Configuration Options Overview
You can fine-tune review behavior with these configuration options in the greptile.json file:| Parameter | Type | Description |
|---|---|---|
strictness | number | Filters comments by importance (1-3 scale) |
commentTypes | array | Categories of feedback to generate |
ignorePatterns | string | Files/folders to skip (newline-separated patterns) |
triggerOnUpdates | boolean | Review on every commit, not just PR open |
skipReview | string | Set to "AUTOMATIC" for manual-only reviews |
Severity Threshold Settings
Control how strict Greptile is about leaving comments with the strictness setting (1–3).1
1. Low (Verbose)
Comments on everything (low threshold).Perfect for initial setup or deep reviews where you want every potential issue flagged.
2
2. Default (Recommended)
Provides moderate filtering (default).Balanced approach highlighting real issues while filtering common noise. We recommend starting here.
3
3. High (Critical)
Shows only the most critical issues (high threshold).Ideal for final reviews or teams that want minimal interruption.
How to Configure
- Dashboard (Quick Testing)
- greptile.json (Production)
Path: 
AI Code Review Agent → SettingsComment Type Filtering
Filter which categories of feedback Greptile provides. All types are enabled by default. Available comment types:logic- Business logic issues, algorithmic problems, potential bugssyntax- Language-specific best practices, proper usage patternsstyle- Code formatting, naming conventions, structural consistencyinfo- Informational comments about code context and patterns
How to Configure
- Dashboard
- greptile.json
Navigate to 
AI Code Review Agent → Settings → Comment TypesIgnore Patterns
Exclude files that don’t need review to speed up analysis and reduce noise.*.generated.*- Generated code**/*.test.js- Test files**/node_modules/**- Dependencies*.config.js- Config filespackage-lock.json- Lock files*.md- Documentation
Trigger Configuration
Control when Greptile performs reviews. This affects developer workflow and review frequency.- Dashboard
- greptile.json
Navigate to 
AI Code Review Agent → Settings → Review TriggersTroubleshooting
Settings not taking effect
Settings not taking effect
Check these in order:
- If using
greptile.json, did you commit and push it? - Are you looking at a new PR? Settings don’t affect existing reviews
- Wait 2-3 minutes - config changes aren’t always instant
- Check if the repo has a
greptile.json(it overrides dashboard) - Verify you saved the settings (look for confirmation message)
Still too many comments with strictness: 3
Still too many comments with strictness: 3
Progressive solutions:
- Reduce comment types to
["logic"]only - Add more ignore patterns for generated/test files
- Consider
skipReview: "AUTOMATIC"for non-critical repos - Give the learning system 2-3 weeks to adapt to your reactions
Missing important issues
Missing important issues
Check these settings:
- Is strictness too high? Try reducing by 1
- Are all comment types enabled that you need?
- Check ignore patterns - are they too broad?
- Has the team been giving 👍 to important catches?
Different teams want different settings
Different teams want different settings
Best practice:
- Set conservative org defaults in dashboard (strictness: 2, all types)
- Let teams create repository-specific
greptile.jsonfiles - Share successful configurations as templates
- Review settings quarterly as teams evolve
greptile.json - embrace it as customization.Excluded authors still getting reviewed
Excluded authors still getting reviewed
Reviews triggering on disabled/release branches
Reviews triggering on disabled/release branches
Solutions:
- Add release branches to excluded branches in dashboard
- Use
greptile.jsonwith branch-specific rules - Set
skipReview: "AUTOMATIC"for release repos
What’s next?
- Train the learning system → to automatically reduce noise over time
- Add custom standards → for team-specific rules
- Set up pattern repositories → for cross-repo context