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.
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
-
Security approved the AI tool, but not the workflow
Security can approve an AI tool and still leave the delivery workflow unmanaged. This post shows the control gap paqad-ai helps close.
-
The AI pilot worked because one senior developer babysat it
A realistic enterprise AI pilot failure: the demo works because one senior developer quietly provides all the missing context, review, and guardrails.
-
When CLAUDE.md, GEMINI.md, and AGENTS.md disagree
A realistic look at how agent instruction files drift in enterprise teams, and how paqad-ai keeps provider files thin while the repo…
-
Enterprise AI rules need executable checks
Written rules help agents. Executable checks make rules enforceable. This post explains how paqad-ai moves enterprise AI governance from prose to scripts…
-
Enterprise AI breaks when every agent has different rules
Teams ask for CLAUDE.md, GEMINI.md, AGENTS.md, and Cursor rules for good reasons. This post shows why those files need one shared repository…
-
Enterprise AI compliance cannot live in chat
Enterprise AI compliance needs durable evidence. This post shows how paqad-ai turns specs into obligations, tests, and reports that reviewers can inspect.