> For the complete documentation index, see [llms.txt](https://docs.360dialog.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.360dialog.com/docs/mba/api-ref/insights/get-conversation-insights.md).

# Get conversation insights

Retrieve how many conversations the AI agent handled over a date range, and how many are currently handed to the business awaiting a reply. Counts are per conversation, not per message. These are the same figures the business sees in their own agent summaries.

```json
{"openapi":"3.1.0","info":{"title":"Business Agent API","version":"1.51.5"},"tags":[{"name":"Insights","description":"Endpoints for retrieving the agent's usage insights"}],"servers":[{"description":"Production server","url":"https://waba-v2.360dialog.io"}],"security":[{"D360-API-KEY":[]}],"components":{"securitySchemes":{"D360-API-KEY":{"description":"API Key for Messaging API authentication. Send your API key in the D360-API-KEY header.","in":"header","name":"D360-API-KEY","type":"apiKey"}},"schemas":{"insights.ConversationInsightsResponse":{"description":"The conversation insights for the requested range","properties":{"data":{"description":"A single row covering the requested range. An array so a future per-day breakdown does not break callers","items":{"$ref":"#/components/schemas/insights.BizAIOmniChannelConversationInsights"},"type":"array","uniqueItems":false}},"required":["data"],"type":"object"},"insights.BizAIOmniChannelConversationInsights":{"description":"Conversation and handoff counts for the requested range","properties":{"ai_handoffs":{"$ref":"#/components/schemas/insights.BizAIOmniChannelConversationInsightsMetric","description":"Conversations currently handed from the AI agent to the business and still awaiting a business reply. This is a snapshot of the present moment, not a count over the requested range: it is the same figure whatever start_date and end_date you send. A conversation drops out of it once the business replies. Present only when the metric was requested"},"ai_threads":{"$ref":"#/components/schemas/insights.BizAIOmniChannelConversationInsightsMetric","description":"Conversations the AI agent replied in at least once between start_date and end_date, counted once however many messages each contains. Present only when the metric was requested"}},"type":"object"},"insights.BizAIOmniChannelConversationInsightsMetric":{"description":"A single conversation insights metric","properties":{"count":{"description":"The number of conversations this metric counts. What it counts, and whether the requested date range applies to it, is described on the metric itself","type":"integer"}},"required":["count"],"type":"object"},"insights.StandardError":{"description":"Standard error response for Meta Business Agent endpoints","properties":{"detail":{"description":"Human-readable explanation of the error","type":"string"},"status":{"description":"HTTP status code","type":"integer"},"title":{"description":"Short, human-readable summary of the problem","type":"string"},"type":{"description":"A URI reference identifying the problem type","type":"string"}},"type":"object"}}},"paths":{"/insights/conversations":{"get":{"description":"Retrieve how many conversations the AI agent handled over a date range, and how many are currently handed to the business awaiting a reply. Counts are per conversation, not per message. These are the same figures the business sees in their own agent summaries.","operationId":"get-conversation-insights","parameters":[{"description":"Meta Business Agent API version","in":"header","name":"X-API-Version","schema":{"enum":["2.0.0"],"type":"string"}},{"description":"First day to include, as YYYY-MM-DD in the business time zone. The boundary is inclusive.","in":"query","name":"start_date","required":true,"schema":{"type":"string"}},{"description":"Last day to include, as YYYY-MM-DD in the business time zone. The boundary is inclusive. start_date and end_date may span at most 90 days, counting both the first and last day.","in":"query","name":"end_date","required":true,"schema":{"type":"string"}},{"description":"Which metrics to return. Defaults to all of them. Requesting only what you need is worthwhile: each metric costs a separate scan of the business's conversations.","in":"query","name":"metrics","schema":{"items":{"enum":["ai_handoffs","ai_threads"],"type":"string"},"type":"array"},"style":"form","explode":false}],"responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.ConversationInsightsResponse"}}},"description":"The conversation insights for the requested range"},"400":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.StandardError"}}},"description":"Bad request"},"401":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.StandardError"}}},"description":"Unauthorized"},"403":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.StandardError"}}},"description":"Forbidden"},"404":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.StandardError"}}},"description":"Not found"},"429":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.StandardError"}}},"description":"Too many requests"},"500":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/insights.StandardError"}}},"description":"Server error"}},"summary":"Get conversation insights","tags":["Insights"]}}}}
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.360dialog.com/docs/mba/api-ref/insights/get-conversation-insights.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.