Build an agent, then see what it cost
Each tutorial builds a working agent in a named framework, pinned to a version, with runnable code. The agent stands on its own — the cost instrumentation comes last, once there is something to measure.
LangGraphopenai15 min
Per-agent cost in a LangGraph supervisor loop
A supervisor that delegates requirements to specialists in LangGraph 1.x on GPT-4.1, then four cost rows and a blocking budget on the role that multiplies.
2 September 2026
LangChainopenai14 min
Per-role cost in a LangChain coding agent
A triager, parallel file readers, an editor and a reviewer in LangChain 1.x on GPT-4.1, then per-agent cost and a blocking budget on the role that fans out.
12 August 2026
LangGraphanthropic15 min
Cost per role in a LangGraph AI scientist that fans out
A planner, hundreds of parallel probes, a referee and a synthesist in LangGraph 1.x on Claude, instrumented into four cost rows with a budget on the probes.
6 August 2026
LangChainanthropic12 min
Cost per agent in a LangChain incident-brief pipeline
A planner, parallel analysts, a critic and a writer in LangChain 1.x on Claude, then per-agent cost and a blocking budget on the role that multiplies.
5 August 2026