October 26, 2026
A coding CLI becomes a service when sessions have owners
Turning a coding agent into a shared service makes session ownership, reconnect behavior, authorization and cleanup part of the system contract.
Read article
Posts tagged “ai-assisted-engineering”.
One tag at a time. The full list is on the articles page.
October 26, 2026
Claude Code mods are an extension-governance decision
Claude Code mods can replace built-in behavior and interact in load order, so teams need an allow-list, compatibility policy, and combined-configuration tests.
Read article
October 26, 2026
Treat agent uncertainty as a review hint
A coding agent’s uncertainty can help direct review, but tests, diffs, and human judgment—not confidence—must determine whether its work is sound.
Read article
October 26, 2026
Put a hard budget around nested coding-agent work
I argue for treating nested coding agents as a resource-control problem, with enforceable limits on delegation, tools, spend and elapsed time.
Read article
October 19, 2026
Test Claude Code hooks as behavior contracts
I explain why natural-language hooks need adversarial regression tests and where deterministic controls must enforce policy outside the agent.
Read article
October 19, 2026
AI review findings need a queue, not a gate
AI review can surface defects faster than a team can resolve them; I argue for managing findings as work with explicit triage and release capacity.
Read article
October 13, 2026
Worktrees move agent risk to integration contracts
I explain why isolated agent worktrees reduce edit collisions but leave task ownership, interface compatibility and integration decisions unresolved.
Read article
October 13, 2026
Give Claude Code workflows explicit stop conditions
A repo-scale coding agent needs defined checks, evidence to return, and clear points where human judgment takes over.
Read article
October 8, 2026
Model upgrades should earn their place in coding-agent workflows
A repeatable set of repository-specific tasks can show whether a new coding model improves your workflow enough to replace its current default.
Read article
October 6, 2026
Managed coding agents change the control-plane question
A practical way to compare managed coding agents with agents running in your own environment is to trace who controls access, execution and evidence.
Read article
October 5, 2026
Long-running coding agents need checkpoints, not just larger tasks
I explain why inspectable changes, explicit stopping points, and deliberate resumption make extended coding-agent work easier to review and recover.
Read article
October 4, 2026
What Claude Code auto mode can decide—and what I would gate
I explain where Claude Code auto mode can reduce approval friction, and which actions I would still keep behind explicit human approval.
Read article
October 4, 2026
Treat coding-agent memory as a cache
Learn why coding-agent memory is useful context, not an architectural record, and how to keep reviewed decisions authoritative when memory goes stale.
Read article