Who thinks, who works, who just runs: how do you build a team of AI models?
Using one AI model for every task costs more than it delivers. A model team splits the roles: one thinks, one works, one just runs once the path is drawn clearly enough. Which model is enough depends on the task. The strongest model available to me right now, Fable, takes the role of strategist and thinker for me. It plans, breaks the task down and makes the decisions that need real context. A solid allrounder takes the role of the worker and carries out what the strategist lays out. A very cheap model takes the role of the pure executor, for subtasks that are described clearly enough. The pure executor only understands what has been chewed up clearly enough beforehand. Deciding a backend architecture or solving a problem from scratch, that is not something it can do. That is what the strategist is for: breaking the task down first so a simpler model understands it cleanly. Whoever does that breakdown well gets low cost and reliable results at the same time.
Why the breakdown of the task decides
The pure executor only understands what has been chewed up clearly enough beforehand. Deciding a backend architecture or solving a problem from scratch, that is not something it can do. That is what the strategist is for: breaking the task down first so a simpler model understands it cleanly. Whoever does that breakdown well gets low cost and reliable results at the same time.
What this means for your own model team
That takes some humility: not running every small thing through the most expensive model just because you can. Once you have found a way for a simpler model to solve a task reliably, you can write that way down as a short instruction. From then on the same task runs through the cheap model every time, without needing the strategist again.
On record
AI DeepDive "Agentic Mindset", August 2026.
- Three roles in the model team: the strongest model as strategist, an allrounder as worker, the cheapest model as pure executor
- Architecture decisions and open-ended problem solving stay with the strategist
- The daily mail review runs entirely on the cheap model
This note keeps growing
2026-09-02: Planted from the Agentic Mindset Deep Dive.