R058 · AI-built software and its verification › Agent delivery workflows

AI-native SDLC: Anthropic's playbook vs AWS AI-DLC

Read the original

sdlcagent-workflowsagent-governanceharness-configevalshuman-oversightcompetitive-analysis

The claim

Rakesh Gohel's post argues that faster models only move the bottleneck: planning, review and approval were sized for human-written code, so the lifecycle itself is what to redesign next. He contrasts two answers. AWS Labs' AI-DLC makes the workflow adapt to each task, so small changes skip stages. Anthropic's AI-native SDLC playbook makes every stage commit an artifact the next stage reads, with humans at the key gates.

The post itself is a framing plus a five-step starter kit: pick one low-risk service, add the AI-DLC rules and check the agent asks questions before coding, write the intent as a repo file and approve the plan first, put conventions in CLAUDE.md and enforce the rest with hooks, and name one senior owner who signs off production. The substance is in the playbook, so most of this summary is about it.

The playbook in one paragraph. Louis Claxton (Anthropic Applied AI), published 2026-08-21, about 40 minutes. When build collapses to hours, plan, review/test and deploy still run at human speed, line-by-line review stops scaling, and governance by committee gets more expensive. The fix is a loop of six non-linear stages (Plan, Design, Build, Test, Deploy, Maintain), each made of "plays" with prerequisites, steps, governance and a leading and lagging metric. The thread through all of it is the committed artifact: intent.md, spec.md, plan.md, the diff and tests, the PR with review findings, the incident record. Each accepted artifact triggers the next stage, and the chain of commits is the audit trail. The end state is closed: a deterministic monitor breaches a control band, Claude diagnoses, and the finding re-enters as a new intent.md.

What is genuinely useful, beyond the product tour.

The artifact chain

Each stage commits an artifact the next stage reads1 Plancommits intent.mdgate: product owner accepts2 Designcommits spec.mdgate: product owner signs off3 Buildcommits plan.md, then the diffgate: engineer approves plan4 Testtests and evals run in CIagent cannot edit the tests5 DeployPR with review findingsgates: code owner, release6 Maintainband breach or scheduled scanwrites a new intent.mdloop closes, no human starts it
AI-native SDLC loop · 6 stages, the artifact and gate of each

An accepted artifact fires the next stage; humans sit at the gates rather than starting each stage. Only Maintain runs without a person in the invocation path.

Playbook vs AI-DLC

They are complements more than rivals: AI-DLC is an engine you install, the playbook is an operating model you assemble from Claude Code primitives. AI-DLC details come from its 2.x repo and spec; playbook details from the article.

DimensionAnthropic AI-native SDLC playbookAWS Labs AI-DLC
What it isGuidance: six stages of plays, each with steps, governance and metricsOpen-source rules plus a deterministic workflow engine for coding agents (MIT-0)
Who routes the workAccepted artifacts trigger the next stage (merge of intent.md, approval of spec.md, merged PR)The engine routes phases and stages, and skips stages for small tasks
Unit of recordCommitted Markdown per change: intent, spec, plan, then diff, PR and incidentPer-intent records, an audit log, kept rules and a code-derived knowledge base
Human gatesProduct owner on intent and spec, engineer on plan, code owner on PR, release manager at productionExplicit stage gates with recorded approvals bound to a source fingerprint
EnforcementSkills (advisory) backed by hooks and managed settings (deterministic)Engine routing plus sensors and post-conditions on stage outputs
Learning loopA mistake made twice goes into CLAUDE.md; every incident becomes an evalA human correction becomes a consented, dated rule after a conflict check
Closing the loopMonitors and scheduled scans write new intent.md files without a human starting themNot a focus; work starts from a human request
MeasurementA leading and lagging metric per play, mostly from git and PR metadataApproval and audit records; less on outcome metrics
PortabilityWritten for Claude Code, Claude Tag and Claude Security, but the pattern is tool-neutralOne core across several harnesses

The post's starter kit mixes them sensibly: AI-DLC's rules for structure on day one, the playbook's artifacts, CLAUDE.md and hooks for the parts you will want to own.

Tradeoffs and failure modes

Review checklist

For a team adopting either approach on one service:

Sources

Connections

See R058 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.