Softwareengineering

A tested Claude Code commit changing after a rebase, causing a release gate to reject stale evidence and run the checks again

Your green check belongs to a commit, not a pull request

A Claude Code branch can change after tests pass and approval is given. Bind test results, review evidence, and release approval to the exact commit that produced them.

An AI agent evaluation that checks the request, identity, tool path, data boundary, side effects, evidence, and final answer

Test the tool path before you trust the agent's answer

An AI agent can return the right answer after using the wrong identity, reading the wrong data, or calling a tool it never needed. Production evals should inspect the path as well as the result.

A Claude Code run replay record connecting the task contract, agent actions, decision points, evidence packet, human review, and incident replay

A diff cannot replay a Claude Code run

A Claude Code diff shows the final change, but it leaves out the starting state, failed commands, MCP results, skipped tests, and plan changes. Capture a compact replay record before the run disappears.

A production control loop for Claude Code with task contract, stop conditions, bounded run, evidence packet, and human review

Claude Code stop conditions are agent security controls

A production Claude Code run should know when to stop. Stop conditions turn unclear scope, wider tool access, weak rollback, and missing evidence into human review moments before an agent crosses a security boundary.

A four step control loop for normal agent grants, exception asks, human gates, and receipts

Give agent exceptions a budget before they become policy

Claude Code and enterprise AI agents sometimes need more access than the normal task contract allows. Treat that extra authority as an exception budget, with a reason, owner, expiry, evidence, and revocation path.

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?

A diagram showing an agent bringing proof into a review packet with intent, diff map, tests, risk note, and rollback

Claude Code diffs need review packets, not trust

A Claude Code diff shows the changed lines. A review packet shows the delegated intent, scope, checks, risks, and rollback path a human needs before merge.

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.