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
-
How do I notice when an AI agent or automation reports success but got it wrong?
A success status only says the steps finished. Catch quiet failures with outcome checks in code, expected-volume alarms and a heartbeat per trigger, and…
-
Can AI code review take load off your human reviewers, and how do you test it first?
An AI reviewer can take part of the first pass on your pull requests. How much is a question for your own code: replay…
-
How should an AI agent hold and use the credentials for the business systems it acts on?
Give each agent its own identity and a named sponsor, let the tool layer fetch a narrow, short-lived credential per action, keep secrets out…
-
What working agreements should a team set for AI-assisted development?
Six working agreements for AI-assisted development (scope, size, tests, an author who can explain the change, unattended agents, owned instruction files), each held by…
-
How do I make an AI agent stop and hand the conversation to a person instead of guessing?
Decide the stop points before launch, check them in code on every message, record who owns each conversation so the agent stays silent during…
-
Loop Engineering: Build the Core Before You Automate the Loop
The recurrence is the visible part of Loop Engineering. The core determines whether every cycle compounds value or repeats uncertainty.