Skip to content

Blog

Context engineering

What an agent reads before it starts and who keeps it current: context files such as CLAUDE.md and AGENTS.md, a focused context window, and the decisions a team never wrote down.

  • 16 posts, newest first
  1. Who owns the file every agent reads first Since Claude Code 2.1.277 reads AGENTS.md where no CLAUDE.md exists, one instruction file can serve every coding agent on a team. The file was never the hard part: the instructions are a team decision and need one owner, so merge the files into one AGENTS.md and name who owns it. 1 min readShort post
  2. Million-token windows did not remove the dumb zone Agent quality degrades without warning above roughly 40 percent context fill, the zone Dex Horthy named. Windows grew to a million tokens and the failure mode came along, so starting bare metal is still the habit that keeps a session out of it. 2 min readShort post
  3. Feed the factory the decisions nobody wrote down In most organizations the knowledge that matters most is decided out loud in meetings and never written. Five concrete steps route it into the context layer the factory reads. 2 min readShort post
  4. AI tool fatigue is a missing context layer Teams count their AI tools when the list that decides is the second one: skills, commands, CLAUDE.md entries and context files. Where that list is rich, the tool list shrinks on its own. 1 min readShort post
  5. Your coding agent is a free audit of your documentation Code generation is solved, so the constraint is now context. Every wrong answer an agent gives points at a standard the team knows and never wrote down. 2 min readShort post
  6. Context engineering is the standardization you could never sell Preparing context for AI agents forces the documentation and standardization architecture teams have pushed for years. The agent does not need it more than the organization did. It removes the resistance. 1 min readShort post
  7. One AGENTS.md for four AI tools is harness debt A single context file behaves differently in every harness and every model. The four kinds of harness debt we keep finding in teams, and what a Dark Factory does instead. 2 min readShort post
  8. A study says context files hurt agents. It tested the wrong thing ETH Zurich found that auto-generated context files make agents worse. That shows auto-generation is useless, not context files. A useful context file records where the model fails your project. 2 min readShort post
  9. Context management matters more than picking the model Letting developers pick a model solves the wrong problem. The real constraint for coding agents is context, and AMP answers it with sub-agents, two working modes and fewer, sharper tools. 1 min readShort post
  10. What context engineering looks like in practice The gap between mediocre and strong agent output comes from how you instruct the agent, not from the model. Concrete practices across three layers: prompting, context and verification. 1 min readShort post
  11. Research, plan, implement keeps coding agents out of the dumb zone A coding agent gets worse the longer a session runs. Research, plan and implement in separate, compacted steps, use sub-agents to control context, and put human effort where mistakes cost the most. 2 min readShort post
  12. A good CLAUDE.md describes how to think, not the project The default CLAUDE.md lists the stack and the commands, and it shapes nothing. The useful ones set philosophy, rules, protocols and principles for how the agent works. 1 min readShort post
  13. Most agent failures are context problems, not prompt problems Prompt engineering is how you ask. Context engineering is what the model sees. Eight practices, the symptoms of a badly built context and a four-question audit for the window. 2 min readShort post
  14. Agents fail from amnesia: context as a living playbook Agent failures are context failures. The ACE framework treats context as a playbook that grows through small updates instead of rewrites, and small open models gain the most from it. 2 min readShort post
  15. Onboard your AI assistant like a junior developer Teams spend weeks onboarding a junior developer and minutes onboarding their AI assistant. Both need the same thing: context, standards, and patience. 2 min readShort post
  16. Reduce and delegate: two ways to keep an agent's context focused A context window is not infinite RAM. First cut what never belongs in it, then spread the rest across sub-agents and context bundles so long tasks keep their focus. 3 min readShort post

Go deeper

Other topics