.
  • [claimed-docs] https://www.greptile.com/cliCoding agents can use the greptile cli to review their own code

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://www.greptile.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.com/api/openapi.json, https://www.greptile.com/.well-known/openapi.json)
  • [probe] https://www.greptile.com/docs/mcp-v2/overviewofficial MCP server documented at https://www.greptile.com/docs/mcp-v2/overview
  • [probe] https://www.greptile.com/docs/code-review/greptile-cliofficial CLI documented at https://www.greptile.com/docs/code-review/greptile-cli
  • [claimed-docs] https://www.greptile.com/cliRun `greptile review`, get a review of the feature branch diff in 60 seconds.
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/setupConnect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 82.8 ÷ 210 × 100 = 39.4

API quality8.6/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://www.greptile.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.com/api/openapi.json, https://www.greptile.com/.well-known/openapi.json)

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://www.greptile.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.com/api/openapi.json, https://www.greptile.com/.well-known/openapi.json)

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 6 (quality) × 1.0 (full) = 6.0 of 10 max

  • [claimed-docs] https://www.greptile.com/trexTREX 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 flows, and leaves the logs, screenshots, and traces on the PR.

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://www.greptile.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.com/api/openapi.json, https://www.greptile.com/.well-known/openapi.json)

API quality = 6.0 ÷ 70 × 100 = 8.6

Openness27.0/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://www.greptile.com/cliRun `greptile review`, get a review of the feature branch diff in 60 seconds.
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/overviewFetch PR comments - Get unaddressed Greptile feedback for any PR
  • [claimed-docs] https://www.greptile.com/docs/mcp-v2/setupConnect Cursor, Claude Code, VS Code, or Codex to Greptile MCP with OAuth.
  • [claimed-docs] https://www.greptile.com/docs/code-review/cli-onboarding`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — the same setup the dashboard does.
  • [claimed-docs] https://www.greptile.com/docs/integrations/fix-with-your-agent.mdOrg admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.
  • [probe] https://www.greptile.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://www.greptile.com/openapi.json, https://www.greptile.com/swagger.json, https://www.greptile.com/api/openapi.json, https://www.greptile.com/.well-known/openapi.json)
  • [probe] https://www.greptile.com/docs/mcp-v2/overviewofficial MCP server documented at https://www.greptile.com/docs/mcp-v2/overview
  • [probe] https://www.greptile.com/docs/code-review/greptile-cliofficial CLI documented at https://www.greptile.com/docs/code-review/greptile-cli

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://www.greptile.com/securitySecurity page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as on-premises - so that you and your users can build, run, and, use Greptile in your virtual private cloud (VPC)"; customers "can choose to also self-host LLMs" or bring their own; "Customers can choose to turn off logging and make chats 100% private. Note that in the self-hosted service, logs are stored on customer servers only."

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://www.greptile.com/docs/security/selfhostDeploy Greptile in your own infrastructure with Docker Compose. Supports AWS, GCP, Azure, air-gapped environments, and custom LLM configurations.
  • [claimed-docs] https://www.greptile.com/docs/deployment-optionsDocker Compose: Up to 100 developers. Single VM, simpler operations. Kubernetes: 100+ developers. Horizontal scaling, high availability.
  • [claimed-docs] https://www.greptile.com/securitySecurity page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as on-premises - so that you and your users can build, run, and, use Greptile in your virtual private cloud (VPC)"; customers "can choose to also self-host LLMs" or bring their own; "Customers can choose to turn off logging and make chats 100% private. Note that in the self-hosted service, logs are stored on customer servers only."

Self-host the core productweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

  • [claimed-docs] https://www.greptile.com/docs/security/selfhostDeploy Greptile in your own infrastructure with Docker Compose. Supports AWS, GCP, Azure, air-gapped environments, and custom LLM configurations.
  • [claimed-docs] https://www.greptile.com/docs/deployment-optionsDocker Compose: Up to 100 developers. Single VM, simpler operations. Kubernetes: 100+ developers. Horizontal scaling, high availability.
  • [claimed-docs] https://www.greptile.com/docs/security/network-rulesIf your GitHub or GitLab instance restricts inbound traffic to specific IP addresses, you need to allowlist Greptile's IP range for code review to work.
  • [claimed-docs] https://www.greptile.com/securitySecurity page, self-hosting and logging: "For self-hosted Greptile services, Custom Apps are hosted using your own infrastructure - such as on-premises - so that you and your users can build, run, and, use Greptile in your virtual private cloud (VPC)"; customers "can choose to also self-host LLMs" or bring their own; "Customers can choose to turn off logging and make chats 100% private. Note that in the self-hosted service, logs are stored on customer servers only."

Openness = 27.0 ÷ 100 × 100 = 27.0

Built-in AI31.2/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 6 (quality) × 0.3 (disputed) = 3.6 of 20 max

  • [claimed-docs] https://www.greptile.com/docs/introductionGreptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.
  • [claimed-docs] https://www.greptile.com/cliKnow how safe a PR is to merge at a glance with a 0-5 score
  • [claimed-docs] https://www.greptile.com/cliParse complex changes with sequence diagrams and flowcharts generated for every PR
  • [claimed-docs] https://www.greptile.com/cliAutomatically generate unit tests for new and changed code in every PR
  • [claimed-docs] https://www.greptile.com/security-checkGreptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.
  • [claimed-docs] https://www.greptile.com/docs/code-review/training-the-learning-systemGreptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and explanatory comments.
  • [community] https://news.ycombinator.com/item?id=39604961Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code review. 'This would have saved me about 30mins of work.'
  • [community] https://news.ycombinator.com/item?id=44786514My 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 and gives the author a chance to reply or fix them before another human reviews the PR.
  • [community] https://news.ycombinator.com/item?id=39604961Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incomplete and usually partly or mostly incorrect, even when comments in source code answer the question.
  • [community] https://news.ycombinator.com/item?id=39604961Not 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] https://news.ycombinator.com/item?id=39604961Ran it on my OSS project - stuck at 99% loading for ~30 minutes, then got 'Error: Internal error while locating sources' on every query. 'This is like a pre-MVP quality product... Charging for something like this is honestly highway robbery.'
  • [community] https://news.ycombinator.com/item?id=39604961Loading a repo with many branches (cassandra), searching for 'vsearch' surfaced branch-named results (CNDB-8708-vsearch, DSP-23946-vsearch) but not the actual vsearch term itself - apparent bug with many-branch repos.
  • [community] https://news.ycombinator.com/item?id=39604961Getting 'Error: Internal error while processing request' while trying on my personal public github repo.

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://www.greptile.com/docs/introductionGreptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.
  • [claimed-docs] https://www.greptile.com/docs/quickstartSet up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first pull request.
  • [claimed-docs] https://www.greptile.com/trexTREX 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 flows, and leaves the logs, screenshots, and traces on the PR.
  • [claimed-docs] https://www.greptile.com/security-checkGreptile pairs static scanning with an AI security agent to catch vulnerabilities in every pull request.
  • [claimed-docs] https://www.greptile.com/changelogv5 is faster, catches more bugs, and flags fewer false positives by running a swarm of narrowly scoped agents in parallel.
  • [claimed-docs] https://www.greptile.com/changelogGreptile 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 it, and if GPT wrote it, Claude reviews it.
  • [claimed-docs] https://www.greptile.com/docs/code-review/controlling-nitpickinessControl how strict Greptile is about leaving comments with the strictness setting (1–3).
  • [claimed-docs] https://www.greptile.com/docs/code-review/greptile-json-referencePlace `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 5 (quality) × 0.3 (disputed) = 4.5 of 30 max

  • [claimed-docs] https://www.greptile.com/docs/introductionGreptile is an AI code review agent that automatically reviews every pull request with complete understanding of your codebase.
  • [claimed-docs] https://www.greptile.com/cliAutomatically generate unit tests for new and changed code in every PR
  • [claimed-docs] https://www.greptile.com/trexTREX 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 flows, and leaves the logs, screenshots, and traces on the PR.
  • [claimed-docs] https://www.greptile.com/docs/code-review/training-the-learning-systemGreptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and explanatory comments.
  • [community] https://news.ycombinator.com/item?id=39604961Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code review. 'This would have saved me about 30mins of work.'
  • [community] https://news.ycombinator.com/item?id=39604961Tried it on my own C++ codebase - impressed it found the C++ standard used, but it's really bad at analyzing templates; answers always incomplete and usually partly or mostly incorrect, even when comments in source code answer the question.
  • [community] https://news.ycombinator.com/item?id=39604961Not 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] https://news.ycombinator.com/item?id=39604961Ran it on my OSS project - stuck at 99% loading for ~30 minutes, then got 'Error: Internal error while locating sources' on every query. 'This is like a pre-MVP quality product... Charging for something like this is honestly highway robbery.'
  • [community] https://news.ycombinator.com/item?id=39604961Getting 'Error: Internal error while processing request' while trying on my personal public github repo.
  • [community] https://news.ycombinator.com/item?id=44786514My 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 and gives the author a chance to reply or fix them before another human reviews the PR.

Operate the product with natural-language commandsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [community] https://news.ycombinator.com/item?id=39604961Asked Greptile about how BigDecimal is encoded in as_json in Rails; got an accurate answer matching what user learned from PRs/issues/code review. 'This would have saved me about 30mins of work.'
  • [claimed-docs] https://www.greptile.com/docs/code-review/custom-standardsCreate custom rules that catch team-specific issues
  • [claimed-docs] https://www.greptile.com/docs/introductionYour 👍/👎 reactions and replies teach Greptile what matters. After 2-3 weeks, it stops commenting on things you don't care about.
  • [claimed-docs] https://www.greptile.com/cliRun `greptile review`, get a review of the feature branch diff in 60 seconds.

Built-in AI = 28.1 ÷ 90 × 100 = 31.2

Automation23.3/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://www.greptile.com/docs/introductionA Fix All button in the review summary sends every issue at once.
  • [claimed-docs] https://www.greptile.com/independenceIteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.
  • [claimed-docs] https://www.greptile.com/independence.mdGreplooping Iteratively fix a PR until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments.
  • [claimed-docs] https://www.greptile.com/docs/code-review/cli-onboarding`greptile onboard` creates your organization, connects GitHub or GitLab, enables repositories, and imports your existing AI rules files — the same setup the dashboard does.
  • [claimed-docs] https://www.greptile.com/docs/integrations/fix-with-your-agent.mdOrg admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://www.greptile.com/docs/quickstartSet up Greptile AI code reviews in 5 minutes. Connect GitHub or GitLab, configure review triggers, and get automated feedback on your first pull request.
  • [claimed-docs] https://www.greptile.com/docs/code-review/custom-standardsCreate custom rules that catch team-specific issues
  • [claimed-docs] https://www.greptile.com/docs/code-review/greptile-json-referencePlace `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.
  • [claimed-docs] https://www.greptile.com/docs/code-review/controlling-nitpickinessControl how strict Greptile is about leaving comments with the strictness setting (1–3).
  • [claimed-docs] https://www.greptile.com/docs/code-review/controlling-nitpickinessWith noise control, Greptile limits reviews to high-signal insights, skipping low impact or repetitive feedback.
  • [claimed-docs] https://www.greptile.com/docs/integrations/fix-with-your-agent.mdEvery Greptile review comment includes a **Fix with your Agent** button. Click it, and the issue gets sent straight to your coding agent with full context
  • [claimed-docs] https://www.greptile.com/docs/integrations/fix-with-your-agent.mdOrg admins can go to **Settings → Code Review → Default Coding Agents** to turn on Fix with your Agent for the org.

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max

  • [claimed-docs] https://www.greptile.com/docs/code-review/greptile-json-referencePlace `greptile.json` in your repository root. Settings are read from the source branch of the PR and override dashboard settings.
  • [claimed-docs] https://www.greptile.com/docs/code-review/controlling-nitpickinessControl how strict Greptile is about leaving comments with the strictness setting (1–3).
  • [claimed-docs] https://www.greptile.com/docs/code-review/custom-standardsCreate custom rules that catch team-specific issues
  • [claimed-docs] https://www.greptile.com/docs/code-review/training-the-learning-systemGreptile learns from your team's feedback to provide increasingly relevant suggestions. The primary training methods are emoji reactions and explanatory comments.

Automation = 18.6 ÷ 80 × 100 = 23.3