Almost every best practice for coding agents comes from one constraint: the context window fills up fast, and quality drops as it fills. Learn the smart zone and the dumb zone, why fresh sessions beat long ones, and the four moves of context engineering.
Key takeaways
- The context window is the agent's working memory. It doesn't learn as it goes; you program that memory directly.
- Quality degrades long before the window is full. Treat roughly the first 40% as the smart zone.
- A long session full of failed attempts poisons the trajectory. A fresh session with a better prompt usually wins.
- Write important state to files, start fresh often, and load context just in time instead of up front.
- Context engineering has four moves: write it down, select what's relevant, compress, and isolate.
Try it with your agent
In a long session, before you clear it:
Summarize this session for a fresh agent who knows nothing: the goal, decisions made, what failed and why, the files that matter, and the exact next step. Under 200 words. Save it to notes/handoff.md.
Transcript
Intro
If you remember one lesson from this course, make it this one. Almost every best practice for working with coding agents comes from a single constraint.
The constraint
Anthropic's own guide to Claude Code says it plainly. Most best practices are based on one constraint: the context window fills up fast, and performance degrades as it fills.
Working memory
Karpathy offers a helpful picture. The model is like a CPU. The context window is its RAM, a small working memory. And unlike a new colleague, the model doesn't get smarter as it works with you. So you are the operating system, deciding what goes into that memory.
Smart zone, dumb zone
Here's the catch. Quality doesn't hold steady until the window is full. Dex Horthy calls the early part the smart zone. Past it comes the dumb zone, where the agent forgets instructions and contradicts itself. His rule of thumb for beginners: try to stay under about forty percent, and start wrapping up around sixty.
You'll recognize the dumb zone when you see it. Deep into a long session, the agent starts trying more and more extreme things to make a test pass. Dex's favorite example: let me just delete your env file and try again. That's your cue to stop.
What poisons context
Size isn't the only problem. Dex lists four things that matter in a context window. Its size. Its quality, meaning wrong or outdated information. What's missing. And the trajectory, the history of what the agent has done. Models continue patterns, so a history full of mistakes and corrections invites more mistakes.
He describes it from the model's point of view. If I read the history, I should probably make another mistake, so the human can yell at me. When a session reaches that point, more corrections won't help.
Fresh beats long
Which leads to the most practical habit in this course. Anthropic's guidance: if you've corrected the agent twice on the same thing, clear the session and start over with a better prompt that includes what you learned. A clean session with a better prompt almost always beats a long one full of corrections.
Hand off, then clear
Here's how to restart without losing progress. Ask the agent to summarize the session for a fresh agent: the goal, what was decided, what failed, which files matter. Review it, clear, and paste it in. As Brendan O'Leary says, AI is really great at writing prompts for AI.
Clear or compact
What about compaction, where the agent summarizes itself automatically when the window fills? It works, but it's lossy, and it decides what to forget on its own. Matt Pocock's advice: clear should be your default. Compact only when you want to keep the gist. Better yet, write the important state to a file before you need to.
Four moves
Lance Martin sums up context engineering in four moves. Write things down outside the window, in notes and plans. Select only what's relevant for this step. Compress what you keep. And isolate work in separate contexts, like subagents, so one task doesn't pollute another. We'll use all four throughout the course.
Quick check
Quick check. You've corrected your agent three times on the same bug, and it keeps making it. What's the best move? Tap your answer.
Try it
Practice the handoff. Next time a session feels long, paste this prompt, save the summary, clear the session, and start again from the summary. Notice how much sharper the agent feels.
Recap
Recap. Context is the agent's working memory, and quality drops as it fills. Stay in the smart zone. When a session goes bad, hand off and start fresh. And write, select, compress and isolate. Next, the core workflow that puts all of this to work: explore, plan, implement, verify.