Jev 1.13 jaggedness (known limitations)

Open on Official

More like this

• Cookbook

  Cookbook: Agent skill suggestion

  Picks which agent skill to load for a given task by scoring candidate skills against the current state.

  TypeSafe AIOpenCookbook: Agent skill suggestion on docs.typesafe.ai

  ChoiceScoreAgent routing and skill selectionTyped tool dispatch
• Cookbook

  Cookbook: Autoresearch feature discovery

  Generates and tests candidate features over a dataset by scoring each one with Jev.

  TypeSafe AIOpenCookbook: Autoresearch feature discovery on docs.typesafe.ai

  ScoreNoulFeature extraction for machine learningComposite scoring
• Cookbook

  Cookbook: Batching parallel questions

  Shows how to send many questions about the same state in a single request instead of issuing one call per question.

  TypeSafe AIOpenCookbook: Batching parallel questions on docs.typesafe.ai

  ChoiceScoreNoul
• Cookbook

  Cookbook: Classification using confidence

  Uses the confidence value returned with Choice and Score answers to decide when to act automatically and when to escalate.

  TypeSafe AIOpenCookbook: Classification using confidence on docs.typesafe.ai

  ChoiceScoreConfidence-gated actionsHierarchical classification
• Cookbook

  Cookbook: Classifying RAG passages

  Filters retrieved passages for relevance before they reach the generation step of a RAG pipeline.

  TypeSafe AIOpenCookbook: Classifying RAG passages on docs.typesafe.ai

  NoulScoreRAG passage filtering
• Cookbook

  Cookbook: Date extraction

  Extracts dates from text using pre-parsing plus Choice questions, working around the documented weakness of jev-1.13 at date arithmetic.

  TypeSafe AIOpenCookbook: Date extraction on docs.typesafe.ai

  ChoiceStructured extraction