Create an AI Agent Task

Creates a new AI agent task and starts async execution. Poll the messages endpoint to retrieve results.

POST /v1/ai/agents/tasks

Create an AI Agent Task

cURL

curl --request POST \
  --url https://eu1.api.matillion.com/dpc/v1/ai/agents/tasks \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "agentConfig": {
    "name": "data_engineer_agent",
    "environmentName": "development",
    "mode": "ACT",
    "projectId": "550e8400-e29b-41d4-a716-446655440001",
    "sourceBranchName": "main",
    "generateBranch": true,
    "graphId": "my-pipeline",
    "targetBranchName": "feature/my-pipeline",
    "workingDirectory": "/pipelines"
  },
  "message": "Build a pipeline to load sales data from S3 into Snowflake",
  "grantedPermissions": [
    {
      "toolName": "execute_sql"
    }
  ]
}
'

import requests

url = "https://eu1.api.matillion.com/dpc/v1/ai/agents/tasks"

payload = {
    "agentConfig": {
        "name": "data_engineer_agent",
        "environmentName": "development",
        "mode": "ACT",
        "projectId": "550e8400-e29b-41d4-a716-446655440001",
        "sourceBranchName": "main",
        "generateBranch": True,
        "graphId": "my-pipeline",
        "targetBranchName": "feature/my-pipeline",
        "workingDirectory": "/pipelines"
    },
    "message": "Build a pipeline to load sales data from S3 into Snowflake",
    "grantedPermissions": [{ "toolName": "execute_sql" }]
}
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({
    agentConfig: {
      name: 'data_engineer_agent',
      environmentName: 'development',
      mode: 'ACT',
      projectId: '550e8400-e29b-41d4-a716-446655440001',
      sourceBranchName: 'main',
      generateBranch: true,
      graphId: 'my-pipeline',
      targetBranchName: 'feature/my-pipeline',
      workingDirectory: '/pipelines'
    },
    message: 'Build a pipeline to load sales data from S3 into Snowflake',
    grantedPermissions: [{toolName: 'execute_sql'}]
  })
};

fetch('https://eu1.api.matillion.com/dpc/v1/ai/agents/tasks', 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://eu1.api.matillion.com/dpc/v1/ai/agents/tasks",
  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([
    'agentConfig' => [
        'name' => 'data_engineer_agent',
        'environmentName' => 'development',
        'mode' => 'ACT',
        'projectId' => '550e8400-e29b-41d4-a716-446655440001',
        'sourceBranchName' => 'main',
        'generateBranch' => true,
        'graphId' => 'my-pipeline',
        'targetBranchName' => 'feature/my-pipeline',
        'workingDirectory' => '/pipelines'
    ],
    'message' => 'Build a pipeline to load sales data from S3 into Snowflake',
    'grantedPermissions' => [
        [
                'toolName' => 'execute_sql'
        ]
    ]
  ]),
  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://eu1.api.matillion.com/dpc/v1/ai/agents/tasks"

	payload := strings.NewReader("{\n  \"agentConfig\": {\n    \"name\": \"data_engineer_agent\",\n    \"environmentName\": \"development\",\n    \"mode\": \"ACT\",\n    \"projectId\": \"550e8400-e29b-41d4-a716-446655440001\",\n    \"sourceBranchName\": \"main\",\n    \"generateBranch\": true,\n    \"graphId\": \"my-pipeline\",\n    \"targetBranchName\": \"feature/my-pipeline\",\n    \"workingDirectory\": \"/pipelines\"\n  },\n  \"message\": \"Build a pipeline to load sales data from S3 into Snowflake\",\n  \"grantedPermissions\": [\n    {\n      \"toolName\": \"execute_sql\"\n    }\n  ]\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://eu1.api.matillion.com/dpc/v1/ai/agents/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"agentConfig\": {\n    \"name\": \"data_engineer_agent\",\n    \"environmentName\": \"development\",\n    \"mode\": \"ACT\",\n    \"projectId\": \"550e8400-e29b-41d4-a716-446655440001\",\n    \"sourceBranchName\": \"main\",\n    \"generateBranch\": true,\n    \"graphId\": \"my-pipeline\",\n    \"targetBranchName\": \"feature/my-pipeline\",\n    \"workingDirectory\": \"/pipelines\"\n  },\n  \"message\": \"Build a pipeline to load sales data from S3 into Snowflake\",\n  \"grantedPermissions\": [\n    {\n      \"toolName\": \"execute_sql\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://eu1.api.matillion.com/dpc/v1/ai/agents/tasks")

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  \"agentConfig\": {\n    \"name\": \"data_engineer_agent\",\n    \"environmentName\": \"development\",\n    \"mode\": \"ACT\",\n    \"projectId\": \"550e8400-e29b-41d4-a716-446655440001\",\n    \"sourceBranchName\": \"main\",\n    \"generateBranch\": true,\n    \"graphId\": \"my-pipeline\",\n    \"targetBranchName\": \"feature/my-pipeline\",\n    \"workingDirectory\": \"/pipelines\"\n  },\n  \"message\": \"Build a pipeline to load sales data from S3 into Snowflake\",\n  \"grantedPermissions\": [\n    {\n      \"toolName\": \"execute_sql\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

201

{
  "taskId": "550e8400-e29b-41d4-a716-446655440000",
  "status": "RUNNING",
  "agentName": "data_engineer_agent",
  "createdAt": "2024-01-15T10:30:00.000Z"
}

{
  "detail": "<string>",
  "instance": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "violations": [
    "<string>"
  ]
}

{
  "detail": "<string>",
  "instance": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "violations": [
    "<string>"
  ]
}

{
  "detail": "<string>",
  "instance": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "violations": [
    "<string>"
  ]
}

{
  "detail": "<string>",
  "instance": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "violations": [
    "<string>"
  ]
}

{
  "detail": "<string>",
  "instance": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "violations": [
    "<string>"
  ]
}

{
  "detail": "<string>",
  "instance": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "violations": [
    "<string>"
  ]
}

Authorizations

Authorization · string · header · required

a valid bearer token

Body

application/json

agentConfig · object · required

Configuration specifying the agent type and its parameters

Show child attributes

message · string · required

The instruction or question to send to the agent

Minimum string length: 1

Example:

"Build a pipeline to load sales data from S3 into Snowflake"

grantedPermissions · object[] | null

Permissions pre-granted to the agent for this task. Each entry must be unique

Show child attributes

Response

201

application/json

Agent task created successfully

agentName · string

The name of the agent handling the task

Example:

"data_engineer_agent"

createdAt · string<date-time>

The date and time the task was created

Example:

"2024-01-15T10:30:00.000Z"

status · enum<string>

The current status of the task

Available options: RUNNING, STOPPED, STOPPING, ERRORED

Example:

"RUNNING"

taskId · string<uuid>

The unique identifier of the created task

Example:

"550e8400-e29b-41d4-a716-446655440000"