Auto-derive contact trait tags via LLM
curl --request POST \
--url https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"contact_id": "<string>",
"max_tags": 6
}
'import requests
url = "https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive"
payload = {
"contact_id": "<string>",
"max_tags": 6
}
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({contact_id: '<string>', max_tags: 6})
};
fetch('https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive', 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/cdp/traits/auto-derive",
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([
'contact_id' => '<string>',
'max_tags' => 6
]),
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/cdp/traits/auto-derive"
payload := strings.NewReader("{\n \"contact_id\": \"<string>\",\n \"max_tags\": 6\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/cdp/traits/auto-derive")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"contact_id\": \"<string>\",\n \"max_tags\": 6\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive")
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 \"contact_id\": \"<string>\",\n \"max_tags\": 6\n}"
response = http.request(request)
puts response.read_body{
"data": {
"contact_id": "<string>",
"derived_traits": [
{
"tag": "<string>",
"rationale": "<string>"
}
],
"features": {
"recent_event_count_30d": 1,
"top_event_counts_30d": {},
"deterministic_segment_label": "<string>"
},
"derived_trait_tags_computed_at": "2023-11-07T05:31:56Z",
"llm_output_preview": "<string>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}CDP
Auto-derive contact trait tags via LLM
Reads the contact’s 30-day event mix + deterministic signals and asks the LLM to synthesise an open-ended kebab-case tag set (high-LTV, churn-risk, engaged-7d, …). The output REPLACES (not appends to) the persisted contact_scores.derived_trait_tags array. Pre-launch: synthesiser-only on-demand surface; segmentation-engine sync ships in a follow-up wave.
POST
/
api
/
v1
/
cdp
/
traits
/
auto-derive
Auto-derive contact trait tags via LLM
curl --request POST \
--url https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"contact_id": "<string>",
"max_tags": 6
}
'import requests
url = "https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive"
payload = {
"contact_id": "<string>",
"max_tags": 6
}
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({contact_id: '<string>', max_tags: 6})
};
fetch('https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive', 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/cdp/traits/auto-derive",
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([
'contact_id' => '<string>',
'max_tags' => 6
]),
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/cdp/traits/auto-derive"
payload := strings.NewReader("{\n \"contact_id\": \"<string>\",\n \"max_tags\": 6\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/cdp/traits/auto-derive")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"contact_id\": \"<string>\",\n \"max_tags\": 6\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.orbit.devotel.io/api/v1/cdp/traits/auto-derive")
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 \"contact_id\": \"<string>\",\n \"max_tags\": 6\n}"
response = http.request(request)
puts response.read_body{
"data": {
"contact_id": "<string>",
"derived_traits": [
{
"tag": "<string>",
"rationale": "<string>"
}
],
"features": {
"recent_event_count_30d": 1,
"top_event_counts_30d": {},
"deterministic_segment_label": "<string>"
},
"derived_trait_tags_computed_at": "2023-11-07T05:31:56Z",
"llm_output_preview": "<string>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}{
"error": {
"code": "<string>",
"message": "<string>",
"status": 123,
"details": "<unknown>"
},
"meta": {
"request_id": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}
}Authorizations
BearerApiKey
Dashboard JWT token from Clerk
Body
application/json
Contact identifier. The handler reads the contact's 30-day event mix + deterministic signals from the tenant schema before invoking the LLM.
Required string length:
1 - 200Soft cap on the tags the LLM proposes. Server-side clamping prevents a chatty model from blowing the contact-detail panel layout.
Required range:
1 <= x <= 10Propagate a completed GDPR erasure to downstream destinationsList SQL-native computed-trait definitions
⌘I