On-Call with AI

Modalità
Online
Lingua
en
Livello
practitioner

Il corso

Fight ordinary production outages with AI agents: wire one into your telemetry, triage, debug live, verify the root cause, and decide exactly what it may touch in prod. All hands-on work runs on a provided lab.

Identità del corso

Livello

practitioner

Lingua

en

Programma e obiettivi

Obiettivi
  • - Wire a read-only agent into your logs, metrics, and traces, then keep the same setup ready for Datadog or New Relic.
  • - Turn a raw 3am page into a sourced, four-question incident brief in under two minutes.
  • - Run a hypothesis loop with an agent against a real, scripted outage, and keep the playbook that finds it again.
  • - Chase a bad deploy past its red herring to a cause a human can verify in five minutes.
  • - Turn a messy prose runbook into steps an agent can run safely, with approval gates where it matters.
  • - Write the policy that decides what your agent can read, what it can propose, and what it can never do alone.
Programma
  • Url: https://aiacademy.anthropos.work/chapters/oncall-with-ai-intro/ · On-Call with AI: Start Here · Position: 1 · Seven chapters, one lab, and a clear line between what your agent can read today and what it earns the right to touch later.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-agent-ready/ · Your Stack, Agent-Ready · Position: 2 · Wire a read-only agent into your logs, metrics, and traces, then keep the same setup ready for Datadog or New Relic.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-alert-triage/ · Alert Triage with an Agent · Position: 3 · Turn a raw 3am page into a sourced, four-question incident brief in under two minutes.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-live-debugging/ · Live Debugging Under Pressure · Position: 4 · Run a hypothesis loop with an agent against a real, scripted outage, and keep the playbook that finds it again.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-root-cause/ · Root Cause Analysis That Holds Up · Position: 5 · Chase a bad deploy past its red herring to a cause a human can verify in five minutes.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-runbooks/ · Runbooks Agents Can Execute · Position: 6 · Turn a messy prose runbook into steps an agent can run safely, with approval gates where it matters.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-guardrails/ · Guardrails: What the Agent Touches in Prod · Position: 7 · Write the policy that decides what your agent can read, what it can propose, and what it can never do alone.
  • Url: https://aiacademy.anthropos.work/chapters/oncall-postmortems/ · Postmortems & the Learning Loop · Position: 8 · Draft a blameless postmortem with an agent, file it with owned action items, and track whether the rotation is actually improving.

Edizioni

Edizioni

Course Mode: online · Course Workload: PT150M · Mode: online

Corsi simili