Curriculum
Module 11
Cost, latency and caching
Where an agent loop burns money and how to stop it: where tokens go, prompt caching, model routing, latency in a loop, and circuit breakers.
5 lessons · 10 videos · 3h 3m- 11.01
Where the tokens actually go
Break a run down by token spend and find the step that dominates it.
- 11.02
Prompt caching
Structure a prompt so the stable half is cached and the bill drops.
- 11.03
Using a smaller model where it is enough
Route steps by difficulty instead of sending everything to the largest model.
- 11.04
Latency multiplies in a loop
Predict wall-clock for an N-step agent and find what to parallelise.
- 11.05
Budgets and circuit breakers
Cap what a single run can spend before it spends it.