Decision

Use System One to classify text, answer yes/no questions, or score text against a rubric.

See the full list of decision models.

Setup

Start Ollama v0.35.0 or later, then download Nimble:

ollama pull nimble

Nimble, Tev1, Clef, and Clef Flash are decision models. The Clef models can also judge images and require v0.35.1 or later.

Local requests do not need an API key.

Ask from the terminal

ollama run answers questions about a state: text or JSON, piped in or given after the model name. Ask each question with --ask. It is answered yes or no, unless you follow it with labels to choose from (--choice) or levels to score it on (--level).

# Ask a yes/no question
ollama run nimble --ask "Is a refund being requested?" < ticket.txt

# Choose a label
ollama run nimble --ask "Which team should handle this?" \
  --choice billing="Payments and refunds" \
  --choice technical="Software problems" < ticket.txt

# Score on a scale, from the lowest level to the highest
ollama run nimble --ask "How urgent is this?" \
  --level "Routine" \
  --level "Soon" \
  --level "Immediate" < ticket.txt

# Ask several questions at once
ollama run nimble --ask "Is a refund being requested?" \
  --ask "Which team should handle this?" \
  --choice billing="Payments and refunds" \
  --choice technical="Software problems" \
  --ask "How urgent is this?" \
  --level "Routine" \
  --level "Soon" \
  --level "Immediate" < ticket.txt

# Use a JSON file as the state, and refer to its fields in backticks
ollama run nimble --ask 'Is a refund being requested in `body`?' < ticket.json

# Judge an image with Clef
ollama run clef ./receipt.png --ask "Is this a restaurant receipt?"

# Print the full response
ollama run nimble --ask "Is a refund being requested?" --format json < ticket.txt

Each answer prints on its own line. A yes/no answer shows the likelier answer and its probability, a label shows its probability, and a score shows the most likely level, its probability, and the score on the scale:

Is a refund being requested?    yes      97%
Which team should handle this?  billing  91%
How urgent is this?             Soon     64%  1.2 / 2

Without a state, ollama run nimble opens an interactive prompt. Your first message is the state, and after that each line is a yes/no question about it, so you can paste several at once; /clear starts over. With --ask, each message is a new state to answer those questions about.

Choose a label

Put your input in state and describe the possible answers in criteria:

curl http://localhost:11434/v1/systemone \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "nimble",
    "state": "Our checkout has returned 500 errors since 9am.",
    "questions": {
      "label": {
        "type": "choice",
        "instructions": "Which label fits this ticket?",
        "criteria": {
          "billing": "Payments and refunds",
          "bug": "Software errors",
          "account": "Login and account access"
        }
      }
    }
  }'

Example response:

{
  "model": "nimble",
  "answers": {
    "label": {
      "type": "choice",
      "choice": "bug",
      "probabilities": {"billing": 0.0125, "bug": 0.9781, "account": 0.0093},
      "confidence": 0.8906
    }
  },
  "usage": {"input_tokens": 174, "output_tokens": 1}
}

Judge an image

Clef and Clef Flash read images alongside the state. Send base64-encoded PNG, JPEG, or WebP files in images; they are shared by all questions, in request order. URLs and data URLs are not accepted. state is still required — it holds the context for the decision.

curl http://localhost:11434/v1/systemone \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "clef-flash",
    "state": "A user took this screenshot and wants to know what it shows.",
    "images": ["<base64-encoded image>"],
    "questions": {
      "has_ollama": {
        "type": "noul",
        "instructions": "Does this image contain Ollama?"
      },
      "app": {
        "type": "choice",
        "instructions": "Which application is shown in this screenshot?",
        "criteria": {
          "vscode": "Visual Studio Code",
          "terminal": "A terminal emulator",
          "browser": "A web browser",
          "other": "A different application"
        }
      }
    }
  }'

Example response:

{
  "model": "clef-flash",
  "answers": {
    "has_ollama": {"type": "noul", "noul": 0.959},
    "app": {
      "type": "choice",
      "choice": "vscode",
      "probabilities": {"vscode": 0.966, "other": 0.017, "browser": 0.010, "terminal": 0.007},
      "confidence": 0.868
    }
  },
  "usage": {"input_tokens": 677, "output_tokens": 0}
}

Use a cloud model

Clef also runs in Ollama's cloud with a paid plan or purchased usage credits. Add :cloud to the model name to send the request through a local Ollama server, v0.40.5 or later, signed in to ollama.com:

curl http://localhost:11434/v1/systemone \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "clef:cloud",
    "state": "Our checkout has returned 500 errors since 9am.",
    "questions": {
      "urgent": {
        "type": "noul",
        "instructions": "Does this ticket need attention within the hour?"
      }
    }
  }'

Or call ollama.com directly with an API key:

curl https://ollama.com/v1/systemone \
  -H "Authorization: Bearer $OLLAMA_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "clef",
    "state": "Our checkout has returned 500 errors since 9am.",
    "questions": {
      "urgent": {
        "type": "noul",
        "instructions": "Does this ticket need attention within the hour?"
      }
    }
  }'

Cloud requests accept up to 64 questions, named with up to 100 ASCII letters, digits, _, ., or -, and up to 4 images of at most 4 MiB and 16 megapixels each, 8 MiB in total. Input is limited to the model's 65,536-token context window; longer input is rejected. Usage is billed per input token at the listed price.

Question types

For the urgency criteria below:

score = 0 × P(Routine) + 1 × P(Soon) + 2 × P(Immediate)

For choice and score, confidence measures how strongly the model favors one answer over the others, from 0 to 1. A higher value does not guarantee the answer is correct.

Ask multiple questions

Combine question types in one request. Here, both questions use the same ticket:

curl http://localhost:11434/v1/systemone \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "nimble",
    "state": {"ticket": "I was charged twice. Please refund the extra payment."},
    "questions": {
      "refund": {
        "type": "noul",
        "instructions": "Is the customer requesting a refund?",
        "criteria": {
          "false": "No refund is requested",
          "true": "The customer requests a refund"
        }
      },
      "urgency": {
        "type": "score",
        "instructions": "How urgently does this ticket need a response?",
        "criteria": [
          "Routine: no time pressure",
          "Soon: a customer is inconvenienced",
          "Immediate: a critical service is unavailable"
        ]
      }
    }
  }'

This returns a refund probability of 0.9989 and an urgency score of 0.8308 on the 0–2 scale (rounded). Results can vary with the model and configuration.

See the API reference for request fields, limits, errors, and token usage.