{ "schema": "aiblocks-page/1", "id": "agency-engineering-incident-response-commander", "type": "agent", "name": "Incident response coordinator", "summary": "Get a clear severity call, roles, update messages and a blameless post-mortem for a tech outage. Bring the timeline, alerts and who is on call.", "headline": "Incident response coordinator", "subhead": "Describe what broke, who is affected and what you know so far. It helps you set severity, give people roles, write status updates and plan the next 15 minutes. Afterward it drafts a post-mortem and a runbook. It cannot see your systems. A person runs the fix.", "job": { "id": "ship-and-host", "name": "Ship and host your app" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-26", "inputs": [ { "type": "question", "required": true, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" }, { "type": "source_text", "required": false, "label": "Source text", "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link" }, { "type": "incident_record", "required": false, "label": "Incident record", "what": "the record of an outage or incident: the timeline, what was affected, the alerts and who did what" } ], "outputs": [ { "type": "plan", "required": true, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" }, { "type": "document", "required": true, "label": "Document", "what": "a finished document, such as a Word file, a PDF or a page of notes" }, { "type": "incident_record", "required": true, "label": "Incident record", "what": "the record of an outage or incident: the timeline, what was affected, the alerts and who did what" } ], "you_give": [ "What is broken, since when and who is affected.", "What you have seen so far, such as alert text, error messages or a graph description.", "Recent changes, such as a deploy or a settings change in the last day.", "Who is on call and who can make decisions, with their roles.", "Your own severity levels or on-call rules (optional)", "After the incident, the full timeline and what fixed it (optional)" ], "you_get": [ "A severity call and why, with what would raise or lower it.", "Named roles and who does what.", "A short list of things to check next, each with a time limit.", "Draft status updates for your team, your leaders and your customers.", "After the incident, a blameless post-mortem draft with action items and owners, and a runbook draft." ], "use_when": [ "Your site or app is down or slow, and a team is in a chat trying to fix it with no clear lead.", "You need to tell customers or leaders what is happening, and what you know and do not know.", "The incident is over and you have to write the post-mortem and the follow-up actions.", "You want a first runbook for a failure that has happened before." ], "skip_when": [ "You think you were hacked or data was stolen. Use the Security incident responder, which covers security incidents.", "A database is down or may have lost data. Use your own runbook and your database admin first. For recovery planning later, use the Database recovery planner.", "You want service goals, error budgets and alert rules set up. Use the SRE agent.", "You want it to find the cause in your logs or fix the system. It cannot see your systems. Your engineers do that." ], "output_sample": { "input": [ "What is broken, since when and who is affected", "Alerts, error messages and recent changes", "Who is on call and who decides", "After the incident, the full timeline and what fixed it (optional)" ], "prerequisites": [ "A person in charge who can approve each update before it is sent." ], "output": [ { "name": "Situation", "contains": "What is broken, since when, who is affected, recent changes and what is still unknown." }, { "name": "Severity", "contains": "A level with the reason, and what would raise or lower it." }, { "name": "Roles", "contains": "A lead, an updates writer, a technical lead and a note taker, with what each does." }, { "name": "Next 15 minutes", "contains": "Things to check in order, each with a time limit and a way to confirm or drop it." }, { "name": "Status updates", "contains": "Draft messages for your team, leaders and customers, with known, unknown and next update time." }, { "name": "Post-mortem", "contains": "Timeline, causes, what went well and poorly, and action items with owners and dates." }, { "name": "Runbook draft", "contains": "Steps to detect, diagnose, fix and verify this failure next time." }, { "name": "Gaps and checks", "contains": "Missing facts and open choices, with who should decide each." } ] }, "output_shape": "DURING THE INCIDENT\n\nSITUATION\n Broken | Since