AI AGENTS
Scheduled Runbook Drill Rehearsal
On a weekly schedule, an agent walks a chosen Notion runbook against staging in fully simulated mode, flags any step whose documented commands no longer match reality.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly drill schedule fires
- ActionLoad runbook from NotionNotion
- ActionSimulate each step against stagingShell
- LogicFlag steps that diverge from docs
- ActionFile GitHub issue per stale stepGitHub
- OutputPost drill summary to SlackSlack
What it does
Keeps runbooks from rotting. On a schedule the agent rehearses a documented playbook against staging without making real changes, detects steps where the written command or expected output no longer holds, and opens a tracked issue for each drift it finds.
When to use it
Use it when your runbooks are written once and trusted forever — until the night they fail because a command changed six months ago. This validates them continuously so the playbook is correct before you need it under pressure.
How it works
- 1A weekly schedule triggers the drill for the next runbook in rotation.
- 2The agent loads the runbook from Notion.
- 3It executes each step against staging in simulate-only mode via shell, capturing actual vs expected output.
- 4Logic flags any step where the command errors or the output diverges from what the runbook documents.
- 5For each flagged step it files a GitHub issue describing the drift and the suggested fix.
- 6It posts a drill summary to Slack with pass, fail, and drift counts.
Set it up
What you configure once, before turning it on.
- 1Connect NotionPages, databases, comments.
- 2Connect ShellRun sandboxed commands inside the workspace.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
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.
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.
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.
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.
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.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
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.