Learnings
Pullfrog carries context forward between runs, so each run starts with what earlier runs learned about the repository and the PR.
| Kind | Scope | Where to edit it |
|---|---|---|
| Repo-level learnings | Every run in a repository | Repository console, Agent → Learnings |
| PR-level learnings | Runs on one pull request | Not editable; agent context only |
| Cross-repo learnings | Cross-repo runs in an organization | Organization console, Advanced → Cross-repo learnings |
Repo-level learnings
Repo-level learnings are durable notes about how a repository works, kept for facts that many future tasks can reuse:
- Setup and verification commands, such as the package manager, the lint command, or a targeted test command.
- Project conventions, such as where shared utilities live or how components are styled.
- Repository gotchas, such as a flaky integration test, a generated file that must not be edited, or a deployment detail that changes how code is validated.
- Stable architecture facts, such as which package owns shared runtime logic or where auth decisions are enforced.
Pullfrog skips one-off discoveries and guesses, and prunes notes that go stale:
- A run is told to record only what it verified in the code or by running a command. A claim from a review comment, a PR description or an issue is not recorded on its word.
- A run that finds a note wrong or out of date corrects or deletes it.
- Once the notes pass 50,000 characters, runs shorten them before adding more.
You can correct any note in the console, or clear them all.
PR-level learnings
PR-level learnings are a rolling summary of one pull request that review and re-review runs read and update:
- What the PR changes, and which subsystems, files, or behaviors it affects.
- Risks, open questions, and contracts the next review must preserve.
- What has been reviewed already, and what changed since the last review.
- Earlier feedback that has been addressed or no longer applies.
The review on GitHub carries its own summary for people to read.

