Deepline Agent: Ai Evaluate - Deepline

Ask an AI model typed questions about a record and get structured answers back, such as scores or yes/no checks.

Tool ID: ai_evaluate

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'ai_evaluate',
  {
    "state": "California",
    "questions": {}
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute ai_evaluate --input '{
  "state": "California",
  "questions": {}
}' --json

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "status": "completed",
  "result": {
    "answers": {},
    "response": {
      "modelId": "model_123",
      "timestamp": "example"
    }
  },
  "usage": {
    "inputTokens": 123,
    "outputTokens": 123,
    "totalTokens": 123
  },
  "output": "example",
  "extracted_json": {}
}

Use deepline describe ai_evaluate --json for the latest machine-readable contract.

Input reference

Name	Type	Required	Default	Details
`payload.model`	`string`	No	`"typesafe-ai/jev"`	Case-sensitive provider-prefixed Vercel AI Gateway evaluation model id, for example “typesafe-ai/jev”. Copy the exact id from https://ai-gateway.vercel.sh/v1/models. Pattern: `^[a-z0-9][a-z0-9._-]/[a-z0-9][a-z0-9._-]$`.
`payload.state`	`unknown`	Yes	—	—
`payload.questions`	`record`	Yes	—	Questions by id, for example {“is_fit”: {“type”: “boolean”, “instructions”: “Is this company a fit?”}}. choice needs criteria as a map of choice to meaning. score needs criteria as an array of at least two levels.
`payload.providerOptions`	`record`	No	—	AI SDK providerOptions passthrough, namespaced by provider.

Output reference

Name	Type	Required	Default	Details
`result.status`	`"completed"`	Yes	—	—
`result.result`	`object`	Yes	—	—
`result.result.answers`	`record`	Yes	—	—
`result.result.rounding`	`record`	No	—	—
`result.result.response`	`object`	Yes	—	—
`result.result.response.modelId`	`string`	Yes	—	—
`result.result.response.timestamp`	`string`	Yes	—	—
`result.usage`	`object`	Yes	—	—
`result.usage.inputTokens`	`integer`	Yes	—	—
`result.usage.outputTokens`	`integer`	Yes	—	—
`result.usage.totalTokens`	`integer`	Yes	—	—
`result.meta`	`object`	No	—	—
`result.meta.model`	`string`	Yes	—	—
`result.output`	`string`	Yes	—	—
`result.extracted_json`	`record`	Yes	—	—

Deepline cost

Pricing model: provider_usage (provider usage).
Estimated Deepline credits: 0 per pricing unit.