Skip to content
InfratoApp

Anthropic · Course

The AI-native SDLC playbook

The AI-native SDLC playbook is Anthropic’s guide for engineering leaders whose approvals, reviews and handoffs still run at human speed after adopting Claude Code. It walks the six stages of the software lifecycle and what changes at each.

Open at Anthropic ↗Common questions

Who it suits

  • Engineering, platform and security leads at organisations that already use Claude Code.
  • Large and regulated enterprises, where the review queue cannot build up and code cannot ship under-reviewed.

What it covers

  • What changes at each of the six stages between a traditional and an AI-native lifecycle.
  • Using an intent.md file as a requirements and design spec in one working session with Claude.
  • Choosing whether knowledge belongs in CLAUDE.md, a skill or a hook.
  • Evals that rerun when the agent’s setup changes, and Claude reviewing every pull request while people review some code by hand.
  • Hooks that hold actions such as a release until a person approves.

Before you start

  • Comfort working in Claude Code day to day.
  • A Git repository and CI pipeline you are allowed to change.

Common questions about The AI-native SDLC playbook

How long is The AI-native SDLC playbook?
Anthropic lists 14 lessons on the course page.
Is it for individual developers?
It is written for leads who can change how their organisation plans, reviews, tests and deploys, not only how it writes code.
Is there a written version?
Anthropic says the full playbook can also be read as a single page on the Claude blog.
Does every play have prerequisites?
Each play names its own prerequisites, and Anthropic says several have none.

More like this

Keep learning on Infrato

Where this comes from

Written from Anthropic’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Anthropic and this is not an endorsement.