DEVOPS
Agent that removes stale flags and verifies no rollback risk
An agent investigates each flag at 100% for 30 days, confirms the off-variation has zero recent traffic, then authors a tested GitHub PR removing the flag only when it is safe.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule starts the agent
- ActionLoad 100%-for-30-days candidates from DatadogDatadog
- LogicCheck if the off-variation still gets any traffic
- ActionRead flag code and author removal PR in GitHubGitHub
- OutputEscalate risky kill-switch flags to SlackSlack
What it does
This agent-driven workflow does the judgment work a human would before deleting a flag. For each flag stuck at 100% for 30+ days it checks whether the disabled variation still receives any traffic, reads the surrounding code, and only authors a removal PR when it can confirm the off path is truly dead. Risky cases get flagged for human review instead of auto-changed.
When to use it
Use it when blanket flag removal scares you — when some 100% flags are kill switches or fallbacks that must not be ripped out. The agent adds a safety verdict to every candidate so you remove the dead ones and quarantine the load-bearing ones.
How it works
A weekly schedule starts the agent. It loads candidate flags at 100% for 30 days from Datadog, then for each one queries Datadog for any evaluations of the off-variation in the last 30 days. If the off path is dead, it reads the flag's code in GitHub, removes the guard, runs the relevant tests, and opens a PR. If the off path still gets traffic or looks like a kill switch, it routes the flag to Slack with its reasoning for a human to decide.
Set it up
What you configure once, before turning it on.
- 1Connect DatadogMetrics, traces, log search.
- 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 DevOps workflows
Slack-approved pause for idle Hugging Face Spaces
On a daily scan it finds idle paid Spaces and posts an interactive Slack approval; on approve it pauses the Space and logs the decision to a GitHub issue audit trail.
Block costly Hugging Face Space hardware upgrades in PR review
When a pull request changes a Space's hardware config, it estimates the new monthly cost and posts a GitHub PR comment that flags upgrades crossing a budget ceiling.
Hugging Face Spaces idle-runtime sweep with auto-pause
On a schedule, scans all Hugging Face Spaces for ones running idle past a threshold, pauses them to stop billing, and posts a Slack summary with the estimated monthly savings.
Open a Zoom war-room from a Datadog multi-alert storm
When a Datadog monitor crosses a critical threshold, this workflow dedupes against active incidents, and only for a genuinely new outage it creates a Zoom bridge.
Auto-spin a Zoom war-room when PagerDuty hits SEV-1
When a PagerDuty incident escalates to a critical severity, this workflow creates a dedicated Zoom meeting and posts the bridge link to the incident's Slack channel so responders…
Spin up a war-room on demand from a Slack slash command
When an engineer runs a Slack command, this workflow creates a Zoom bridge, opens a tracking Sentry-linked incident, files a Linear issue for follow-up.
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.