Recipes

Six finished jobs, each with the labels, schema, thresholds and code already chosen.

A pattern is a shape you apply to your own problem. A recipe is a finished job. Each page below names the capability, the exact labels or schema, the thresholds, and the code that ties them together.

Pick a recipe by the problem

RecipeThe jobCapabilities used
Support ticket triageRoute, prioritise, and flag an inbound ticket with three calls.classify, rate, yes-no
Invoice extraction with verificationPull a typed invoice record, then prove the critical fields.extract, verify
Content moderationScore harm, hard-flag the clear cases, send the rest to a person.rate, yes-no
RAG passage filteringDrop retrieved passages that do not answer the question.yes-no
PII detectionFind personal data and its offsets, then redact.entities
Taxonomy classificationWalk a deep label tree one level at a time.classify

The recipes

By capability

Use this index when you already know the capability and want a worked example.

By input type

Your inputStart here
A short message from a personSupport triage
User-generated posts or commentsContent moderation
A scanned or parsed documentInvoice extraction
Retrieved chunks from a vector storeRAG passage filtering
Free text that may hold personal dataPII detection
Text against a label tree of hundreds of labelsTaxonomy classification

Every recipe runs against https://api.milliseconds.ai as written. No API key is required during the launch period.

Before you copy one

Three things change per deployment. Read them once, then adapt each recipe.

  1. Your label and statement wording drives accuracy. Writing good statements and labels gives the rules.
  2. The thresholds in each recipe are starting points, not defaults. Set your own bands with thresholds and confidence routing.
  3. A text holds at most 20,000 characters, and texts holds at most 32 items. Limits and rate limits lists every other field limit.