Context Layer
Maintain and build on top of AI-generated code. Git AI stores intent, helping engineers understand the code and making your agents smarter.
The /ask Skill
See something you don't understand? The /ask skill lets you talk to the agent that wrote the code about its instructions, decisions, and the intent of the engineer who assigned the task.
Git AI adds the /ask skill to ~/.agents/skills/ and ~/.claude/skills/ at install time, available in Cursor, Claude Code, Copilot, Codex, and others by typing /ask:
/ask Why didn't we use the SDK here?Reading Code + Transcript (/ask) | Only Reading Code (not using Git AI) |
|---|---|
When Aidan was building telemetry, he instructed the agent not to block the exit of our CLI flushing telemetry. Instead of using the Sentry SDK directly, we came up with a pattern that writes events locally first via append_envelope(), then flushes them in the background via a detached subprocess. This keeps the hot path fast and ships telemetry async after the fact. | src/commands/flush_logs.rs is a 5-line wrapper that delegates to src/observability/flush.rs (~700 lines). The commands/ layer handles CLI dispatch; observability/ handles Sentry, PostHog, metrics upload, and log processing. Parallel modules like flush_cas, flush_logs, flush_metrics_db follow the same thin-dispatch pattern. |
Make Your Agents Smarter
Agents make fewer mistakes and produce more maintainable code when they understand the requirements and decisions behind the code they build on. The best way to provide this context is to give agents the same /ask tool you use yourself.
Add to your AGENTS.md (or CLAUDE.md, .cursorrules, etc.):
- In plan mode, always use the /ask skill to read the code and the original transcript that generated it. Understanding intent will help you write a better plan.Transcript Storage
Transcripts stay out of Git — Git Notes link to transcripts stored locally, in the Git AI Cloud, or in a self-hosted store — keeping your repos lean, free of sensitive information, and giving you control over your data.
By default Git AI stores transcript data locally in a SQLite database. You can see your own transcripts, but no one else can. When you use AI Blame to inspect some AI-code you generated, the transcript is fetched from this local database.
Locally stored transcripts (the default) are never shared with your other devices, included in git notes, or uploaded to any server.
Sharing with your team
Prompts are the new code — sharing the intent and rationale behind decisions in the codebase is essential for any team managing large AI-generated codebases.
- Cloud Transcript Store - great for startups + small teams. Get early access
- Self-Hosted Enterprise Transcript Store - great for large organizations with tight security requirements. Get early access