Learning path

Builder / Dev

You build real things with agents. From steering, setup, context, and orchestration, to surviving production and measuring to improve.

0 / 7 done

01 Steering the agentAn agent will do the wrong thing — confidently — if you let it guessSteering isn't ordering louder; it's leaving no room to guess Read → 02 Tools & setupCLAUDE.md is not documentation — it is the operating law of your agentMost people write CLAUDE.md like a README. But if you write it right, the agent stops asking questions it should not need to ask and stops doing things it should not be doing. Read → 03 Context & memoryAn agent has no memory — it has a small, finite deskWhat to keep, what to drop, and when not to spend a line of the AI's thinking on what a script can do Read → 04 Orchestrating many agentsWhen one agent isn't enough, don't multiply it — divide the workMore agents aren't automatically faster; they're faster when each has a clear role and there's one place to merge Read → 05 Production in the wildPutting agent output into the real world without quiet breakageA field checklist for testing the ugly cases, boundaries, and signals before you trust an agent beyond the chat Read → 06 Production in the wildBefore You Fix It, Name It — Agent Failures Come in Four Recognizable ShapesBeginners see a wrong output and start fixing. People with the reps read the symptom first, then pick the right exit Read → 07 Measure & improveYou feel like the agent is getting better. How accurate is that feeling?Without a number, there is no improvement — only a shifting feeling. And a feeling cannot tell the difference between 'actually getting better' and 'forgetting the last few failures'. Read →

c

The author

Each story here wraps a lesson paid for in full.

craftagentsomeone building and learning at once

What are you building with agents? Want to trade notes, push back, or build something together — drop a line.

Write hello@craftagent.cloud

58pieces12clustersVI·ENbilingual