Call Trace Analysis

Deep call understanding with emotional arcs, key decision moments, coaching recommendations, and signal-response alignment.

The call trace analysis endpoints provide deep understanding of individual calls, including emotional dynamics, decision quality, coaching recommendations, and interaction patterns.

Endpoints

Method	Path	Description
GET	/calls/traces	List call trace analyses with filters and pagination
GET	/calls/{call_id}/trace-analysis	Get detailed trace analysis for a specific call

List Trace Analyses

GET /calls/traces

Returns a paginated list of call trace analyses.

Query Parameters

Parameter	Type	Default	Description
outcome	string	-	Filter by outcome: succeeded, partially, failed, abandoned
min_computed_at	datetime	-	Only include analyses computed after this timestamp
max_computed_at	datetime	-	Only include analyses computed before this timestamp
limit	integer	20	Max results per page (1-100)
continuation_token	integer	-	Offset for the next page of results

Response

Field	Type	Description
items	array	List of trace analysis summaries
has_more	boolean	Whether more results are available
continuation_token	integer	Token to pass for the next page

Each item in items:

Field	Type	Description
call_sid	string	Call identifier
call_entity_id	string	Associated entity ID
summary	string	Brief narrative summary of the call
outcome	string	Call outcome classification
emotional_arc	string	High-level emotional trajectory
key_moment_count	integer	Number of key decision moments identified
computed_at	datetime	When the analysis was computed

Get Trace Analysis

GET /calls/{call_id}/trace-analysis

Returns the full trace analysis for a specific call.

Path Parameters

Parameter	Type	Description
call_id	string	Call SID or call entity ID

Response

Field	Type	Description
call_sid	string	Call identifier
call_entity_id	string	Associated entity ID
status	string	Analysis status: ready, pending, or unavailable
summary	string	Narrative summary of the call
outcome	string	Outcome classification: succeeded, partially, failed, abandoned
emotional_arc	string	High-level emotional trajectory across the call
key_moment_count	integer	Number of key decision moments
computed_at	datetime	When the analysis was computed
key_moments	array	Key decision points (see below)
coaching	array	Coaching recommendations (see below)
counterfactuals	array	Alternative actions (see below)
emotional_shifts	array	Emotional state changes (see below)
signal_response_alignment	array	Signal-response alignment assessments (see below)
interaction_dynamics	object	System-level conversation analysis (see below)
missed_opportunities	array of strings	Patterns the agent could have acted on
emergent_patterns	array of strings	Behavioral patterns detected
deep_understanding	string	Synthesized understanding of the conversation

Key Moment

Field	Type	Description
what_happened	string	Description of the decision point
timestamp_seconds	number	Position in the call (seconds)
quality	string	Quality assessment: optimal, adequate, suboptimal
reasoning	string	Why the agent made this decision
alternative	string	What the agent could have done instead
decision_factors	array	Factors that drove the decision, each with factor (string) and source_type (string)

Coaching Item

Field	Type	Description
observation	string	What was observed in the call
recommendation	string	Suggested improvement
moment_timestamp	number	Position in the call (seconds)
expected_impact	string	Predicted effect of the recommendation

Counterfactual

Field	Type	Description
actual	string	What actually happened
alternative	string	What could have happened instead
predicted_impact	string	Expected effect of the alternative
timestamp_seconds	number	Position in the call (seconds)

Emotional Shift

Field	Type	Description
from_state	string	Emotional state before the shift
to_state	string	Emotional state after the shift
trigger	string	What caused the shift
agent_awareness	string	Whether the agent recognized the shift
timestamp_seconds	number	Position in the call (seconds)

Signal-Response Alignment

Field	Type	Description
signal	string	The salient signal from the caller
agent_response	string	How the agent responded
alignment	string	Assessment: aligned, misaligned, partial
insight	string	Additional context about the alignment

Interaction Dynamics

Field	Type	Description
turn_taking_quality	string	Assessment of conversational turn-taking
information_density	string	How efficiently information was exchanged
rapport_trajectory	string	How rapport evolved during the call
repair_effectiveness	string	How well communication breakdowns were resolved