Steering the agent
4 pieces · bilingualMake it understand the right task before it acts — through command structure, forcing functions, and a clarify-first habit, not luck.
Every piece here falls into one of five clusters. All five are now open to read. This map shows you the whole terrain up front.
The thread through all five: an agent is a genius junior with amnesia — you manage it, you do not let it run loose.
Make it understand the right task before it acts — through command structure, forcing functions, and a clarify-first habit, not luck.
Memory is a finite resource: what to keep, what to drop, where to persist it — and when to let a script do the work instead of burning tokens on the AI.
When one agent isn't enough: split roles, hand off work, gather results — orchestration patterns so many agents run without stepping on each other.
Four human-control gates — plan · checkpoint · impact · verify — placed at the four moments an agent is most likely to fall on the life of one task.
Faceplants from the field — retold with every name and specific detail stripped, keeping only the general trap so you can dodge it first.