Volume VIII
Production Systems
Durable, observable, evaluated
Ship the simplest system that can be paused, resumed, traced, and scored. Durable graphs, human-in-the-loop as a tool, evals before architecture, and a ruthless list of anti-patterns.
- VIII.1Durable ExecutionAgents run longer than request timeouts. Checkpoint after every turn. Resume as a first-class API. LangGraph won production on this axis.6 min
- VIII.2EvaluationEvals are tests. promptfoo, DSPy, Langfuse datasets, and the Hugging Face agents course all assume you have a golden set before you have an architecture.7 min
- VIII.3ObservabilityA trace is the loop laid out in time: prompts, tool I/O, token counts, costs, user id. Without it you cannot eval, debug, or bill.5 min
- VIII.4Choosing a FrameworkPick for the constraint you actually have. Durability, types, roles, code-act, TypeScript, Azure, Gemini, documents — each has a default. Do not pick for stars.8 min
- VIII.5Anti-PatternsThe field's repeating failures, collected from the 12-factor journey, Anthropic's warnings, and every framework README's implicit 'please do not'.7 min