Create an automation

curl --request POST \
  --url https://api.reasonmachines.com/v3/organizations/{orgId}/automations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Nightly dependency audit",
  "instructions": "Audit dependencies for known CVEs and open a PR if any need patching.",
  "repo": "acme/widget",
  "provider": "github"
}
'

import requests

url = "https://api.reasonmachines.com/v3/organizations/{orgId}/automations"

payload = {
    "name": "Nightly dependency audit",
    "instructions": "Audit dependencies for known CVEs and open a PR if any need patching.",
    "repo": "acme/widget",
    "provider": "github"
}
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({
    name: 'Nightly dependency audit',
    instructions: 'Audit dependencies for known CVEs and open a PR if any need patching.',
    repo: 'acme/widget',
    provider: 'github'
  })
};

fetch('https://api.reasonmachines.com/v3/organizations/{orgId}/automations', 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.reasonmachines.com/v3/organizations/{orgId}/automations",
  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([
    'name' => 'Nightly dependency audit',
    'instructions' => 'Audit dependencies for known CVEs and open a PR if any need patching.',
    'repo' => 'acme/widget',
    'provider' => 'github'
  ]),
  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.reasonmachines.com/v3/organizations/{orgId}/automations"

	payload := strings.NewReader("{\n  \"name\": \"Nightly dependency audit\",\n  \"instructions\": \"Audit dependencies for known CVEs and open a PR if any need patching.\",\n  \"repo\": \"acme/widget\",\n  \"provider\": \"github\"\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.reasonmachines.com/v3/organizations/{orgId}/automations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"Nightly dependency audit\",\n  \"instructions\": \"Audit dependencies for known CVEs and open a PR if any need patching.\",\n  \"repo\": \"acme/widget\",\n  \"provider\": \"github\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.reasonmachines.com/v3/organizations/{orgId}/automations")

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  \"name\": \"Nightly dependency audit\",\n  \"instructions\": \"Audit dependencies for known CVEs and open a PR if any need patching.\",\n  \"repo\": \"acme/widget\",\n  \"provider\": \"github\"\n}"

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

{
  "id": "automation_example",
  "org_id": "org_example",
  "name": "Daily repository review",
  "instructions": "Review open issues.",
  "model": null,
  "enabled": true,
  "tools": {
    "mcp_servers": null,
    "app_tools": []
  },
  "environment": {
    "repo": "example/project",
    "provider": "github"
  },
  "triggers": [
    {
      "id": "trigger_example",
      "kind": "schedule",
      "enabled": true,
      "schedule": {
        "kind": "cron",
        "expression": "0 9 * * *",
        "every_seconds": null,
        "next_run_at": "2026-09-24T09:00:00Z"
      },
      "github": null,
      "webhook": null,
      "run_kind": null,
      "last_fired_at": null,
      "created_at": "2026-09-01T00:00:00Z",
      "updated_at": "2026-09-01T00:00:00Z"
    }
  ],
  "created_at": "2026-09-01T00:00:00Z",
  "updated_at": "2026-09-01T00:00:00Z"
}

{
  "error": "prompt_required"
}

{
  "error": "missing_bearer",
  "message": "Authorization required"
}

{
  "error": "missing_scope",
  "required_scope": "sessions:read"
}

{
  "error": {
    "type": "rate_limited",
    "message": "This API key exceeded its request-rate limit"
  }
}

Automations

Create an automation

Creates the automation’s configuration (instructions + environment binding). Add a trigger with POST /automations/{automationId}/triggers to make it fire. The repo must already be connected. Name and instructions are trimmed and may not be blank; tools must name MCP servers the workspace has and known app tools (see the field descriptions for each 400 code). A known app tool that is not connected yet is accepted with an app_tool_not_connected entry in warnings.

_{Scope: automations:write}

POST

organizations

{orgId}

automations

Create an automation

curl --request POST \
  --url https://api.reasonmachines.com/v3/organizations/{orgId}/automations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Nightly dependency audit",
  "instructions": "Audit dependencies for known CVEs and open a PR if any need patching.",
  "repo": "acme/widget",
  "provider": "github"
}
'

import requests

url = "https://api.reasonmachines.com/v3/organizations/{orgId}/automations"

payload = {
    "name": "Nightly dependency audit",
    "instructions": "Audit dependencies for known CVEs and open a PR if any need patching.",
    "repo": "acme/widget",
    "provider": "github"
}
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({
    name: 'Nightly dependency audit',
    instructions: 'Audit dependencies for known CVEs and open a PR if any need patching.',
    repo: 'acme/widget',
    provider: 'github'
  })
};

fetch('https://api.reasonmachines.com/v3/organizations/{orgId}/automations', 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.reasonmachines.com/v3/organizations/{orgId}/automations",
  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([
    'name' => 'Nightly dependency audit',
    'instructions' => 'Audit dependencies for known CVEs and open a PR if any need patching.',
    'repo' => 'acme/widget',
    'provider' => 'github'
  ]),
  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.reasonmachines.com/v3/organizations/{orgId}/automations"

	payload := strings.NewReader("{\n  \"name\": \"Nightly dependency audit\",\n  \"instructions\": \"Audit dependencies for known CVEs and open a PR if any need patching.\",\n  \"repo\": \"acme/widget\",\n  \"provider\": \"github\"\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.reasonmachines.com/v3/organizations/{orgId}/automations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"Nightly dependency audit\",\n  \"instructions\": \"Audit dependencies for known CVEs and open a PR if any need patching.\",\n  \"repo\": \"acme/widget\",\n  \"provider\": \"github\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.reasonmachines.com/v3/organizations/{orgId}/automations")

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  \"name\": \"Nightly dependency audit\",\n  \"instructions\": \"Audit dependencies for known CVEs and open a PR if any need patching.\",\n  \"repo\": \"acme/widget\",\n  \"provider\": \"github\"\n}"

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

{
  "id": "automation_example",
  "org_id": "org_example",
  "name": "Daily repository review",
  "instructions": "Review open issues.",
  "model": null,
  "enabled": true,
  "tools": {
    "mcp_servers": null,
    "app_tools": []
  },
  "environment": {
    "repo": "example/project",
    "provider": "github"
  },
  "triggers": [
    {
      "id": "trigger_example",
      "kind": "schedule",
      "enabled": true,
      "schedule": {
        "kind": "cron",
        "expression": "0 9 * * *",
        "every_seconds": null,
        "next_run_at": "2026-09-24T09:00:00Z"
      },
      "github": null,
      "webhook": null,
      "run_kind": null,
      "last_fired_at": null,
      "created_at": "2026-09-01T00:00:00Z",
      "updated_at": "2026-09-01T00:00:00Z"
    }
  ],
  "created_at": "2026-09-01T00:00:00Z",
  "updated_at": "2026-09-01T00:00:00Z"
}

{
  "error": "prompt_required"
}

{
  "error": "missing_bearer",
  "message": "Authorization required"
}

{
  "error": "missing_scope",
  "required_scope": "sessions:read"
}

{
  "error": {
    "type": "rate_limited",
    "message": "This API key exceeded its request-rate limit"
  }
}

Authorizations

Authorization

string

header

required

Your Reason API key from Settings > API. New keys use reason_; legacy ara_ keys remain accepted. Keys are capability-scoped: run, mcp:read, mcp:write, secrets:read, secrets:write, sessions:read, sessions:debug, knowledge:read, memory:read, memory:write, skills:read, skills:write, repos:read, repos:write, reviews:read, reviews:write, deployment:read, analytics:read, org:read, org:write, attachments:read, attachments:write, guardrails:read, guardrails:write, automations:read, automations:write, agent_auth:read. mcp:write manages MCP server configuration only; it does not authorize remote MCP-tool execution. sessions:read reads sessions, including the assistant, reasoning and tool activity in their events. sessions:debug is privileged: only for organization owners/admins, it expands session events to the full diagnostic projection (diagnostic event kinds, status text and raw event metadata).

Path Parameters

orgId

string

required

Organization id or slug. Resolve it with GET /v3/self.

Body

application/json

Creates the automation's configuration. It has no triggers until you add one via POST /automations/{automationId}/triggers, so it will not fire on its own yet.

instructions

string

required

The system instructions the automation runs with, trimmed, at most 100,000 characters. Blank instructions return 400 instructions_required; longer ones return 400 instructions_too_long.

repo

string

required

Connected GitHub repository path in owner/name form.

name

string

Display name, trimmed, at most 200 characters. Defaults to the start of instructions when omitted. A blank name returns 400 name_required; a longer one returns 400 name_too_long.

provider

enum<string>

Source-control provider for the connected repository. GitHub is the only supported provider.

Available options:

github

model

string | null

Model override. null uses the workspace default. New runs accept only the currently available Reason model catalog.

tools

object

Show child attributes

Response

Created.

An automation: its instructions, tools, environment binding, and triggers.

string

org_id

string

name

string | null

instructions

string | null

The system instructions the automation runs with.

model

string | null

enabled

boolean

A paused (false) automation's triggers never fire.

tools

object

Show child attributes

environment

object

Show child attributes

triggers

object[]

Every condition that fires this automation. Empty until you add one.

Show child attributes

warnings

object[]

Present only when the request was accepted but something is not as sent or not usable yet. Codes: schedule_interval_raised, app_tool_not_connected.

Show child attributes

created_at

string<date-time>

updated_at

string<date-time>