List simulations
List simulations with optional filtering and sorting.
Authorizations
API key for authentication.
Query Parameters
Filter expression syntax.
Supported fields: status, agent_id, persona_id, test_set_id, test_case_id, run_id, external_conversation_id, mutation_id, mutation_name, create_time, metric.{metric_id}
Operators: =, !=, >, <, >=, <=, AND, OR
A metric.{metric_id} predicate (score filtering; number and string metrics, type inferred
from the literal) returns only simulations whose metric matches, with each simulation's value
per metric embedded inline (metric_values). On this path the request is keyset-paginated,
ordered newest-first by creation time, and supports only AND alongside create_time,
agent_id, status, test_set_id, and persona_id; other fields and any non-default
order_by are rejected with 400, and page_size is capped at 100.
Values may be unquoted or double-quoted. Values containing spaces must be quoted (e.g., status="IN PROGRESS").
The external_conversation_id field is your system's conversation ID for cross-system lookup.
Mutation Filtering: Use mutation_id or mutation_name to filter simulations by agent mutation variant.
Base agent simulations have both mutation_id and mutation_name = null.
To get only base agent results, filter for simulations where mutation_id is not set.
Maximum number of results per page
1 <= x <= 1000Opaque pagination token from previous response
Sort order specification.
Format: field or -field (descending)
Supported fields: create_time, status
Set to metric_values to embed each simulation's value per metric inline. Served by the
keyset engine (newest-first, page_size capped at 100).
metric_values