AI AGENTS
On-Call Runbook Executor with Slack Approval Gate
When PagerDuty fires a high-severity incident, an agent pulls the matching runbook, drafts concrete remediation steps.
How it runs
The automated pipeline, trigger to output.
- TriggerPagerDuty high-urgency incident firesPagerDuty
- ActionFetch matching runbook from ConfluenceConfluence
- ActionAgent drafts ordered remediation plan
- LogicPost plan to Slack, await Approve/RejectSlack
- ActionOn approval, execute remediation commandsShell
- OutputPost outcome back to incident channelSlack
What it does
Turns a paging alert into a proposed action plan that a human approves before any change lands. The agent reads the incident, finds the right runbook, and writes out the exact commands or API calls it intends to run — but it waits for a Slack approval before touching production.
When to use it
Use this when your team trusts automation to *propose* fixes but not to act unsupervised. Ideal for the 2am page where the responder wants a ready-to-go plan instead of digging through a wiki, while keeping a human in the loop for the actual remediation.
How it works
- 1A PagerDuty incident with high urgency triggers the workflow.
- 2The agent reads the incident title, service, and notes, then fetches the matching runbook from Confluence.
- 3It drafts an ordered remediation plan, each step phrased as a concrete, reversible action.
- 4A logic gate posts the plan to Slack with Approve / Reject buttons and pauses.
- 5On approval, the agent executes the named shell or API actions; on reject it logs the decline.
- 6It posts the outcome and any output back to the incident's Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect PagerDutyIncidents, on-call, escalations.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Connect ShellRun sandboxed commands inside the workspace.
- 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.