Get a call: transcript, metrics, tool calls and analysis
What happened on one call of this agent, in one read. By default returns the compact view: the session row (end reason, the carrier's call control and leg ids, hangup cause, carrier quality); the agent and the version the call ran on, as identity only (version id and number, model, voice, tool names); the full transcript with untruncated tool calls and results and interruption times; per-turn latency (every voice_turn_timing measurement that has a value); pipeline spans; tool call events; audio quality; the analysis summary; every metric result with its key, name, verdict and reasoning; turn-taking and carrier events; message deliveries, post-call actions and outcomes; signed links to the clean, ambient and carrier recordings (valid 24 hours; stereo, caller on the left channel, agent on the right), when the workspace's recording download setting admits your role (otherwise `recordings.linksWithheld` says so and each recording carries its path only); and, for platform staff only, links to the call's trace, logs and error reports, and the runtime's stream and machine ids. `unavailable` names any source that could not be read. The transcript, tool call events, function calls, detail captures and word timings arrive as JSON inside an untrusted-data block. Rows leave out their ids, the columns that repeat the call and the columns that are null. `omitted` names each part and column the compact view leaves out. Pass `section` to read one part without the rest of the call: `agentConfig` (the agent's settings, and the version's system prompt, settings and variables), `tools` (the version's tool definitions with descriptions, params and requires), `metricDefinitions` (the agent's active metric definitions), `metricDetail` (every metric result with its detail payload), `telnyxPayloads` (every carrier event with its raw payload) or `wordTimings` (the start and end of each word the caller spoke, keyed by message id and sequence). `section: "full"` returns the whole bundle in one reply, several times what a client shows inline.
Authorization
bearerAuth A personal access token from Settings > API tokens.
In: header
Path Parameters
Workspace slug (GET /me lists yours).
Agent slug within the workspace.
Query Parameters
Omit for the compact call. Set it to read one part the compact view leaves out, without the rest of the call: agentConfig, tools, metricDefinitions, metricDetail, telnyxPayloads or wordTimings. full returns the whole bundle in one reply.
"agentConfig" | "tools" | "metricDefinitions" | "metricDetail" | "telnyxPayloads" | "wordTimings" | "full"Response Body
application/json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
curl -X GET "https://example.com/workspaces/string/agents/string/calls/string"{
"bundle": {
"property1": null,
"property2": null
},
"property1": null,
"property2": null
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}Run one test scenario POST
Run a single test against the agent's current published or draft version. Returns `verdict` (passed / failed / scoring / review_required / error), read as Test analytics reads it: an operator override wins, a passed run whose critical metric failed is failed with `failedCritical` naming the metric, and scoring means the criteria passed but critical metrics are still scoring. Also returns the graded rubric count and (on failure) the judge's reasoning for each failed rubric. A voice test, and over MCP a text test still going after 45 seconds, returns a `verdict` of running with a `batchId` instead: read the verdict with get_test_results, and do not run the test again, which would start a second paid run. After a failure, read the reasoning carefully: the judge often pinpoints exactly which line of the system prompt or which tool description is at fault. Cap at 2 retry passes per test, if the second fix doesn't take, mark it as a known-failing test and move on rather than spinning forever.
List calls GET
List this agent's calls, newest first, each with its sessionId, agent name, the caller's number and name, channel, sentiment/outcome, the analysis summary, topic and urgency, its length in seconds, and a coarse metric pass/fail summary. Call this FIRST to resolve a sessionId before get_call_bundle, get_call_metrics or evaluate_call. Narrow it with since, until and outcome; page through older calls by passing back next_cursor until it is null. Real calls only by default; pass includeTests=true to widen to test and discovery calls. Eval runs never appear here.