ENGINEERING
Agentic Auto-Deflake Pull Request for Quarantined Tests
For a quarantined test, an agent reads the test and its recent failure logs, drafts a stabilization fix, and opens a draft GitHub pull request linked to the deflake issue.
How it runs
The automated pipeline, trigger to output.
- TriggerLinear issue moved to 'Deflake Ready'Linear
- ActionFetch test source and recent failure logsGitHub
- ActionDiagnose flake cause and draft fix (agent)
- LogicValidate diff scope is test-only
- ActionOpen draft pull request with diagnosisGitHub
- OutputUpdate Linear issue with PR linkLinear
What it does
It takes a quarantined flaky test and attempts a first-pass fix automatically. An agent pulls the test source plus its recent failing run logs from the ledger, diagnoses common flake causes (timing, shared state, ordering, network), drafts a candidate change, and opens a draft pull request that references the tracking deflake issue for an engineer to review.
When to use it
Use it to get a head start on the deflake backlog — the agent does the tedious diagnosis and first edit so engineers review a proposal instead of starting cold. Best for suites with high flake volume and recurring patterns.
How it works
- 1A Linear issue moved to 'Deflake Ready' triggers the flow.
- 2The flow fetches the test file from GitHub and recent failure logs from the BigQuery ledger.
- 3An agent diagnoses the likely flake cause and drafts a targeted code change.
- 4Logic validates the diff touches only the test or its fixtures before proceeding.
- 5A draft GitHub pull request is opened with the change and a diagnosis summary.
- 6The Linear issue is updated with the PR link and moved to 'In Review'.
Set it up
What you configure once, before turning it on.
- 1Connect LinearIssues, projects, cycles, triage.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect BigQueryDatasets, queries, schemas.
- 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
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.