Attention: Ask Attention V2

Ask Attention a question across chosen conversations or a deal, optionally summarized with timestamps.

Tool ID: attention_ask_attention_v2

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(
  'attention_ask_attention_v2',
  {
    "conversations_ids": [
      "conversations_123"
    ],
    "deal_id": "deal_123",
    "prompt": "example"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute attention_ask_attention_v2 --input '{
  "conversations_ids": [
    "conversations_123"
  ],
  "deal_id": "deal_123",
  "prompt": "example"
}' --json

Example response

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

{
  "data": [
    {
      "output": "example",
      "conversation_id": "conversation_123",
      "error": "example"
    }
  ]
}

Use deepline describe attention_ask_attention_v2 --json for the latest machine-readable contract.

Input reference

Analyzes conversations or prompts to provide insights and attention points. This endpoint helps identify key information, sentiment, and important details in the provided content.

Name	Type	Required	Default	Details
`payload.include_timestamps`	`boolean`	No	—	When true, return timestamped segments (start/end seconds + excerpt) for each conversation alongside the textual answer.
`payload.summarize`	`boolean`	No	—	When true, synthesize all per-conversation outputs into a single combined response appended with conversation_id “summary”.
`payload.conversations_ids`	`array`	Yes	—	—
`payload.deal_id`	`string`	Yes	—	—
`payload.prompt`	`string`	Yes	—	—

Output reference

Standard tool result payload.

Name	Type	Required	Default	Details
`result.data`	`array`	Yes	—	Provider response payload.
`result.data[].output`	`string`	Yes	—	—
`result.data[].conversation_id`	`string`	Yes	—	—
`result.data[].error`	`string`	Yes	—	—
`result.data[].segments`	`array`	No	—	Optional timestamped segments relevant to the answer (present when include_timestamps=true).
`result.data[].segments[].start_sec`	`number`	No	—	Start time in seconds
`result.data[].segments[].end_sec`	`number`	No	—	End time in seconds
`result.data[].segments[].text`	`string`	No	—	Transcript excerpt for this segment
`result.data[].title`	`string`	No	—	Conversation title
`result.meta`	`object`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: fixed (per call).
Estimated Deepline credits: 0 per pricing unit.
Provider-native pricing may still exist outside Deepline credit billing.

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation