1. Measure accuracy on your own data first
Decision models are not LLMs, and yours is the only data that decides whether they are good enough. Before you migrate anything, compare the engine against your current classifier on your labelled examples. We run this with you: send us the labelled set and your current classifier’s outputs, and you get back accuracy and cost for each engine next to your incumbent. If the engine loses on your data, stop there. You can also measure it yourself: write the labelled documents to a namespace, post the labels as outcomes, and read the judgment’s calibration report.2. Turn each prompt into a judgment
Most classification prompts map onto one of three types:
Move the prompt’s instructions into
question and criteria, and the parts of the record it reads into a context recipe. Prompts that sent the same record for five separate classifications become five judgments that share one recipe, which go to the engine as one request.
The engines cannot abstain. A choice judgment always gets a none_of_the_above escape option, and its probability comes back as escape_p. Use it where your prompt said “otherwise, answer other”.
3. Mirror your writes
Send every create, update and delete from your system of record to the write API.patch and append let you send only what changed, and writes are idempotent, so your sync can retry freely. Documents stay yours: Vainona is not your system of record. To load the records you already have, see import existing data.
Choose each judgment’s freshness policy. A judgment your pipeline ran on every change, whose results you filter on, is on_change. One you only show on a detail page can be on_read, which costs nothing until someone looks.