Decision and extraction models for runtime

Sage2 extracts structured data and returns decisions with calibrated confidence. Discover the full capabilities of Sage2 below.

• 01Decide Request: POST /decide with the yes or no question “Does this message ask for a refund?” about a message that asks to refund a duplicate charge. Response: yes, probability of yes 0.999, 104.1 ms on the server.
• 02Stream Request: WS /v1/stream with the question “Does this need escalation to the on-call engineer now?”, then three appends to one session. Append 1: “Hi, one user on our team can't sign in.” Decision: no, probability of yes 0.009, 110.8 ms on the server. Append 2: “Now nobody in our EU workspace can sign in.” Decision: yes, probability of yes 0.991, 76.9 ms on the server. Append 3: “Checkout is failing for every customer and we are losing orders.” Decision: yes, probability of yes 0.999, 131.2 ms on the server.
• 03_Extract_ Request: POST /v1/extract with the text “I can pay $450/mo” and the money field monthly_limit. Response: 450 USD, 182.1 ms on the server.

POST/decide

{ "question": { "kind": "yesno", "id": "refund", "instructions": "Does this message ask for a refund?" }, "content": "Hi, I was charged twice for order #1048…" }

WS/v1/stream

→ { "type": "append", "text": "Hi, one user on our team can't sign in." }
→ { "type": "append", "text": "Now nobody in our EU workspace can sign in." }
→ { "type": "append", "text": "Checkout is failing for every customer and we are losing orders." }

POST/v1/extract

{ "content": "I can pay $450/mo", "extract": { "monthly_limit": { "type": "money", "definition": "the monthly limit" } } }

Choose the decision type to put intelligence at runtime.

Yes/NoChoiceScaleTagsSort

Define the question and criteria in natural language. Sage returns a structured result your code can use to select a tool, assign a category, evaluate a condition, or prioritize work.

Streaming is 3× faster and uses fewer tokens.

Open a streaming session, define your questions, and append text as it arrives. Sage retains the conversation or document server-side and reuses cached prefix computation, so your client sends new text without uploading the full history on every update.

Extract the values your runtime needs.

Define fields for the information your application needs. Sage turns natural language into typed values, including text, amounts, dates, and durations. Extract one value or every matching mention from a document.

How teams use Sage.

Leap turns study requests into learning tools with Sage

Leap uses Sage to recognize requests for flashcards, quizzes, and other study activities inside chat, then offers the corresponding native tool.

Capacitr uses Sage to save money on market analysis

Six decision points filter market information, determine when research is needed, and check proposed agent actions. Capacitr projects approximately 44% lower pipeline LLM spend.

PerpFlow cuts its agentic research workflow from 14 days to 12 hours with Sage

Claude Code delegates repeated market classifications to Sage. PerpFlow’s founder reports reducing elapsed research workflow time from 14 days to 12 hours.

Build with Sage2

Define the information your application needs and the decisions it must make. Test Sage on your own inputs and connect the results to your application logic.