Tag: ai
All the articles with the tag "ai".
-
Agentic reflective practice
David Morgan-Brown looks at why coding agents sometimes abandon their built-in tools for surprising shell pipelines, and what reflective practice can tell us about that behaviour.
-
From One Agent to Many
Adding a second agent is not a linear productivity upgrade. Work decomposition, review capacity, shared state, and cost all become coordination problems rather than prompting problems.
-
The Agent Harness Is the Product
A capable model is only one component of a dependable coding agent. The harness decides what context it sees, which actions it can take, how it receives feedback, and when it must stop.
-
Stop Reviewing Every Line
Line-by-line review does not scale with agent output, but abandoning review is not the answer. A risk-based approach moves attention towards invariants, interfaces, dangerous changes, and evidence.
-
Tests Are Backpressure
Faster code generation only helps when the rest of the system can reject bad work quickly. Tests, static checks, and CI provide the backpressure that makes greater agent autonomy sustainable.