Run a live-persona simulation against an agent
curl --request POST \
--url https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"scenarios": [
{
"id": "scn_refund",
"title": "Refund request",
"channel": "chat",
"persona": {
"name": "Dana",
"mood": "frustrated",
"background": "Charged twice for the same invoice."
},
"situation": "A customer wants a duplicate charge refunded.",
"objective": "Issue a refund or escalate to billing with a clear handoff.",
"rubric": [
{
"key": "resolution",
"label": "Resolution",
"description": "The refund was issued or correctly escalated."
}
],
"maxTurns": 8
}
],
"threshold": 75
}
'import requests
url = "https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation"
payload = {
"scenarios": [
{
"id": "scn_refund",
"title": "Refund request",
"channel": "chat",
"persona": {
"name": "Dana",
"mood": "frustrated",
"background": "Charged twice for the same invoice."
},
"situation": "A customer wants a duplicate charge refunded.",
"objective": "Issue a refund or escalate to billing with a clear handoff.",
"rubric": [
{
"key": "resolution",
"label": "Resolution",
"description": "The refund was issued or correctly escalated."
}
],
"maxTurns": 8
}
],
"threshold": 75
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
scenarios: [
{
id: 'scn_refund',
title: 'Refund request',
channel: 'chat',
persona: {
name: 'Dana',
mood: 'frustrated',
background: 'Charged twice for the same invoice.'
},
situation: 'A customer wants a duplicate charge refunded.',
objective: 'Issue a refund or escalate to billing with a clear handoff.',
rubric: [
{
key: 'resolution',
label: 'Resolution',
description: 'The refund was issued or correctly escalated.'
}
],
maxTurns: 8
}
],
threshold: 75
})
};
fetch('https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'scenarios' => [
[
'id' => 'scn_refund',
'title' => 'Refund request',
'channel' => 'chat',
'persona' => [
'name' => 'Dana',
'mood' => 'frustrated',
'background' => 'Charged twice for the same invoice.'
],
'situation' => 'A customer wants a duplicate charge refunded.',
'objective' => 'Issue a refund or escalate to billing with a clear handoff.',
'rubric' => [
[
'key' => 'resolution',
'label' => 'Resolution',
'description' => 'The refund was issued or correctly escalated.'
]
],
'maxTurns' => 8
]
],
'threshold' => 75
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation"
payload := strings.NewReader("{\n \"scenarios\": [\n {\n \"id\": \"scn_refund\",\n \"title\": \"Refund request\",\n \"channel\": \"chat\",\n \"persona\": {\n \"name\": \"Dana\",\n \"mood\": \"frustrated\",\n \"background\": \"Charged twice for the same invoice.\"\n },\n \"situation\": \"A customer wants a duplicate charge refunded.\",\n \"objective\": \"Issue a refund or escalate to billing with a clear handoff.\",\n \"rubric\": [\n {\n \"key\": \"resolution\",\n \"label\": \"Resolution\",\n \"description\": \"The refund was issued or correctly escalated.\"\n }\n ],\n \"maxTurns\": 8\n }\n ],\n \"threshold\": 75\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"scenarios\": [\n {\n \"id\": \"scn_refund\",\n \"title\": \"Refund request\",\n \"channel\": \"chat\",\n \"persona\": {\n \"name\": \"Dana\",\n \"mood\": \"frustrated\",\n \"background\": \"Charged twice for the same invoice.\"\n },\n \"situation\": \"A customer wants a duplicate charge refunded.\",\n \"objective\": \"Issue a refund or escalate to billing with a clear handoff.\",\n \"rubric\": [\n {\n \"key\": \"resolution\",\n \"label\": \"Resolution\",\n \"description\": \"The refund was issued or correctly escalated.\"\n }\n ],\n \"maxTurns\": 8\n }\n ],\n \"threshold\": 75\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"scenarios\": [\n {\n \"id\": \"scn_refund\",\n \"title\": \"Refund request\",\n \"channel\": \"chat\",\n \"persona\": {\n \"name\": \"Dana\",\n \"mood\": \"frustrated\",\n \"background\": \"Charged twice for the same invoice.\"\n },\n \"situation\": \"A customer wants a duplicate charge refunded.\",\n \"objective\": \"Issue a refund or escalate to billing with a clear handoff.\",\n \"rubric\": [\n {\n \"key\": \"resolution\",\n \"label\": \"Resolution\",\n \"description\": \"The refund was issued or correctly escalated.\"\n }\n ],\n \"maxTurns\": 8\n }\n ],\n \"threshold\": 75\n}"
response = http.request(request)
puts response.read_body{
"data": {
"agent_id": "<string>",
"candidate_version_id": "<string>",
"judge_model": "<string>",
"replay_modes": {},
"duration_ms": 123,
"summary": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "RATE_LIMITED",
"message": "<string>",
"status": 429,
"retry_after": 2
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}Agents
Run a live-persona simulation against an agent
Drive one or more LLM-simulated caller personas turn-by-turn against the agent’s sandboxed runtime, then have an LLM judge grade each finished conversation against the scenario’s objective and rubric. Returns a rollout-gate report (pass rate, mean score, per-scenario verdicts, tool usage) suitable for gating a prompt/config change in CI. A scenario may instead carry scripted_utterances — a deterministic one-utterance-per-turn replay — so the same regression suite re-runs the exact same conversation on every prompt change while the judge still scores it. Use GET …/batch-simulation for fully scripted journeys. Owner/admin/developer role required; 503 when the LLM judge is not configured on the deployment; 404 when the agent does not exist.
POST
/
api
/
v1
/
agents
/
{id}
/
persona-simulation
Run a live-persona simulation against an agent
curl --request POST \
--url https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"scenarios": [
{
"id": "scn_refund",
"title": "Refund request",
"channel": "chat",
"persona": {
"name": "Dana",
"mood": "frustrated",
"background": "Charged twice for the same invoice."
},
"situation": "A customer wants a duplicate charge refunded.",
"objective": "Issue a refund or escalate to billing with a clear handoff.",
"rubric": [
{
"key": "resolution",
"label": "Resolution",
"description": "The refund was issued or correctly escalated."
}
],
"maxTurns": 8
}
],
"threshold": 75
}
'import requests
url = "https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation"
payload = {
"scenarios": [
{
"id": "scn_refund",
"title": "Refund request",
"channel": "chat",
"persona": {
"name": "Dana",
"mood": "frustrated",
"background": "Charged twice for the same invoice."
},
"situation": "A customer wants a duplicate charge refunded.",
"objective": "Issue a refund or escalate to billing with a clear handoff.",
"rubric": [
{
"key": "resolution",
"label": "Resolution",
"description": "The refund was issued or correctly escalated."
}
],
"maxTurns": 8
}
],
"threshold": 75
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
scenarios: [
{
id: 'scn_refund',
title: 'Refund request',
channel: 'chat',
persona: {
name: 'Dana',
mood: 'frustrated',
background: 'Charged twice for the same invoice.'
},
situation: 'A customer wants a duplicate charge refunded.',
objective: 'Issue a refund or escalate to billing with a clear handoff.',
rubric: [
{
key: 'resolution',
label: 'Resolution',
description: 'The refund was issued or correctly escalated.'
}
],
maxTurns: 8
}
],
threshold: 75
})
};
fetch('https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'scenarios' => [
[
'id' => 'scn_refund',
'title' => 'Refund request',
'channel' => 'chat',
'persona' => [
'name' => 'Dana',
'mood' => 'frustrated',
'background' => 'Charged twice for the same invoice.'
],
'situation' => 'A customer wants a duplicate charge refunded.',
'objective' => 'Issue a refund or escalate to billing with a clear handoff.',
'rubric' => [
[
'key' => 'resolution',
'label' => 'Resolution',
'description' => 'The refund was issued or correctly escalated.'
]
],
'maxTurns' => 8
]
],
'threshold' => 75
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation"
payload := strings.NewReader("{\n \"scenarios\": [\n {\n \"id\": \"scn_refund\",\n \"title\": \"Refund request\",\n \"channel\": \"chat\",\n \"persona\": {\n \"name\": \"Dana\",\n \"mood\": \"frustrated\",\n \"background\": \"Charged twice for the same invoice.\"\n },\n \"situation\": \"A customer wants a duplicate charge refunded.\",\n \"objective\": \"Issue a refund or escalate to billing with a clear handoff.\",\n \"rubric\": [\n {\n \"key\": \"resolution\",\n \"label\": \"Resolution\",\n \"description\": \"The refund was issued or correctly escalated.\"\n }\n ],\n \"maxTurns\": 8\n }\n ],\n \"threshold\": 75\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"scenarios\": [\n {\n \"id\": \"scn_refund\",\n \"title\": \"Refund request\",\n \"channel\": \"chat\",\n \"persona\": {\n \"name\": \"Dana\",\n \"mood\": \"frustrated\",\n \"background\": \"Charged twice for the same invoice.\"\n },\n \"situation\": \"A customer wants a duplicate charge refunded.\",\n \"objective\": \"Issue a refund or escalate to billing with a clear handoff.\",\n \"rubric\": [\n {\n \"key\": \"resolution\",\n \"label\": \"Resolution\",\n \"description\": \"The refund was issued or correctly escalated.\"\n }\n ],\n \"maxTurns\": 8\n }\n ],\n \"threshold\": 75\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.orbit.devotel.io/api/v1/agents/{id}/persona-simulation")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"scenarios\": [\n {\n \"id\": \"scn_refund\",\n \"title\": \"Refund request\",\n \"channel\": \"chat\",\n \"persona\": {\n \"name\": \"Dana\",\n \"mood\": \"frustrated\",\n \"background\": \"Charged twice for the same invoice.\"\n },\n \"situation\": \"A customer wants a duplicate charge refunded.\",\n \"objective\": \"Issue a refund or escalate to billing with a clear handoff.\",\n \"rubric\": [\n {\n \"key\": \"resolution\",\n \"label\": \"Resolution\",\n \"description\": \"The refund was issued or correctly escalated.\"\n }\n ],\n \"maxTurns\": 8\n }\n ],\n \"threshold\": 75\n}"
response = http.request(request)
puts response.read_body{
"data": {
"agent_id": "<string>",
"candidate_version_id": "<string>",
"judge_model": "<string>",
"replay_modes": {},
"duration_ms": 123,
"summary": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "RATE_LIMITED",
"message": "<string>",
"status": 429,
"retry_after": 2
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": {}
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z",
"docs_url": "<string>"
}
}Authorizations
BearerApiKey
Dashboard JWT token from Clerk
Headers
Stripe-style idempotency token. Pass a stable, client-generated value (1-255 chars) to dedupe retries on transient timeouts. The same key+credential+path replays the original response for 24h on 2xx (5min on 4xx, 30s on 5xx). Returns 409 if a concurrent request with the same key is already in flight; replayed responses include the Idempotency-Replay: true response header.
Required string length:
1 - 255Sandbox opt-in for Clerk-session-authenticated requests. Set to true to route the call through the test-mode pipeline: no real provider delivery, no credits deducted, response meta.test_mode: true. Ignored for live API keys (dv_live_sk_*) — server-to-server clients must use a test-prefixed key (dv_test_sk_*) to exercise sandbox. Test-prefixed keys unconditionally enable sandbox regardless of this header.
Available options:
true, false Path Parameters
Body
application/json
Simulation scenarios (max 10 per batch). Each carries a live persona — or deterministic scripted_utterances — plus an objective and optional rubric the LLM judge grades against.
Minimum array length:
1Show child attributes
Show child attributes
Score a specific agent version instead of the live one — run the gate BEFORE promoting.
Pass threshold (0-100, default 70).
Required range:
0 <= x <= 100Max scenarios run in parallel (default 3).
Required range:
x >= 1Optional LLM judge model override from the Claude allowlist — pin it in regression suites so verdict diffs track the agent change, not judge drift.