AI AGENTS
PagerDuty Incident Runbook: Propose Fix, Wait for Approval
When a high-urgency PagerDuty incident fires, an agent reads the matching runbook, drafts the exact remediation steps.
How it runs
The automated pipeline, trigger to output.
- TriggerPagerDuty incident createdPagerDuty
- LogicKeep only high-urgency incidents
- ActionFetch matching runbook from ConfluenceConfluence
- ActionAgent drafts remediation steps + rollback
- OutputPost plan to Slack with Approve/RejectSlack
- ActionOn approval, execute via shellShell
What it does
Turns a paged incident into a concrete, reviewable remediation plan. The agent matches the alert to your runbook library, writes out the precise commands and their expected effect, and pauses for a human to approve or reject in Slack. Nothing is executed without an explicit yes.
When to use it
Use this when your on-call rotation handles recurring incident types (disk full, stuck queue, hung worker) that have documented fixes, but you are not yet comfortable letting automation act unsupervised. It compresses the diagnosis-and-draft phase while keeping a human in the loop for the action.
How it works
- 1A PagerDuty incident triggers the flow with its title, service, and urgency.
- 2A logic step filters to high-urgency incidents only; low-urgency ones are dropped.
- 3The agent fetches the candidate runbook from Confluence and matches it to the alert signature.
- 4It drafts step-by-step remediation with the exact shell commands and rollback notes.
- 5The plan is posted to the incident's Slack channel with Approve / Reject controls.
- 6On approval, the shell action executes the steps and the final result is posted back to Slack.
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
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.