Get agent conversation topics

GET

/v1/convai/agents/:agent_id/topics

GET

/v1/convai/agents/:agent_id/topics

$ curl https://api.elevenlabs.io/v1/convai/agents/agent_id/topics

1 {
2   "topics": [
3     {
4       "topic_id": "string",
5       "label": "string",
6       "description": "string",
7       "conversation_count": 1,
8       "parent_topic_id": "string",
9       "x_2d": 1.1,
10       "y_2d": 1.1,
11       "metrics": {
12         "conversation_count": 0,
13         "sentiment": {
14           "sentiment": {
15             "count": 0,
16             "sum": 0,
17             "min": 1.1,
18             "max": 1.1
19           },
20           "frustration": {
21             "count": 0,
22             "sum": 0,
23             "min": 1.1,
24             "max": 1.1
25           },
26           "positive_count": 0,
27           "neutral_count": 0,
28           "negative_count": 0
29         },
30         "evaluation_criteria": [
31           {
32             "criteria_id": "string",
33             "success_count": 0,
34             "failure_count": 0,
35             "unknown_count": 0
36           }
37         ]
38       },
39       "success_rate": 1.1
40     }
41   ],
42   "window_start_unix_secs": 1,
43   "window_end_unix_secs": 1,
44   "aggregated_run_count": 0,
45   "has_more": false,
46   "next_cursor": "string"
47 }

Returns the latest topic discovery run results for a given agent.

Path parameters

agent_idstringRequired

ID of the agent

Query parameters

page_sizeinteger or nullOptional1-100

Number of top-level topic groups to return.

sort_byenumOptional

Column to rank topics by. Use conversations for volume, sentiment with sort_direction=asc for the most negative topics, and frustration with sort_direction=desc for the most frustrated ones. Topics with no score are always ranked last.

Allowed values:

sort_directionenumOptional

Direction to sort topics.

Allowed values:

from_unix_secsinteger or nullOptional

Start of the window to view topics for. When set with to_unix_secs, the completed daily topic-discovery runs in the range are aggregated together, so the window scopes the metrics as well as the topic set. Floored to the start of its UTC day because runs cover whole UTC days; aggregated_run_count reports how many runs were summed. Omit both bounds to get the single latest run.

to_unix_secsinteger or nullOptional

End of the window to view topics for.

include_evaluation_criteriabooleanOptionalDefaults to true

Include the per-criteria evaluation breakdown on each topic’s metrics. Pass false to drop it: it dominates the payload and the weighted success_rate is returned either way.

cursorstring or nullOptional

Used for fetching next page. Cursor is returned in the response.

Response

Successful Response

topicslist of objects

window_start_unix_secsinteger

window_end_unix_secsinteger

aggregated_run_countintegerOptionalDefaults to 0

Number of daily topic-discovery runs the returned metrics were summed over.

has_morebooleanOptionalDefaults to false

next_cursorstring or nullOptional

Errors

422

Unprocessable Entity Error

Path parameters

Headers

Query parameters

Response

Errors