Articles
Notes from shipping software with AI
For engineering leaders who want AI-assisted delivery they can check. Written from our own work, not from the sidelines.
Topics
- AI agents (13)
- AI Coding Agents (1)
- AI delivery (88)
- AI Delivery Programme (12)
- AI Workflow Audit (2)
- Architecture Review (2)
- Laravel (1)
- MVP to Production (1)
Start here
Review capacity
The review queue is the bottleneck AI coding created
Why more code did not mean more shipped, and where the queue actually forms.
Instruction drift
Agent instruction drift in enterprise AI teams
How every developer ends up with a different AI, and what a shared rule set changes.
What was tested
AI coding checkpoint contract: make checks reproducible
What “tested” should mean before a pull request is allowed to say it.
Latest
-
The provider compatibility contract for Claude Code, Codex, Gemini, and other hosts
A provider agnostic AI coding workflow owns intent, rules, state, decisions, evidence, and receipts in the repository, then publishes a versioned compatibility contract for…
-
Documentation sync as context maintenance for the next human and agent
AI documentation sync maps a code change to every affected documentation surface, assigns an owner, updates or explicitly defers each artifact, and verifies consistency…
-
AI coding is fast. Verification is the work.
AI coding tools can produce useful first drafts, but the real engineering work starts when a team has to verify, secure, and maintain that…
-
How do you secure a Laravel API before production?
Protect each request at three separate boundaries: who may call it, which values may enter the model, and how often the action may run.
-
When should you use no-code instead of custom code?
Choose no-code for standard governed workflows and custom code for distinctive logic, demanding integration, scale or control.
-
When should you rewrite a codebase from scratch?
Rewrite a codebase only when repair cannot reach a required outcome and behaviour, data and operations can migrate safely.