The Agent-Shaped Codebase
Codebases are about to be read more often by agents than by people. That changes what "clean code" means.
Agentic Development
Everything filed under Agentic Development — essays, notes, playbooks and signals.
The Review Is the Work
When generation is free, the scarce resource is judgement. That reframes what a senior engineer is for.
What Agents Still Cannot Do
An honest list, kept up to date, of where the end-to-end agentic workflow still falls over.
AGENTS.md is the new README
The README was written for a human who would skim it once. This file is read in full, every run.
The context window is a budget, not a container
Half-formed thought on why "just paste more" stops working past a certain repo size.
The cost of a half-finished abstraction
Unfinished abstractions are worse than none, and agents make them cheaper to create and harder to spot.
What I want from an agent harness
A running wishlist. Mostly about observability and being able to stop the thing mid-flight.
Budget the context before adding tools
Every tool definition costs tokens on every turn. Most agent slowdowns are a context problem, not a model problem.
AI is breaking our proxies for expertise
The signals we used to judge competence — clean code, fast output — no longer carry information.
Workflow or agent, and why the distinction matters
The clearest public writing on when an agent loop beats a fixed workflow.
Don't build tools for AI agents
An argument that agents should use the tools humans already use, rather than getting bespoke ones.
Engineer away the slop
On treating low-quality agent output as an engineering problem rather than a model problem.
Slow developer experience will bottleneck fast models
If the model is faster than your CI, your CI is now the product constraint.