List agent prompt improvements
List this agent's Optimise-Prompt sessions, newest first. Each session is one run of the self-improving prompt loop and reports its status (pending / running / proposed / accepted / rejected / error), the before/after pass rate on the selected scenarios, the exit reason (e.g. 'Exited: 100% pass + full-set regression sweep clean' or 'Exited: max_iterations reached (10)'), and when it was created. Use this to see whether the last optimise run produced a proposal you can accept_agent_prompt_improvement, or to review past runs. Returns an empty list when the agent has never been optimised. agentId is optional and defaults to the agent you're editing.
Authorization
bearerAuth A personal access token from Settings > API tokens.
In: header
Header Parameters
A key you choose, such as a UUID, that makes this POST safe to retry. Within 24 hours the same key and request answers with the first successful answer and runs nothing, the same key with a different request answers 422 idempotency_key_reused, and a key whose request is still running answers 409 idempotency_key_in_use. A failed request keeps nothing, so the same key runs it again.
1 <= length <= 255Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
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 POST "https://example.com/operations/list_agent_prompt_improvements" \ -H "Content-Type: application/json" \ -d '{ "agent": "string" }'{}{
"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
}List agent connections POST
List the apps connected for THIS agent and their status. Returns `agentConnections`, the agent's own connections, each `{ toolkit, status, enabled, allowedTools }` where status is 'pending' | 'active' | 'failed' | 'revoked', plus `workspaceActive`, the workspace-wide apps available to scope onto the agent. Use after initiate_agent_connection to check whether a connection has gone from 'pending' to 'active', and before set_agent_connection to see what's already connected.
List agent templates POST
List the agent templates a new agent can start from: tested agents kept in the template workspace (the inbound receptionist, speed-to-lead, review request and the rest of the set). Each has a `template` handle, the `name` a copy gets, a one-line description, its channels, its `section` (incoming, enquiries or customers) and its `direction` (inbound or outbound). Only agents a platform admin has listed with add_agent_template appear; an unlisted agent in the template workspace is a draft nobody sees. Read one in full with get_agent_template; start an agent from one with create_agent_from_template.