Send a message to the AI assistant (experimental — Soul Document V2 prompt)
curl --request POST \
--url https://hiimpria.ai/api/ai/experimental/personal/qanda-v2 \
--header 'Content-Type: application/json' \
--header 'x-access-token: <api-key>' \
--data '
{
"id": 1750660464754,
"requestArgs": {
"userISODate": "2025-06-23T06:34:24.754Z",
"userTimezone": "America/New_York",
"socketId": "DhXE7OVjCtfUmDFTAAAB",
"assistantId": "6856fa89cbafcff8d98680f5",
"selectedCourse": {
"course_id": 1750532703472,
"course_name": "Research Discussion",
"assistant": {
"_id": "6856fa89cbafcff8d98680f5"
}
},
"ragOnly": false,
"ragIgnore": false
},
"inputs": [
"What is machine learning?"
],
"outputs": []
}
'import requests
url = "https://hiimpria.ai/api/ai/experimental/personal/qanda-v2"
payload = {
"id": 1750660464754,
"requestArgs": {
"userISODate": "2025-06-23T06:34:24.754Z",
"userTimezone": "America/New_York",
"socketId": "DhXE7OVjCtfUmDFTAAAB",
"assistantId": "6856fa89cbafcff8d98680f5",
"selectedCourse": {
"course_id": 1750532703472,
"course_name": "Research Discussion",
"assistant": { "_id": "6856fa89cbafcff8d98680f5" }
},
"ragOnly": False,
"ragIgnore": False
},
"inputs": ["What is machine learning?"],
"outputs": []
}
headers = {
"x-access-token": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-access-token': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
id: 1750660464754,
requestArgs: {
userISODate: '2025-06-23T06:34:24.754Z',
userTimezone: 'America/New_York',
socketId: 'DhXE7OVjCtfUmDFTAAAB',
assistantId: '6856fa89cbafcff8d98680f5',
selectedCourse: {
course_id: 1750532703472,
course_name: 'Research Discussion',
assistant: {_id: '6856fa89cbafcff8d98680f5'}
},
ragOnly: false,
ragIgnore: false
},
inputs: ['What is machine learning?'],
outputs: []
})
};
fetch('https://hiimpria.ai/api/ai/experimental/personal/qanda-v2', 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://hiimpria.ai/api/ai/experimental/personal/qanda-v2",
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([
'id' => 1750660464754,
'requestArgs' => [
'userISODate' => '2025-06-23T06:34:24.754Z',
'userTimezone' => 'America/New_York',
'socketId' => 'DhXE7OVjCtfUmDFTAAAB',
'assistantId' => '6856fa89cbafcff8d98680f5',
'selectedCourse' => [
'course_id' => 1750532703472,
'course_name' => 'Research Discussion',
'assistant' => [
'_id' => '6856fa89cbafcff8d98680f5'
]
],
'ragOnly' => false,
'ragIgnore' => false
],
'inputs' => [
'What is machine learning?'
],
'outputs' => [
]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-access-token: <api-key>"
],
]);
$response = curl_exec($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://hiimpria.ai/api/ai/experimental/personal/qanda-v2"
payload := strings.NewReader("{\n \"id\": 1750660464754,\n \"requestArgs\": {\n \"userISODate\": \"2025-06-23T06:34:24.754Z\",\n \"userTimezone\": \"America/New_York\",\n \"socketId\": \"DhXE7OVjCtfUmDFTAAAB\",\n \"assistantId\": \"6856fa89cbafcff8d98680f5\",\n \"selectedCourse\": {\n \"course_id\": 1750532703472,\n \"course_name\": \"Research Discussion\",\n \"assistant\": {\n \"_id\": \"6856fa89cbafcff8d98680f5\"\n }\n },\n \"ragOnly\": false,\n \"ragIgnore\": false\n },\n \"inputs\": [\n \"What is machine learning?\"\n ],\n \"outputs\": []\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-access-token", "<api-key>")
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://hiimpria.ai/api/ai/experimental/personal/qanda-v2")
.header("x-access-token", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"id\": 1750660464754,\n \"requestArgs\": {\n \"userISODate\": \"2025-06-23T06:34:24.754Z\",\n \"userTimezone\": \"America/New_York\",\n \"socketId\": \"DhXE7OVjCtfUmDFTAAAB\",\n \"assistantId\": \"6856fa89cbafcff8d98680f5\",\n \"selectedCourse\": {\n \"course_id\": 1750532703472,\n \"course_name\": \"Research Discussion\",\n \"assistant\": {\n \"_id\": \"6856fa89cbafcff8d98680f5\"\n }\n },\n \"ragOnly\": false,\n \"ragIgnore\": false\n },\n \"inputs\": [\n \"What is machine learning?\"\n ],\n \"outputs\": []\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://hiimpria.ai/api/ai/experimental/personal/qanda-v2")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-access-token"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"id\": 1750660464754,\n \"requestArgs\": {\n \"userISODate\": \"2025-06-23T06:34:24.754Z\",\n \"userTimezone\": \"America/New_York\",\n \"socketId\": \"DhXE7OVjCtfUmDFTAAAB\",\n \"assistantId\": \"6856fa89cbafcff8d98680f5\",\n \"selectedCourse\": {\n \"course_id\": 1750532703472,\n \"course_name\": \"Research Discussion\",\n \"assistant\": {\n \"_id\": \"6856fa89cbafcff8d98680f5\"\n }\n },\n \"ragOnly\": false,\n \"ragIgnore\": false\n },\n \"inputs\": [\n \"What is machine learning?\"\n ],\n \"outputs\": []\n}"
response = http.request(request)
puts response.read_body{
"success": true,
"streamingFailed": false,
"outputs": [
"Machine learning is a subset of artificial intelligence..."
],
"usage": 1234,
"credits": 5,
"query_duration_ms": 2500,
"model": "gpt-4o"
}{
"success": false,
"message": "<string>",
"error": "<string>"
}{
"success": false,
"message": "<string>",
"error": "<string>"
}{
"success": false,
"message": "<string>",
"error": "<string>"
}Conversation
Send a message to the AI assistant (experimental — Soul Document V2 prompt)
Second-generation experimental variant of /api/ai/personal/qanda.
Identical request / response contract to the V1 experimental endpoint,
but uses the Soul Document V2 prompt generator
(getSoulDocumentPromptV2 / getSoulDocumentPromptV2Bypassed) which
refines the cohesive-anchor architecture introduced in V1. Used for
three-way A/B testing alongside classic /api/ai/personal/qanda and
the V1 experimental endpoint.
Behavior is otherwise identical to /api/ai/experimental/personal/qanda:
- Same
inputs[]+requestArgsrequest shape (QandARequest). - Same Socket.IO streaming via optional
requestArgs.socketId. - Same downstream middleware chain (
creditCheck,contentFilterCheck,creditPayment,saveToHistory,sendResponse). - Same handler-level
User.findOne({_id})re-load (theresolveInstitutionmiddleware still runs upstream, but the handler operates on the freshly re-loaded user object). req.locals.experimental = trueandreq.locals.promptMode = 'soul-v2'are stamped on the history record so the A/B harness can distinguish V1 from V2 runs.
See docs/plans/2026-02-01-soul-document-experiment-design.md and the
three-way comparison runner in test/soul-comparison/.
POST
/
api
/
ai
/
experimental
/
personal
/
qanda-v2
Send a message to the AI assistant (experimental — Soul Document V2 prompt)
curl --request POST \
--url https://hiimpria.ai/api/ai/experimental/personal/qanda-v2 \
--header 'Content-Type: application/json' \
--header 'x-access-token: <api-key>' \
--data '
{
"id": 1750660464754,
"requestArgs": {
"userISODate": "2025-06-23T06:34:24.754Z",
"userTimezone": "America/New_York",
"socketId": "DhXE7OVjCtfUmDFTAAAB",
"assistantId": "6856fa89cbafcff8d98680f5",
"selectedCourse": {
"course_id": 1750532703472,
"course_name": "Research Discussion",
"assistant": {
"_id": "6856fa89cbafcff8d98680f5"
}
},
"ragOnly": false,
"ragIgnore": false
},
"inputs": [
"What is machine learning?"
],
"outputs": []
}
'import requests
url = "https://hiimpria.ai/api/ai/experimental/personal/qanda-v2"
payload = {
"id": 1750660464754,
"requestArgs": {
"userISODate": "2025-06-23T06:34:24.754Z",
"userTimezone": "America/New_York",
"socketId": "DhXE7OVjCtfUmDFTAAAB",
"assistantId": "6856fa89cbafcff8d98680f5",
"selectedCourse": {
"course_id": 1750532703472,
"course_name": "Research Discussion",
"assistant": { "_id": "6856fa89cbafcff8d98680f5" }
},
"ragOnly": False,
"ragIgnore": False
},
"inputs": ["What is machine learning?"],
"outputs": []
}
headers = {
"x-access-token": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-access-token': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
id: 1750660464754,
requestArgs: {
userISODate: '2025-06-23T06:34:24.754Z',
userTimezone: 'America/New_York',
socketId: 'DhXE7OVjCtfUmDFTAAAB',
assistantId: '6856fa89cbafcff8d98680f5',
selectedCourse: {
course_id: 1750532703472,
course_name: 'Research Discussion',
assistant: {_id: '6856fa89cbafcff8d98680f5'}
},
ragOnly: false,
ragIgnore: false
},
inputs: ['What is machine learning?'],
outputs: []
})
};
fetch('https://hiimpria.ai/api/ai/experimental/personal/qanda-v2', 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://hiimpria.ai/api/ai/experimental/personal/qanda-v2",
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([
'id' => 1750660464754,
'requestArgs' => [
'userISODate' => '2025-06-23T06:34:24.754Z',
'userTimezone' => 'America/New_York',
'socketId' => 'DhXE7OVjCtfUmDFTAAAB',
'assistantId' => '6856fa89cbafcff8d98680f5',
'selectedCourse' => [
'course_id' => 1750532703472,
'course_name' => 'Research Discussion',
'assistant' => [
'_id' => '6856fa89cbafcff8d98680f5'
]
],
'ragOnly' => false,
'ragIgnore' => false
],
'inputs' => [
'What is machine learning?'
],
'outputs' => [
]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-access-token: <api-key>"
],
]);
$response = curl_exec($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://hiimpria.ai/api/ai/experimental/personal/qanda-v2"
payload := strings.NewReader("{\n \"id\": 1750660464754,\n \"requestArgs\": {\n \"userISODate\": \"2025-06-23T06:34:24.754Z\",\n \"userTimezone\": \"America/New_York\",\n \"socketId\": \"DhXE7OVjCtfUmDFTAAAB\",\n \"assistantId\": \"6856fa89cbafcff8d98680f5\",\n \"selectedCourse\": {\n \"course_id\": 1750532703472,\n \"course_name\": \"Research Discussion\",\n \"assistant\": {\n \"_id\": \"6856fa89cbafcff8d98680f5\"\n }\n },\n \"ragOnly\": false,\n \"ragIgnore\": false\n },\n \"inputs\": [\n \"What is machine learning?\"\n ],\n \"outputs\": []\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-access-token", "<api-key>")
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://hiimpria.ai/api/ai/experimental/personal/qanda-v2")
.header("x-access-token", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"id\": 1750660464754,\n \"requestArgs\": {\n \"userISODate\": \"2025-06-23T06:34:24.754Z\",\n \"userTimezone\": \"America/New_York\",\n \"socketId\": \"DhXE7OVjCtfUmDFTAAAB\",\n \"assistantId\": \"6856fa89cbafcff8d98680f5\",\n \"selectedCourse\": {\n \"course_id\": 1750532703472,\n \"course_name\": \"Research Discussion\",\n \"assistant\": {\n \"_id\": \"6856fa89cbafcff8d98680f5\"\n }\n },\n \"ragOnly\": false,\n \"ragIgnore\": false\n },\n \"inputs\": [\n \"What is machine learning?\"\n ],\n \"outputs\": []\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://hiimpria.ai/api/ai/experimental/personal/qanda-v2")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-access-token"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"id\": 1750660464754,\n \"requestArgs\": {\n \"userISODate\": \"2025-06-23T06:34:24.754Z\",\n \"userTimezone\": \"America/New_York\",\n \"socketId\": \"DhXE7OVjCtfUmDFTAAAB\",\n \"assistantId\": \"6856fa89cbafcff8d98680f5\",\n \"selectedCourse\": {\n \"course_id\": 1750532703472,\n \"course_name\": \"Research Discussion\",\n \"assistant\": {\n \"_id\": \"6856fa89cbafcff8d98680f5\"\n }\n },\n \"ragOnly\": false,\n \"ragIgnore\": false\n },\n \"inputs\": [\n \"What is machine learning?\"\n ],\n \"outputs\": []\n}"
response = http.request(request)
puts response.read_body{
"success": true,
"streamingFailed": false,
"outputs": [
"Machine learning is a subset of artificial intelligence..."
],
"usage": 1234,
"credits": 5,
"query_duration_ms": 2500,
"model": "gpt-4o"
}{
"success": false,
"message": "<string>",
"error": "<string>"
}{
"success": false,
"message": "<string>",
"error": "<string>"
}{
"success": false,
"message": "<string>",
"error": "<string>"
}Authorizations
JWT token passed in x-access-token header
Body
application/json
Request payload for AI Q&A conversation
User messages to send to the AI
Example:
["What is machine learning?"]
Client-generated request identifier (epoch timestamp)
Example:
1750660464754
Context arguments for AI conversation requests
Show child attributes
Show child attributes
Previous AI responses (for context continuity)
Example:
[]
Response
AI response generated successfully (Soul Document V2 system prompt)
Response from AI Q&A conversation
Whether the request completed successfully
True if Socket.IO streaming failed (response still contains full output)
Error message if streaming failed
AI-generated response messages
Total tokens consumed (input + output)
Credits consumed for this request
User's total credits consumed
User's remaining credit balance
Total processing time in milliseconds
AI model identifier used for generation
Example:
"gpt-4o"
Pricing modality — true when the turn was billed on the subagent-modality lanes (conversation + orchestrator + workers at true model cost × margin), false/absent for flat single-shot pricing (10,000 tokens = 1 credit)
Per-lane fractional credits (post-margin) summed into the billed integer — voice (conversation), conductor (orchestrator), subagents (workers). Present on billed turns only.
Show child attributes
Show child attributes
Orchestrator-lane fractional credits (subagent-modality turns only)
The cost margin applied to the subagent-modality lanes on this turn (e.g. 1.5)
Was this page helpful?