ENGINEERING
Smart CI Rerun with Escalation to PagerDuty
On a CI failure, automatically reruns only the failed jobs once; if they pass it labels the failure flaky, but if they fail again on an unchanged commit it pages the on-call…
How it runs
The automated pipeline, trigger to output.
- TriggerGitHub check failure on protected branchGitHub
- ActionRerun only failed jobsGitHub
- LogicCompare rerun result: flake vs regression
- ActionLabel run as flaky on passGitHub
- OutputPage on-call via PagerDuty on repeat failurePagerDuty
What it does
This workflow distinguishes flakes from real breakage automatically. It reruns failed jobs a single time. A pass on rerun is logged as a flake and the build is unblocked; a second consecutive failure on the same commit is treated as a genuine regression and escalated to on-call so a person looks immediately, with no wasted manual reruns.
When to use it
Use this on protected branches where a red build is either a flake or a true regression and you need fast, automatic disambiguation without an engineer babysitting the pipeline.
How it works
- 1A GitHub check_run failure on a protected branch triggers the flow.
- 2An action reruns only the failed jobs via the GitHub API.
- 3A logic step waits for the rerun result and compares against the prior attempt.
- 4If it passed, an action labels the run flaky and records it.
- 5If it failed again, the output creates a PagerDuty incident for the on-call engineer.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect PagerDutyIncidents, on-call, escalations.
- 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.