On this page
Read
The useful mental model
A decision model is a gate in front of an action. It evaluates a bounded question and returns a structured judgment, so the rest of the system can follow a clear route.
In plain English
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.
Where builders use it
- 01Routing requests to the right workflow
- 02Checking whether an action meets a policy
- 03Scoring or ranking possible decisions
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.
Why now
Decision models are becoming easier to use inside normal AI stacks. Since version 0.35, Ollama has exposed Jev-style decision models through a dedicated endpoint, with local models for bounded choices, true-or-false judgments, and rubric scores.
A common misconception
“A decision model is just another name for a language model.”
A language model is commonly used to generate open-ended text. A decision model is used for bounded judgments such as choosing, ranking, scoring, or checking.
See
See the mental model
The visual is generated from the same structured knowledge as the written explanation.
An incoming Shushi message passes through a decision model and is routed to a calendar action, follow-up question, generated reply, or no action.
Watch
Watch the explainer
A short visual explanation built from the same reviewed knowledge object.
Decision Model: a structured judgment before action
See how a scheduling assistant scores four allowed options, returns a result that is only data, passes it through explicit workflow checks, changes the calendar, and only then asks a language model to write the confirmation.
Read transcript
A learner asks a scheduling assistant to move Friday's workshop to four. It could reply right away, but replying is not the same as deciding. First, a decision model steps in. It scores a fixed set of options and picks one. Here, the four options are changing the calendar, asking a question, writing a reply, or doing nothing. The scores settle, and the calendar option wins. That result is just data. It does not change anything yet. Ordinary workflow code checks the event, the person's permission, and the policy. Only then does the calendar change. Now a language model can write the confirmation. A decision model makes one narrow judgment. Your workflow decides what that judgment is allowed to do.
Builder example
Route a Shushi request before generation
Shushi receives a message that may require a calendar action, a follow-up question, a normal reply, or no action.
Failure
Sending every message directly to the main language model mixes routing decisions with language generation and makes the action boundary harder to inspect.
Intervention
A decision model first scores the message against the allowed routes and returns the selected route as structured data.
Observable result
Shushi can invoke the language model only when language is needed and handle the remaining routes with explicit workflow logic.
Sources
Go deeper
- Ollama now supports Jev-style decision models
- Ollama - Tev1 decision model and API reference
- Together AI - Tev1 training and evaluation repository
Last researched 11 October 2026