{ "schema": "aiblocks-page/1", "id": "agency-engineering-sre", "type": "agent", "name": "Site reliability engineer", "summary": "Turn how your service fails into reliability goals, alert rules and recovery checks. Give it your service details and get a plan to review.", "headline": "Site reliability engineer", "subhead": "Describe one service, how it runs and how it has failed before. It sets goals for what \"working\" means, decides how much failure you can allow, and drafts alert rules and recovery checks. You get a reliability plan you can check against your own numbers.", "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": "document", "required": false, "label": "Document", "what": "a finished document, such as a Word file, a PDF or a page of notes" }, { "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": "audit_report", "required": true, "label": "Audit report", "what": "findings with evidence, severity, missing inputs and next actions" } ], "you_give": [ "The service name and what users do with it, such as logging in, paying or loading a page", "How it runs, in a few lines. Name the host or cloud, the main parts and how you release changes.", "What your users would call broken, and the worst failures you have had", "Your current monitoring, alerts and who gets paged (optional)", "Request and error numbers for the last 30 days (optional)" ], "you_get": [ "Reliability targets for the service, each with how to measure it", "An error budget and the rule for what to do when it runs out", "Alert rules tied to how fast the budget burns, with who is paged", "A list of manual jobs to automate, ranked", "Recovery checks to test before you need them" ], "use_when": [ "Customers have started to notice your site or app going down, and you have no written goal for how reliable it should be.", "Your alerts fire all night and the team now ignores them.", "You want to decide when to pause new features and fix stability, and need a rule that is not a gut call.", "A big launch is coming and you want to know what could fail and how you would recover." ], "skip_when": [ "Your service is down right now. Use the Incident response coordinator.", "You want only targets and an error budget for one service. Use the Service reliability target planner.", "You run a small site and want simple uptime pings and an on-call plan. Use the Uptime and alert setup planner." ], "output_sample": { "input": [ "One service and what users do on it", "How it runs and how you release changes", "What users would call broken, and your worst past failures", "Your current alerts and request or error numbers (optional)" ], "prerequisites": [ "An AI that can read pasted text or files", "Access to your monitoring tool, to copy numbers from it (optional)" ], "output": [ { "name": "Service scope", "contains": "The service, its users and what they would call broken." }, { "name": "Reliability targets", "contains": "Each measure with a target, a time window and how to measure it." }, { "name": "Error budget", "contains": "How much failure each target allows, and what to do when it runs out." }, { "name": "Alert rules", "contains": "Fast and slow burn alerts with who is paged and what to check first." }, { "name": "What you can see", "contains": "Delay, traffic, errors and load, marked seen or blind spot." }, { "name": "Recovery checks", "contains": "Checks to test before you need them, with an owner and how often." }, { "name": "Repeat work to automate", "contains": "Manual jobs ranked by how much time they cost." }, { "name": "Assumptions and checks missed", "contains": "What the AI assumed and what it could not check." } ] }, "output_shape": "SERVICE SCOPE\n Service | Users | What counts as broken \n\nRELIABILITY TARGETS\n | |