ENGINEERING
AI PR summary and risk-based reviewer routing
On each new PR it generates a plain-English change summary and a risk score from the diff, then routes high-risk PRs to senior reviewers and posts the summary as a PR comment.
How it runs
The automated pipeline, trigger to output.
- TriggerPR openedGitHub
- ActionFetch diff, title, and descriptionGitHub
- ActionGenerate summary and risk rating with OpenAIOpenAI
- LogicRoute by risk: senior pool vs default rotation
- ActionAssign reviewers on GitHubGitHub
- OutputPost AI summary as PR commentGitHub
What it does
When a pull request opens, the workflow feeds the diff and description to an LLM that writes a concise summary of what changed and assigns a risk level based on signals like migrations, auth code, or large blast radius. High-risk PRs are routed to a senior reviewer pool; routine ones go to the normal rotation. The generated summary is posted as a comment so reviewers know what they're looking at before reading a line.
When to use it
Use it when reviewers waste time reverse-engineering large or cryptic diffs, or when risky changes (schema, auth, payments) need senior eyes but currently rely on the author remembering to flag them.
How it works
- 1A GitHub webhook fires on PR open.
- 2The flow retrieves the diff, title, and description.
- 3An OpenAI call produces a structured summary plus a low/medium/high risk rating with reasons.
- 4A branch checks the risk rating: high routes to the senior reviewer pool, otherwise the default rotation.
- 5The flow assigns reviewers on GitHub and posts the AI summary as a PR comment.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Upstream Release to Notion Upgrade Brief
When a watched package publishes a new release, fetches the release notes, maps them to the internal modules that depend on it.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.