MCP | Thomas Talks AI

A Claude Code agent run leaving receipts for changed files, tests run, logs captured, risk notes, and undo path

Claude Code needs permission receipts, not blanket trust

Claude Code permissions matter before the run, but teams also need permission receipts after the run: what the agent used, what was blocked, what still needs approval, and how to undo it.

Two books connected to an operating stack for useful, reviewable, bounded, and auditable AI agent work

Treat agent autonomy like a production privilege

The safer question for Claude Code and enterprise agents is not how much autonomy the model can handle. It is which privilege the work deserves, how long it lasts, and what evidence the human gets back.

Two AI agent books connected by code and risk loops for production AI agents

The agent runbook needs a buyer's question

AI agent teams often ask whether the demo worked. Buyers, auditors, and production owners ask a harder question: can we trust the run when authority, evidence, and rollback are visible?

Two books, one operating stack: Claude Code in production and bounded enterprise AI autonomy

The agent diff and the agent boundary belong in the same conversation

Claude Code review packets and enterprise agent security are often treated as separate problems. They are two parts of the same operating stack: evidence for the work, boundaries for the authority.

A production review path for AI agents: task, authority, evidence, and approval

Before the agent gets more access, write the review path

Teams keep asking whether an AI agent is ready for more autonomy. A better question is whether the review path is clear enough before the next permission is added.

A prompt box outside a production control plane with identity, scope, approvals, logs, revocation, and review

The prompt is not the control plane

A good prompt can shape agent behavior, but production teams need a control plane around identity, tool scope, approval, logs, revocation, and review.

Agent autonomy needs a stop button and a receipt

Production AI agents need a fast way to stop action and a plain receipt after every meaningful run. Without both, autonomy becomes trust without evidence.

A workflow showing pilot AI agent access reviewed with evidence before it is renewed or expired

AI agent access should expire before it becomes hidden authority

Agent permissions that helped a pilot can become hidden production authority. Put expiry, renewal evidence, and removal paths around AI agents before access drifts.

Cover of Architect the Agent: The CCAR-F Certification Guide

CCA exam preparation: think in boundaries, not product features

For the Claude Architect exam, product knowledge helps, but boundary judgment matters more: tool scope, context provenance, permissions, review, and recovery.

A diagram showing the risky handoff between an AI agent demo and production use

The agent demo is not the risk. The handoff is.

AI agent demos fail quietly when teams hand them to real workflows without scope, authority, evidence, and rollback. This is where Claude Code practice and enterprise agent security meet.