LLM Cost

You'll learn how to calculate what a merged, lasting change really costs when an AI agent does the work, and two cheap ways to bring that cost down without switching models.

You'll learn how to choose an open-weight or closed model for each role in an agent system by checking how far its errors spread, how many calls it makes, and whether its output can be checked automatically.

You will learn how to measure where tokens go in an orchestrator-plus-sub-agents fleet, and how to cut re-read context with cache-friendly prompt prefixes, a shared context ledger and decision-based handoffs.

You will learn how to model, measure and reduce the tokens each agent spends reading, validating and summarising the same shared data, and how to price that spend next to your warehouse bill.

You'll learn how to measure prompt cache hits in a coding agent harness, and how to fix the things that quietly break caching: volatile values in the system prompt, shifting tool lists, shared CLAUDE.md edits, aggressive compaction and badly placed breakpoints.

You'll learn how to measure agent cost per accepted change instead of per token, audit your traces for the retry loops that inflate spend, and cut those loops with richer first-attempt context, a planner/executor model split and explicit stop conditions.

You'll learn to route each agent step to a cheap or frontier model based on what a mistake would cost and whether anything catches it, rather than on how hard the task looks.

A billing anomaly forced us to trace one request through a reasoning loop with twelve hidden calls inside it — and exposed the blind spot every API gateway has the moment your agents start calling each other behind its back.

Your subagents are re-planning your tasks mid-execution, off the books, and the constraint that mattered most is the first thing they drop.