Written by
Haider Lasani
Author of The Decisions AI Can’t Make for You and The Backlog That Thinks. Writes for engineering leaders whose teams ship with AI, about delivering inside one enforced, checkable process. About Eliyce · Talk to us
Articles
Everything published under this name
-

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.