[Go to site: main page, start]

Skip to main content
POST
Evaluate
Integration Prompt for AI Agents
Any key-value pairs passed in the metadata field can be referenced as dynamic variables in the custom metrics that run on this call.

Headers

X-API-Key
string
required

API key required to authenticate requests.

Body

application/json
agent_id
string
required

ID of the agent associated with the call

start_time_utc
string<date-time>
required

When the call started, in UTC ([python] log: datetime.now(timezone.utc) at call start)

participants
Participant · object[]
required

List of call participants

Required array length: 2 elements
recording_url
string<uri> | null

URL to the recording file (supported formats: .mp3, .mp4, .wav, .m4a)

Required string length: 1 - 5000
recording_base64
string | null

Base64 encoded recording file in data URL format (supported formats: .mp3, .mp4, .wav, .m4a)

call_direction
enum<string> | null
default:INBOUND

Direction of the call from the Agent's perspective (INBOUND or OUTBOUND)

Available options:
INBOUND,
OUTBOUND
interface
enum<string> | null
default:PHONE

Interface used for the call

Available options:
PHONE,
WEB
transcript_url
string<uri> | null

URL to the transcript file (supported formats: .json)

Required string length: 1 - 5000
transcript
TranscriptEntryRequest · object[] | null

Transcript of the call in text format

tool_calls
ToolCallData · object[] | null

List of tool calls made during the call

events
Event · object[] | null

List of events that occurred during the call

tags
string[] | null

List of tags associated with the call

trace_id
string | null

Trace ID of the call

created_at
string<date-time> | null

When this request was created (defaults to now in UTC)

metadata
Metadata · object | null

Additional metadata associated with the evaluation

webhook_tag
string | null

Tag of the webhook to send the evaluation to

custom_metrics
string<uuid>[] | null

List of additional custom metrics to be used in the call

custom_metric_tags
string[] | null

Specify one or more tags to include all custom metrics associated with those tags. This allows you to run groups of related custom metrics without listing each individually.

label
string | null

Label of the agent to use for the evaluation (determines which prompt and knowledge base to use and defaults to the production label if not provided)

enable_phrase_latencies
boolean | null

Whether to enable phrase-level latency tracking for this call

conversation_ended_by
enum<string> | null

Which participant role ended the conversation: 'USER' or 'AGENT'

Available options:
AGENT,
USER,
DIGITAL_HUMAN,
agent,
digital_human
multichannel
boolean | null
default:false

Whether the participants of the call are on different audio channels

Response

Successful Response

status
string
required
call_id
string
required
message
string
required