Skip to lesson
Exit
Building AI-Native Workflows1 / 2

1 min lesson

Match the model to the task

Choose two examples from the table in "Match the model to the task" and explain what each teaches you to do.

Step 1 of 2

Match the model to the taskdon’t reach for the biggest by reflex

Route by difficulty: a small model handles the easy bulk, a large model handles the hard tail.

Task
Rename a symbol, format, mechanical edit
Tier
Small / fast
Why
Deterministic enough that a small model nails it cheaply.
Task
Localized bug fix with a failing test
Tier
Mid
Why
Needs reasoning but is well-scoped by the test.
Task
Cross-cutting refactor or migration plan
Tier
Large
Why
Wide context and harder reasoning justify the cost.

Tiering by task is the single biggest cost lever in most workflows.

Say it like this

“Fast, cheap and good don’t all come together, so I pick two per workflow and defend the third. For an overnight migration I trade latency: batched on a large model, run offline, because nobody is watching the clock at 3am. That buys high quality at a moderate bill. For an interactive edit someone is waiting on, I stream from a bigger model with rich context and accept the higher cost. Mechanical bulk goes to a small, fast model on tight context.”