Imagine you're a senior developer working on an account-management service. You ask a coding agent to add audit logging when users change their account details. It has access to the repository, you give it a few constraints, and you get on with something else.

AI can now generate clean, well-tested code in minutes, but who ensures we're building the right thing? This article explores why engineering judgment, challenging assumptions, and understanding business requirements are becoming increasingly important as AI transforms software development..

Part of the Change Seams series - Instrument once, export anywhere..

Part of the Change Seams series - why args_schema is the most important five lines in your tool definition, and how a contract layer survives model upgrades.

Part of the Change Seams series - architecture patterns for LLM applications that survive the real world.

Applying Software Engineering Principles to Everyday Challenges