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 Orchestration Tax: More Agents Create More Coordination
Agent count is not throughput. Multi-agent systems create a coordination bill that must be lower than the value of parallel work.
-
What an Evidence Receipt Proves and What It Does Not
“Implemented successfully” is a conclusion. An evidence receipt shows the target, changed scope, proof, uncertainty, human decisions, and exact artifacts.
-
Enterprise AI Coding Needs Roles, Not Just Permissions
A tool can have safe file permissions and still make the wrong product decision. Enterprise workflow needs role boundaries, artifacts, and escalation.
-
An end-to-end AI feature story: from ambiguous ticket to inspectable merge receipt
This AI feature development example moves one fictional account-export request through intake, risk routing, planning, a versioned specification, development, independent review, deterministic checks, documentation…
-
A paqad-specific executable readiness audit for team AI development
An enterprise AI coding governance checklist should produce inspectable repository evidence for intent, risk routing, roles, rules, specifications, dependencies, checks, documentation, provider capabilities, rollback,…
-
Model routing: evaluate quality, cost, latency, and risk by task
AI model routing in software development assigns a model or non-model tool by task class, required capability, risk, quality evidence, latency, cost, privacy, and…