AI Garage Jargons
Decision Model
A model designed to make structured judgments or choose between possible actions, returning scores or probabilities instead of primarily generating open-ended text.
Use Cases
- Routing requests to the right workflow
- Checking whether an action meets a policy
- Scoring or ranking possible decisions
ELI5
A language model is often asked what to say next. A decision model is asked which option to choose, whether something is true, or how strongly something scores.
Why you're hearing about it now
Decision models are becoming easier to use inside normal AI stacks. Ollama now exposes Jev-style decision models through a dedicated API and supports Tev1 models built for fast classification and structured judgments.
Why it matters
Agents often need many small, repeatable judgments. A specialized decision model can make those steps more explicit and structured instead of asking a general-purpose LLM to generate an answer every time.
AI Garage example
In an assistant like Shushi, a decision model could sit before the main language model and judge things such as: Is this message asking for a calendar action? Does the assistant have enough information to act? Should it reply, ask a follow-up question, or do nothing? The language model can then handle the parts that actually need language generation.
Go deeper
Last researched: 2026-09-30