> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.ada.cx/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ada.cx/_mcp/server.

# get_ada_metric

Retrieves performance metrics and conversation-level metadata for the AI Agent.

## Example prompts

* "What's our CSAT this week?"
* "Show my AR and volume for the last 7 days."
* "How is my AR this week compared to last week?"
* "What's our containment rate trend for the last 30 days?"

## Parameters

| Parameter     | Type   | Required | Description                                                                                                                                       |
| ------------- | ------ | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `metric_type` | string | Yes      | The metric to retrieve. See supported values below.                                                                                               |
| `start_date`  | string | Yes      | Start date in `YYYY-MM-DD` format.                                                                                                                |
| `end_date`    | string | Yes      | End date in `YYYY-MM-DD` format.                                                                                                                  |
| `filters`     | array  | No       | Array of filter objects from [`get_available_filters`](/mcp/tools/get-available-filters). Each filter has `type`, `operator`, and `value` fields. |

### Supported metric types

| `metric_type` value           | Description                                                                                             |
| ----------------------------- | ------------------------------------------------------------------------------------------------------- |
| `resolution_rate`             | Percentage (0–100) of automatically resolved conversations.                                             |
| `csat_rate`                   | Percentage (0–100) customer satisfaction.                                                               |
| `conversation_volume_engaged` | Count of conversations where the customer actively engaged.                                             |
| `conversation_volume_opened`  | Count of conversations where a greeting was presented, including those without active engagement.       |
| `containment_rate`            | Percentage (0–100) of conversations not escalated to a human agent.                                     |
| `containment_volume`          | Count of conversations not escalated to a human agent.                                                  |
| `conversation_summaries`      | Up to 250 conversation records with ID, inquiry summary, resolution status, reason, and dashboard link. |
| `avg_handle_time`             | Average time in seconds customers spent with the AI Agent for contained conversations.                  |
| `avg_handle_time_agent`       | Average time in seconds customers spent with live agents after escalation.                              |

## Response

Returns an object with `metric_type` and `value`.

When using `conversation_summaries`, per-conversation metadata includes:

| Field                         | Description                                                                  |
| ----------------------------- | ---------------------------------------------------------------------------- |
| `conversation_id`             | Unique identifier for the conversation.                                      |
| `timestamp`                   | Earliest engagement time.                                                    |
| `customer_inquiry_summary`    | AI-generated summary of what the customer was asking about.                  |
| `automated_resolution_status` | `"Resolved"` or `"Unresolved"` by automation.                                |
| `automated_resolution_reason` | Explanation for why the conversation received its resolution classification. |
| `conversation_url`            | Link to the conversation in the Ada dashboard.                               |