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
-

What evidence should enterprise AI teams keep outside chat?
Keep durable evidence beside the work: approved intent, material decisions, executed checks, exceptions, and the person who accepted the result.
-

What decisions should enterprise AI teams commit to the repository?
Commit decisions that change scope, risk, architecture, data use, or acceptance, and link them to the change they authorized.
-

Why do enterprise AI teams need workflows instead of better prompts?
Prompts help a single interaction; a workflow defines the durable handoffs, evidence, authority, and stop conditions that many people and tools must share.
-

What documentation should an enterprise create before using AI coding agents?
Document the decisions an agent cannot safely infer: module boundaries, approved commands, data rules, review owners, and release constraints.
-

How do you stop AI test output from consuming the context window?
Keep the full log as an artifact, but return a compact failure summary to the agent: command, exit status, failing cases, first useful error,…
-

What should an AI development workflow audit prove?
The audit should prove that a reviewer can connect the request, decisions, code, checks, and release without reconstructing the story from chat.