Merit AC
Guide · from the Agentic DevSecOps reference deck Andrew Clark

Four control boundaries for agentic DevSecOps

Code generation is the easy part. The enterprise problem is controlling what happens after the model decides what it wants to do.

The problem

Model reasoning — inspect repository, propose a change, select a tool, explain intent.

Enterprise authority — identity, policy, CI/security gates, approval + deployment.

Do not collapse these two layers.

The four boundaries

The platform has four control boundaries. Every action crosses a boundary that can be logged, denied, reviewed, tested, or rolled back.

  1. Request — engineer / application
  2. Reason — Claude Code + Bedrock
  3. Authorize — Gateway + identity + policy
  4. Verify — CI/CD + sandbox

Evidence rail: model call · tool call · policy result · CI result · approval · deployment · health

Claude Code: treat the repository as the operating context

CLAUDE.md is the engineering contract, not a substitute for security enforcement. The workflow: Discover → Plan → Change → Validate → Pull request.

Repository rules that matter:

MCP + tools: narrow tools beat an unrestricted shell

Claude Code requests an operation → the Tool Gateway enforces a typed contract and policy → AWS/Git authorizes the target.

Blocked by design: arbitrary admin shell · broad inherited credentials · unregistered cloud actions

DevSecOps: the agent does not grade its own work

Build → unit + integration → IaC validation → SAST / SCA → secrets → approval → deploy. Independent gates decide whether the artifact moves forward. A model assertion never replaces a test result, scan result, policy decision, or deployment health signal.

Observability: an evidence chain, not a chat transcript

  1. Request — who asked + what changed
  2. Model — invocation + reasoning context
  3. Tool — operation + identity + policy
  4. Pipeline — tests + scans + artifact
  5. Decision — review + approval
  6. Runtime — deploy + health + rollback

The operating model: start bounded, scale on evidence

Agentic engineering becomes useful at enterprise scale when the controls are visible, independent, attributable, and measurable.

Claude Code + AWS controls + independent evidence = trust.

This is the short version of the ten control disciplines — see the 30-day challenge to build the reference project these four boundaries describe.