Cuiar
Sign inDownload

Write an incident postmortem from the timeline

A blameless draft with the timeline, impact, cause and actions, built from chat, monitors and deploys.

  • You start it: When you start it
Use in CuiarRun from your AI agent

What it does

The task

Read the Slack channel incident channel, the Datadog monitors and graphs for the time window window, and the GitHub deploys and pull requests in that window. Build a timeline in UTC with each detection, decision, deploy and recovery. Write a blameless postmortem draft in a new Google Doc: summary, impact with numbers, timeline, root cause, what went well, what went badly, and actions with the owners named in the channel. Mark each statement that has no source as 'to confirm'. Do not share the doc.

  • It works in Slack, Datadog, GitHub and Google Docs, in the workspace you pick, and signs in with passwords from your Cuiar vault.
  • It runs once, when you start it.

What you give it

BlankWhat to giveExample
incident channelThe Slack channel of the incident#inc-export
windowThe start and end of the incident, with the time zone4 Nov 2026, 10:30 to 12:30 UTC

What you get back

An example run with the example values above. Your run uses your own data.

Postmortem draft: CSV export failures, 4 Nov

Impact: 1 h 38 min, 1,240 failed exports, 312 accounts

Timeline (UTC)

10:42 Deploy of 2.5.0 (web#817)

10:50 First alert: export-worker error rate above 5%

11:20 Incident opened in #inc-export

11:58 Rollback to 2.4.2 started

12:20 Error rate back to 0.2%

Root cause: a renamed field in the export query (to confirm)

Actions: contract test for the export API (Kofi), alert on export errors per release (Nadia)

Run it in Cuiar

  1. 01

    Open it

    Click Use in Cuiar on this page. The side panel opens with the task in the composer.

  2. 02

    Fill in 2 blanks

    Type incident channel and window. Tab moves to the next blank.

  3. 03

    Run it

    Run sends it to the agent. Follow each step in the panel, and stop it at any time.

From the terminal

cuiar exec "Read the Slack channel #inc-export, the Datadog monitors and graphs for the time window 4 Nov 2026, 10:30 to 12:30 UTC, and the GitHub deploys and pull requests in that window. Build a timeline in UTC with each detection, decision, deploy and recovery. Write a blameless postmortem draft in a new Google Doc: summary, impact with numbers, timeline, root cause, what went well, what went badly, and actions with the owners named in the channel. Mark each statement that has no source as 'to confirm'. Do not share the doc."

Run it from your AI agent

Claude Code, Codex, Cursor and other MCP clients reach Cuiar at https://mcp.cuiar.com/mcp. Add the server one time, then ask for the task in plain words, or call run_task yourself.

1. Add Cuiar to Claude Code

claude mcp add --transport http cuiar https://mcp.cuiar.com/mcp

2. Ask your agent

Use the Cuiar tool run_task to run my "Write an incident postmortem from the timeline" template with incident channel = #inc-export; window = 4 Nov 2026, 10:30 to 12:30 UTC.

Setup for other agents: AI agents.

The tool call

{
  "name": "run_task",
  "arguments": {
    "task": "Read the Slack channel #inc-export, the Datadog monitors and graphs for the time window 4 Nov 2026, 10:30 to 12:30 UTC, and the GitHub deploys and pull requests in that window. Build a timeline in UTC with each detection, decision, deploy and recovery. Write a blameless postmortem draft in a new Google Doc: summary, impact with numbers, timeline, root cause, what went well, what went badly, and actions with the owners named in the channel. Mark each statement that has no source as 'to confirm'. Do not share the doc."
  }
}

Related templates

All engineering templates

  • EngineeringAsks first

    Draft status page updates during an incident

    A clear update from the incident channel and your monitors, posted to your status page after you approve it.

    You start it: When you start it
    • Slack
    • Datadog
    • Any status page

  • OpsAsks first

    Set up accounts for a new employee

    Invites to each tool your team uses, with the same access as a colleague in the same role.

    You start it: When you start it
    • Any admin panel
    • Slack
    • Notion
    • +1 more: Google Docs

  • OpsAsks first

    Remove a former employee's access to your tools

    Every account the person still has, closed after your approval, with their files moved to a new owner.

    You start it: When you start it
    • Any admin panel
    • Google Drive
    • Slack
    • +1 more: GitHub

  • Recruiting

    Review take-home assignments with your rubric

    Each submission scored against your rubric, with evidence from the code or document for every score.

    You start it: When you start it
    • GitHub
    • Google Docs

  • Recruiting

    Brief interviewers before each interview

    A one-page brief from the candidate's resume and work samples, with the focus for this round.

    On an event: Two hours before each interview in your calendar
    • Google Calendar
    • Greenhouse
    • GitHub
    • +1 more: Google Docs

  • Engineering

    Check web pages for accessibility problems

    WCAG 2.2 AA problems on each page, with the element, the rule and a fix, the blockers first.

    You start it: When you start it
    • Any website
    • Google Docs