Operations · Advanced

Verified

Automated verification

  • Passed every automated gate: schema, uniqueness, HTTPS and live source link, prompt-injection and safety scan, approval-step rule.
  • Drafted by deepseek-flash via DeepSeek API.
  • Second-model review: kimi-code/k3.1-pro (no critical or high findings).
  • Verified .
  • Automated checks and AI review only, not human review.
How verification works

Investigate production alerts with reusable runbook steps

Turn repeated incident checks into saved steps an agent can reuse

Use with BotBento

Opens BotBento with this bot ready to create. You check it, create it in one click, then connect its apps. Nothing runs until you do.

  1. When something happensMonitoring alert arrives
  2. ThenCorrelate logs, code changes and open
  3. ResultDraft incident summary for approval

When a monitoring alert fires, the bot gathers evidence from telemetry, recent code changes, open issues and team chat, then traces the most likely cause. After a successful investigation, it records the checks that worked as a reusable procedure so similar alerts can be handled faster. It prepares an incident note for a human to review before anything is posted or changed.

Quick answers

What does it do?

Turn repeated incident checks into saved steps an agent can reuse. Result: Draft incident summary for approval.

What does it need?

Tools: Datadog, GitHub, Linear, Slack, Notes. Advanced: more tools and setup. The prompt includes an approval step.

How do I run it?

When something happens: Monitoring alert arrives. Copy the prompt below into a bot in BotBento.

Prompt to start with

BotBentoRecommended
When an alert arrives, collect the relevant telemetry signals, inspect recent code changes and related open issues, and review team chat for context. Identify the likely cause and note which checks resolved the investigation. Save the successful sequence as a reusable runbook step for similar alerts. Draft an incident summary with evidence, suspected cause and suggested next actions. Do not post messages, update tickets, send emails or delete anything without the user's approval; present changes for review first.