Tutorials

Field notes on RAG, evals, agents, and LLM cost.

Human-in-the-Loop That Ships: Approvals, Interrupts, and Resume in LangGraph

October 19, 2026

An approval step is not a confirm dialog bolted onto an agent. It is a durable pause, a decision record, and a resume path that has to survive a deploy. Here is how we build them.

Capacity Planning for LLM Apps: Rate Limits, Concurrency, and the Queue You Already Have

October 12, 2026

Your app does not fall over at high load because the model is slow. It falls over because nothing in the stack bounds concurrency, and provider 429s arrive as user-visible errors. Here is how to size, queue, and degrade on purpose.

Parsing PDFs for RAG: Layout, Tables, and the Pages Your Pipeline Silently Drops

October 5, 2026

Retrieval quality has a floor set by your parser. How to audit extraction, route documents by class, keep tables intact, and gate parse quality at ingest.

Long-Term Agent Memory: What to Write, What to Read, and What to Forget

September 28, 2026

Cross-session memory is a small database your model writes without review. Split it by type, write on a decision instead of every turn, read narrowly, and measure interference as well as recall.

Subagents Without the Sprawl: When to Split a LangGraph Agent, and What It Costs

September 21, 2026 · TokenTailors

Multi-agent architectures are the default answer right now. Most teams need one or two subagents, not a org chart. Here is how to decide, and how to keep the split from eating your latency and your debuggability.