Technical topic
AI cost engineering
Outcome units, request ledgers, model routing, caching, capacity, and the cost of failed attempts.
Questions answered
- How do I calculate cost per AI outcome?
A fully loaded outcome-ledger method that includes accepted, rejected, reversed, and reviewed AI work instead of dividing one provider invoice by request count.
- When should I route to a smaller or larger model?
A task-family routing experiment that compares model policies at equal quality, escalation, refusal, latency, cost, and serious-failure conditions.
Primary field guide
AI Cost Engineering — Token Economics, Model Routing, Caching, Capacity, and Cost per Outcome
Related books
Reusable resources
- Cost-per-outcome ledger (CSV)
- Agent evaluation task card (YAML)