ENGINEERING
Agent that fixes drifted README examples and opens a PR
On a schedule, detects README code examples that no longer run, uses an agent to rewrite each broken snippet against the current API, verifies the fix runs clean.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule fires
- ActionInstall latest version, run examples to find failuresShell
- ActionAgent rewrites failing snippets against current APIOpenAI
- ActionRe-run rewritten snippets to verify they passShell
- LogicKeep only verified fixes, discard unrepairable ones
- OutputOpen GitHub PR with corrected READMEGitHub
What it does
This workflow does not just flag drift, it repairs it. A scheduled run finds README code examples that fail against the current API, then an agent reads the failing snippet, the error output, and the current API signatures to rewrite the example. It re-runs the rewritten snippet to confirm it passes, then opens a GitHub pull request containing only verified fixes for a human to review.
When to use it
Use it when documentation drift is frequent enough that manual fixing is a chore and you trust an agent to draft corrections behind a review gate. Best for well-typed SDKs where the API surface is discoverable.
How it works
- 1A schedule triggers the run.
- 2A shell step installs the latest version and runs the README examples to find failures.
- 3An agent step rewrites each failing snippet using the error output and current API signatures.
- 4A shell step re-runs every rewritten snippet to verify it now passes.
- 5A logic step keeps only verified fixes and discards any the agent could not repair.
- 6A GitHub step opens a pull request with the corrected README and a summary of each change.
Set it up
What you configure once, before turning it on.
- 1Connect ShellRun sandboxed commands inside the workspace.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
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…
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.
Scan for deprecated endpoints and email consumers a weekly sunset countdown
On a weekly schedule, scans the OpenAPI spec for endpoints marked deprecated with a sunset date, and emails each consuming team a countdown of how many days remain before removal.
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.
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.
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.