#coding-agents

Evals, backpressure and agent guardrails are the feedback loops we already had. The mechanism didn't change, only who reads the output.

There's a quiet assumption in agentic workflows that context switching stopped being a problem. It didn't. Here's how I capture mid-session discoveries without leaving the task I'm actually in.

A principle emerging from agentic coding: verification steps that pass should produce no output; failures should dump everything. Simple idea, but it matters more than you'd expect when an LLM is the one reading the output.

Matt Pocock explains why subagents are the dominant pattern for coding agents, keeping work in the first 40-50% of the context window where models perform best.