AI AGENTS
A/B Kill Verdict Opens Feature-Flag Rollback PR
On a scheduled check, an agent reads experiment results from BigQuery; when the verdict is kill, it opens a GitHub pull request that removes the losing variant's feature flag…
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled concluded-experiment check
- ActionPull results from BigQueryBigQuery
- LogicBranch: continue only on kill verdict
- ActionOpen feature-flag rollback PR in GitHubGitHub
- OutputNotify on-call engineer in SlackSlack
What it does
Makes killing a losing variant a single approval instead of a manual cleanup. When the agent's verdict is kill, it opens a GitHub PR that turns off or removes the experiment's feature flag and pings the responsible engineer so the change ships fast and cleanly.
When to use it
Use this when losing variants linger in production because nobody circles back to remove the flag. It converts a kill decision directly into a reviewable code change.
How it works
- 1A scheduled trigger checks for newly concluded experiments.
- 2A BigQuery action pulls the results for each one.
- 3A logic branch proceeds only when the verdict is kill (significant negative or flat result).
- 4A GitHub action opens a PR that disables or deletes the variant's feature flag, with the data in the description.
- 5A Slack message notifies the on-call engineer that the rollback PR is ready for review.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect SlackChannels, DMs, threads, mentions.
- 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 AI Agents workflows
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Datadog Bill Spike Attribution Agent
When a daily Datadog cost check detects a spend jump, an agent attributes the increase to the specific services and metric types driving it and posts a ranked breakdown to Slack.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
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.