Loading
You have already built the easy version of this. HouseWarm shows a per-field confidence number, the source crop and the raw OCR text, and a human approves before anything downstream fires. That is one value, from one model call, in one gate. The thing the next job asks for is a different problem: a run that took eleven steps, called four tools, retried one of them, cost sixty cents, cited three documents, and changed two records, rendered so a reviewer can tell in four seconds whether to trust it, and in four minutes exactly where it went wrong. In this course you will learn the data shape first, then build the view against it, so the panel can show the runs people actually open it to see.
Start lesson one: The view comes second →
Almost every team builds that panel by drawing it first. This course does the opposite, and the ordering is the whole argument: learn the data shape before designing the view. A trace renderer designed against an imagined payload handles the happy path and quietly loses the retry, the parallel call, and the run that died at step seven. Those are the only runs anyone opens the panel to look at.
The whole four-module spine is registered so the lesson numbers never move. The first module (the data layer everything else renders) is written. Ask your teaching agent for the next one once <AgentTrace /> has a schema it can actually parse.
What the runtime actually emits, learned before a single pixel of the trace panel gets designed.
The four altitudes as one component family, from a one-line summary to the raw payload.
Tying a claim to its source, and saying how sure the system is without inventing precision.
The numbers a reviewer needs per step, and the roll-up the person paying for the run needs instead.
Every claim on these pages links to its source. If a source looks wrong or out of date, check the resource list and tell your teaching agent. The course is meant to be corrected.