Skip to main content

Arrotech Hub Public API (1.0.0)

Download OpenAPI specification:Download

Welcome to the Arrotech Hub Public API

Arrotech Hub provides a unified, powerful interface for building autonomous AI agents and complex marketing automations. Our API allows you to programmatically control the entire "Mini-Hub" ecosystem, from managing connections to executing multi-step workflows.

🚀 Core Capabilities

  • Autonomous Agents: Deploy AI that can "think" and act across different platforms.
  • Workflow Orchestration: Chain together disparate tools (Slack, HubSpot, WhatsApp) into a single logical flow.
  • Model Agnostic: Build once and switch between OpenAI, Anthropic, or local Ollama models.
  • Tool Bridge (MCP): Use the Model Context Protocol to bridge local enterprise data to global LLMs.

🔑 Authentication

All requests to the Arrotech Hub API require a Bearer Token. You can generate these in your developer dashboard.

Authorization: Bearer <YOUR_API_KEY>

[!IMPORTANT] Keep your API keys secure. Never expose them in client-side code or public repositories.

âš¡ Performance & Rate Limits

The API is optimized for high-concurrency automation. Default limits are:

  • Free Tier: 100 requests / day
  • Pro Tier: 10,000 requests / day
  • Enterprise: Custom high-throughput limits available.

🛠 Support & Feedback

Join our Developer Discord or open a ticket in the Support Portal.

connections

Get Connections

List Your Integrated Platforms

Retrieves all active and inactive connections you've established with external services.

Connection Statuses:

  • active: Ready for use.
  • error: Failed authentication or disconnected. See error_message for details.
  • expired: Authentication token has expired.

Developer Tip: Use this to populate "Integrations" or "Settings" pages in your UI, showing users which apps they've already connected.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

Create Connection

Establishes a secure link between Arrotech Hub and an external service. This is the first step in enabling specialized "skills" for your AI agents.

The Connection Process:

  1. Authorization: Arrotech attempts to authenticate with the provided credentials.
  2. Capability Mapping: Once connected, Arrotech discovers all tools available for that platform (e.g., connecting Slack enables slack_send_message).
  3. Tier Check: Some platforms (like Salesforce or Premium HR tools) require a Professional or Enterprise tier.

Security: All credentials are encrypted at rest and never exposed back in plain text after the initial creation.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
platform
required
string (Platform)

The target platform ID (e.g., 'slack', 'hubspot', 'whatsapp'). Available platforms can be queried via the MCP registry.

name
required
string (Name)

A friendly name for this connection to help you identify it in the dashboard.

required
object (Config)

Platform-specific configuration credentials (API keys, workspace IDs, etc.). Each platform has a unique schema.

Responses

Request samples

Content type
application/json
{
  • "platform": "slack",
  • "name": "Marketing Slack",
  • "config": {
    }
}

Response samples

Content type
application/json
null

Update Connection

Update a connection.

Authorizations:
HTTPBearer
path Parameters
connection_id
required
integer (Connection Id)
Request Body schema: application/json
required
name
required
string (Name)
status
required
string (Status)
required
object (Config)

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "status": "string",
  • "config": { }
}

Response samples

Content type
application/json
null

Delete Connection

Delete a connection.

Authorizations:
HTTPBearer
path Parameters
connection_id
required
integer (Connection Id)

Responses

Response samples

Content type
application/json
null

Test Connection

Test a connection.

Authorizations:
HTTPBearer
path Parameters
connection_id
required
integer (Connection Id)

Responses

Response samples

Content type
application/json
null

Test New Connection

Test a connection configuration before saving.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
platform
required
string (Platform)
required
object (Config)

Responses

Request samples

Content type
application/json
{
  • "platform": "string",
  • "config": { }
}

Response samples

Content type
application/json
null

Get Available Platforms

Get available connection platforms from the platform registry.

Responses

Response samples

Content type
application/json
null

mcp

List Tools Get

List Available MCP Tools

Returns a catalog of all tools currently available to the user. This includes built-in tools and those dynamically loaded via Model Context Protocol (MCP) servers.

The Power of MCP: Arrotech Hub uses MCP to bridge the gap between LLMs and external software. This endpoint tells your front-end or your AI agent which "skills" are currently equipped.

Filtering:

  • include_all: Set to true to see even those tools that require additional configuration or authentication (useful for discovery).
Authorizations:
HTTPBearer
query Parameters
include_all
boolean (Include All)
Default: false
all
boolean (All)
Default: false

Responses

Response samples

Content type
application/json
null

Call Tool

Atomic Tool Execution

Executes a single tool and returns the result. This is a low-level endpoint primarily used by the Execution Orchestrator, but can be called directly for testing or precise control.

Execution Protocol:

  1. Registry Lookup: Finds the tool implementation in the dynamic_tool_registry.
  2. Auth Validation: Ensures you have a valid Connection (e.g., OAuth token) for the target platform.
  3. Secure Invocation: Calls the underlying API (e.g., Slack Web API, HubSpot CRM API).

Safety: All tool calls are subject to rate limiting and audit logging to ensure secure and responsible AI actions.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
name
required
string (Name)

The unique name of the MCP tool to execute (e.g., 'slack_send_message', 'hubspot_contact_create').

required
object (Arguments)

A dictionary of arguments required by the tool. Arguments vary depending on the tool's schema.

Responses

Request samples

Content type
application/json
{
  • "name": "slack_send_message",
  • "arguments": {
    }
}

Response samples

Content type
application/json
null

Call Tool Stream

Stream tool execution using Server-Sent Events.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
name
required
string (Name)

The unique name of the MCP tool to execute (e.g., 'slack_send_message', 'hubspot_contact_create').

required
object (Arguments)

A dictionary of arguments required by the tool. Arguments vary depending on the tool's schema.

Responses

Request samples

Content type
application/json
{
  • "name": "slack_send_message",
  • "arguments": {
    }
}

Response samples

Content type
application/json
null

Test Whatsapp Token

Test WhatsApp token validity.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

Debug Settings

Debug all WhatsApp settings.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

chat

Get Conversations

List User Conversations

Retrieves a paginated list of all conversation threads belonging to the authenticated user. Conversations are returned in descending order of their last update (most recent first).

This is useful for building a "Recent Chats" or "History" sidebar in your application.

Note: This endpoint only returns metadata (IDs, titles). To get the actual messages, use the GET /conversations/{conversation_id} endpoint.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

Create Conversation

Create a New Conversation

Initiates a fresh conversation thread for the authenticated user. Conversations act as containers for messages and maintain the state for AI interactions.

Key features of conversations:

  • Persistence: Messages are stored and can be retrieved later for context.
  • Context Awareness: The AI uses the message history within a conversation to provide relevant responses.
  • Platform Bridging: A single conversation can involve multiple tools and platforms (e.g., fetching a lead from HubSpot and sending a Slack alert).

Returns: A success object containing the newly created conversation's unique ID and metadata.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
Title (string) or Title (null) (Title)

An optional title for the conversation. If omitted, the system will generate a title based on the first message.

Any of
string (Title)

An optional title for the conversation. If omitted, the system will generate a title based on the first message.

Responses

Request samples

Content type
application/json
{
  • "title": "HubSpot Integration Project"
}

Response samples

Content type
application/json
null

Get Conversation

Get Conversation Details

Fetches the full metadata and a snapshot of messages for a specific conversation.

This endpoint is the standard way to resume a chat session in a UI. It returns the conversation's state, its title, and its message history.

Security:

  • Only the conversation owner can access this data.
  • All timestamps are returned in ISO 8601 UTC format.

Optimization Tip: For very long conversations, consider using the /messages endpoint with pagination (if available) to avoid loading massive JSON payloads at once.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)

Responses

Response samples

Content type
application/json
{ }

Update Conversation

Update a conversation title.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
Request Body schema: application/json
required
title
required
string (Title)

The new title for the conversation.

Responses

Request samples

Content type
application/json
{
  • "title": "Marketing Automation Campaign v2"
}

Response samples

Content type
application/json
null

Delete Conversation

Delete a conversation and all its messages.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)

Responses

Response samples

Content type
application/json
null

Send Message

Send a Message & Direct AI Execution

This is the core "command center" endpoint of Arrotech Hub. When you send a message here, the Hub's Execution Orchestrator takes over to perform autonomous tasks.

The Orchestration Lifecycle:

  1. Intent Analysis: The AI determines if your request requires action (tool calling) or just a textual response.
  2. Semantic Tool Selection: The system selects relevant tools from over 50+ integrations based on your query.
  3. Autonomous Execution: The AI calls tools (e.g., Slack, M-Pesa, HubSpot) in a loop until your goal is reached.
  4. Context Management: Every message is saved, ensuring the AI remembers previous steps in the chain.

Usage Examples:

  • Simple Chat: "Explain how Arrotech MCP works."
  • Automation: "Find all 'In Progress' tickets in Jira and post a summary to Slack #prod-updates."
  • Platform Query: "Who are my top 5 customers in HubSpot by revenue?"

Note on Providers: You can explicitly request a provider like gpt-4o or claude-3-5-sonnet using the provider field, or leave it null to use your default.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
Request Body schema: application/json
required
content
required
string (Content)

The text content of the message. Supports markdown. This is the primary input for the AI agent.

Provider (string) or Provider (null) (Provider)

Optional LLM provider override (e.g., 'openai', 'anthropic', 'ollama'). If not provided, the user's default provider is used.

Responses

Request samples

Content type
application/json
{
  • "content": "Create a summary of my last 5 HubSpot deals.",
  • "provider": "openai"
}

Response samples

Content type
application/json
{
  • "id": 0,
  • "conversation_id": 0,
  • "role": "string",
  • "content": "string",
  • "status": "string",
  • "tokens_used": 0,
  • "tools_called": [
    ],
  • "tool_call_id": "string",
  • "error_message": "string",
  • "created_at": "string"
}

Get Messages

Fetch Message History

Retrieves the complete chronological list of messages in a conversation. This includes user prompts, assistant responses, and "tool" messages (the technical results of API calls made by the AI).

Understanding Roles:

  • user: Your input.
  • assistant: The AI's response to you.
  • tool: Internal technical data from integrations (e.g., raw JSON from HubSpot). Usually hidden from end-users but vital for debugging.
  • system: Architectural instructions provided to the AI.
Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)

Responses

Response samples

Content type
application/json
null

Check Ollama Status

Check Ollama service status.

Responses

Response samples

Content type
application/json
null

Ollama Diagnostic

Comprehensive Ollama diagnostic.

Responses

Response samples

Content type
application/json
null

Test Direct Response

Test direct response generation without tools.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
content
required
string (Content)

The text content of the message. Supports markdown. This is the primary input for the AI agent.

Provider (string) or Provider (null) (Provider)

Optional LLM provider override (e.g., 'openai', 'anthropic', 'ollama'). If not provided, the user's default provider is used.

Responses

Request samples

Content type
application/json
{
  • "content": "Create a summary of my last 5 HubSpot deals.",
  • "provider": "openai"
}

Response samples

Content type
application/json
null

Get Available Providers

Get available LLM providers.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

Get Available Tools

Get available MCP tools.

Authorizations:
HTTPBearer
query Parameters
include_all
boolean (Include All)
Default: true
all
boolean (All)
Default: true

Responses

Response samples

Content type
application/json
null

Download File

Download a file from a specific message.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
message_id
required
integer (Message Id)
filename
required
string (Filename)

Responses

Response samples

Content type
application/json
null

Get File Info

Get file information from a specific message.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
message_id
required
integer (Message Id)

Responses

Response samples

Content type
application/json
null

Validate Tool Call

Validate a tool call before execution.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
Request Body schema: application/json
required
property name*
additional property
any

Responses

Request samples

Content type
application/json
{ }

Response samples

Content type
application/json
null

Explain Intent

Explain the intent classification for a user message.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
Request Body schema: application/json
required
content
required
string (Content)

The text content of the message. Supports markdown. This is the primary input for the AI agent.

Provider (string) or Provider (null) (Provider)

Optional LLM provider override (e.g., 'openai', 'anthropic', 'ollama'). If not provided, the user's default provider is used.

Responses

Request samples

Content type
application/json
{
  • "content": "Create a summary of my last 5 HubSpot deals.",
  • "provider": "openai"
}

Response samples

Content type
application/json
null

Explain Relevant Tools

Explain which tools are relevant for a user message.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)
Request Body schema: application/json
required
content
required
string (Content)

The text content of the message. Supports markdown. This is the primary input for the AI agent.

Provider (string) or Provider (null) (Provider)

Optional LLM provider override (e.g., 'openai', 'anthropic', 'ollama'). If not provided, the user's default provider is used.

Responses

Request samples

Content type
application/json
{
  • "content": "Create a summary of my last 5 HubSpot deals.",
  • "provider": "openai"
}

Response samples

Content type
application/json
null

workflows

Create Workflow

Natural Language Workflow Generation

This endpoint allows you to build complex automations using simple English instructions. The system uses a specialized Workflow Builder LLM to translate your description into a series of logical steps, tool calls, and conditional branches.

How it works:

  1. Deconstruction: The AI breaks your request into discrete "Atomic Steps".
  2. Tool Mapping: Each step is matched against our 50+ integrated tools (HubSpot, Slack, Asana, etc.).
  3. Variable Wiring: Data flows are automatically established (e.g., Output of Step 1 becomes Input for Step 2).
  4. Drafting: A draft workflow is created in your account for review.

Pro Tip: Be as specific as possible about platform names and filters.

  • Vague: "Send data to Slack."
  • Better: "Whenever a new lead is added in HubSpot with a value > $1000, send a Slack message to #big-wins."
Authorizations:
HTTPBearer
Request Body schema: application/json
required
description
required
string (Description)

A natural language description of the workflow you want to build. Our AI will analyze this to generate steps.

Name (string) or Name (null) (Name)

An optional name for the workflow. If omitted, a creative name will be generated.

Responses

Request samples

Content type
application/json
{
  • "description": "Every Monday at 9 AM, fetch my last 10 HubSpot deals and post a summary to Slack #sales-updates.",
  • "name": "Weekly Revenue Sync"
}

Response samples

Content type
application/json
{
  • "id": 0,
  • "name": "string",
  • "description": "string",
  • "status": "string",
  • "version": 0,
  • "is_template": true,
  • "trigger_type": "string",
  • "trigger_config": { },
  • "variables": { },
  • "workflow_metadata": { },
  • "created_at": "string",
  • "updated_at": "string",
  • "steps": [
    ]
}

Get Workflows

Get all workflows for the current user.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

Get All Executions

Get all workflow executions for the current user.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
null

Get Workflow

Get a specific workflow by ID.

Authorizations:
HTTPBearer
path Parameters
workflow_id
required
integer (Workflow Id)

Responses

Response samples

Content type
application/json
null

Update Workflow

Update a workflow.

Authorizations:
HTTPBearer
path Parameters
workflow_id
required
integer (Workflow Id)
Request Body schema: application/json
required
name
string (Name)

The updated name for the workflow.

description
string (Description)

The updated purpose or logic description.

status
string (Status)

The new status (e.g., 'active', 'paused', 'draft').

trigger_type
string (Trigger Type)

Update the initiation logic (e.g., 'manual', 'schedule').

object (Trigger Config)

Updated configuration for the trigger.

object (Variables)

Updated map of global workflow variables.

Array of objects (Steps)

The complete list of updated steps in sequence.

object (Workflow Metadata)

Additional metadata for categorization or UI rendering.

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "status": "string",
  • "trigger_type": "string",
  • "trigger_config": { },
  • "variables": { },
  • "steps": [
    ],
  • "workflow_metadata": { }
}

Response samples

Content type
application/json
null

Delete Workflow

Delete a workflow.

Authorizations:
HTTPBearer
path Parameters
workflow_id
required
integer (Workflow Id)

Responses

Response samples

Content type
application/json
null

Execute Workflow

Trigger Workflow Execution

Manually triggers the execution of a specific workflow. This is ideal for testing or for "On-Demand" automations triggered by external scripts.

Execution Features:

  • Variable Injection: Provide different input_data to change the workflow's behavior on each run.
  • Isolation: Each execution runs in a sandboxed environment with its own state.
  • Traceability: Detailed logs of every tool call and outcome are stored and can be retrieved via the /executions endpoint.

Error Handling: If a step fails, the workflow will attempt retries based on its configuration before marking the execution as failed.

Authorizations:
HTTPBearer
path Parameters
workflow_id
required
integer (Workflow Id)
Request Body schema: application/json
required
object (Input Data)
Default: {}

A dictionary of key-value pairs used as input for the workflow's dynamic variables.

property name*
additional property
any

Responses

Request samples

Content type
application/json
{
  • "input_data": {
    }
}

Response samples

Content type
application/json
null

Get Workflow Executions

Get all executions for a specific workflow.

Authorizations:
HTTPBearer
path Parameters
workflow_id
required
integer (Workflow Id)

Responses

Response samples

Content type
application/json
null

Test Condition

Test conditional logic evaluation.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
required
object (Condition)

The conditional logic object to evaluate.

required
object (Context)

The data context (variables/step results) to evaluate against.

Responses

Request samples

Content type
application/json
{
  • "condition": { },
  • "context": { }
}

Response samples

Content type
application/json
{
  • "result": true,
  • "evaluated_value": null,
  • "expected_value": null,
  • "operator": "string"
}

Test Variable Substitution

Test variable substitution in parameters.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
required
object (Parameters)

The template parameters containing {{variables}}.

required
object (Context)

The data context providing the values for substitution.

Responses

Request samples

Content type
application/json
{
  • "parameters": { },
  • "context": { }
}

Response samples

Content type
application/json
{
  • "original_parameters": { },
  • "substituted_parameters": { },
  • "substitutions_made": [
    ]
}

Get Workflow Templates

Get available workflow templates.

Responses

Response samples

Content type
application/json
null

Create Chat Agent

Create a chat agent from a workflow.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
description
required
string (Description)

A natural language description of the workflow you want to build. Our AI will analyze this to generate steps.

Name (string) or Name (null) (Name)

An optional name for the workflow. If omitted, a creative name will be generated.

Responses

Request samples

Content type
application/json
{
  • "description": "Every Monday at 9 AM, fetch my last 10 HubSpot deals and post a summary to Slack #sales-updates.",
  • "name": "Weekly Revenue Sync"
}

Response samples

Content type
application/json
null

Extract Workflow From Conversation

Extract a workflow from conversation history. Analyzes tool calls in a conversation and creates a reusable workflow.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
conversation_id
required
integer (Conversation Id)
workflow_name
required
string (Workflow Name)
description
string (Description)
selected_step_ids
Array of strings (Selected Step Ids)
parameterize_fields
Array of strings (Parameterize Fields)
trigger_type
string (Trigger Type)
Default: "manual"
object (Trigger Config)

Responses

Request samples

Content type
application/json
{
  • "conversation_id": 0,
  • "workflow_name": "string",
  • "description": "string",
  • "selected_step_ids": [
    ],
  • "parameterize_fields": [
    ],
  • "trigger_type": "manual",
  • "trigger_config": { }
}

Response samples

Content type
application/json
null

Create Workflow From Steps

Create a workflow from explicit step definitions. Used when saving a workflow extracted from conversation.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
workflow_name
required
string (Workflow Name)
description
required
string (Description)
required
Array of objects (Steps)
trigger_type
string (Trigger Type)
Default: "manual"
object (Trigger Config)
object (Variables)
object (Workflow Metadata)

Responses

Request samples

Content type
application/json
{
  • "workflow_name": "string",
  • "description": "string",
  • "steps": [
    ],
  • "trigger_type": "manual",
  • "trigger_config": { },
  • "variables": { },
  • "workflow_metadata": { }
}

Response samples

Content type
application/json
null

Get Conversation Tool Calls

Get all tool calls from a conversation for workflow extraction preview.

Authorizations:
HTTPBearer
path Parameters
conversation_id
required
integer (Conversation Id)

Responses

Response samples

Content type
application/json
null

agents

Create Agent

Deploy an Autonomous Agent

Transforms a static workflow into a dynamic, autonomous agent. Agents are the "living" versions of your automations that can run on schedules or respond to events.

When to deploy an agent:

  • When you need a workflow to run periodically (e.g., every hour).
  • When you want an AI to monitor a channel (like WhatsApp or Slack) and take action automatically.
  • When building a complex, multi-stage business process that requires state management.

Configuration Overrides: You can pass specialized instructions to the agent during creation to fine-tune its "personality" or "reasoning" style beyond the basic workflow definition.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
workflow_id
required
integer (Workflow Id)

The unique ID of the workflow that this agent will automate. The workflow must exist and be accessible by the user.

Agent Config (object) or Agent Config (null) (Agent Config)

Optional configuration overrides for the agent, such as specific prompt instructions or execution parameters.

Responses

Request samples

Content type
application/json
{
  • "workflow_id": 42,
  • "agent_config": {
    }
}

Response samples

Content type
application/json
{ }

Create Agent

Deploy an Autonomous Agent

Transforms a static workflow into a dynamic, autonomous agent. Agents are the "living" versions of your automations that can run on schedules or respond to events.

When to deploy an agent:

  • When you need a workflow to run periodically (e.g., every hour).
  • When you want an AI to monitor a channel (like WhatsApp or Slack) and take action automatically.
  • When building a complex, multi-stage business process that requires state management.

Configuration Overrides: You can pass specialized instructions to the agent during creation to fine-tune its "personality" or "reasoning" style beyond the basic workflow definition.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
workflow_id
required
integer (Workflow Id)

The unique ID of the workflow that this agent will automate. The workflow must exist and be accessible by the user.

Agent Config (object) or Agent Config (null) (Agent Config)

Optional configuration overrides for the agent, such as specific prompt instructions or execution parameters.

Responses

Request samples

Content type
application/json
{
  • "workflow_id": 42,
  • "agent_config": {
    }
}

Response samples

Content type
application/json
{ }

Schedule Agent

Schedule an agent for automatic execution.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
agent_id
required
string (Agent Id)

The unique UUID of the agent to schedule.

required
object (Schedule Config)

Configuration for the execution schedule. Supports 'interval' (seconds) or 'cron' (standard cron expression).

Responses

Request samples

Content type
application/json
{
  • "agent_id": "string",
  • "schedule_config": {
    }
}

Response samples

Content type
application/json
{ }

Schedule Agent

Schedule an agent for automatic execution.

Authorizations:
HTTPBearer
Request Body schema: application/json
required
agent_id
required
string (Agent Id)

The unique UUID of the agent to schedule.

required
object (Schedule Config)

Configuration for the execution schedule. Supports 'interval' (seconds) or 'cron' (standard cron expression).

Responses

Request samples

Content type
application/json
{
  • "agent_id": "string",
  • "schedule_config": {
    }
}

Response samples

Content type
application/json
{ }

Get User Agents

Get all agents for the current user.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Get User Agents

Get all agents for the current user.

Authorizations:
HTTPBearer

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Get Agent Status

Agent Pulse & Health Monitoring

Retrieves deep diagnostic information and current health metrics for a specific agent.

Monitoring Data includes:

  • execution_count: Total number of times the agent has run.
  • success_count: Number of successful goal completions.
  • last_error: The last exception encountered (if any).
  • success_rate: Percentage of successful executions.

Use this endpoint to:

  • Build a health dashboard for your automations.
  • Trigger alerts if an agent's success rate falls below a threshold.
  • Inspect real-time performance of business-critical bots.
Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
{
  • "agent_id": "string",
  • "workflow_id": 0,
  • "workflow_name": "string",
  • "status": "string",
  • "trigger_type": "string",
  • "schedule": { },
  • "monitoring": { },
  • "performance_metrics": { },
  • "created_at": "string",
  • "updated_at": "string"
}

Get Agent Status

Agent Pulse & Health Monitoring

Retrieves deep diagnostic information and current health metrics for a specific agent.

Monitoring Data includes:

  • execution_count: Total number of times the agent has run.
  • success_count: Number of successful goal completions.
  • last_error: The last exception encountered (if any).
  • success_rate: Percentage of successful executions.

Use this endpoint to:

  • Build a health dashboard for your automations.
  • Trigger alerts if an agent's success rate falls below a threshold.
  • Inspect real-time performance of business-critical bots.
Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
{
  • "agent_id": "string",
  • "workflow_id": 0,
  • "workflow_name": "string",
  • "status": "string",
  • "trigger_type": "string",
  • "schedule": { },
  • "monitoring": { },
  • "performance_metrics": { },
  • "created_at": "string",
  • "updated_at": "string"
}

Pause Agent

Pause an autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Pause Agent

Pause an autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Resume Agent

Resume a paused autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Resume Agent

Resume a paused autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Delete Agent

Delete an autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Delete Agent

Delete an autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Execute Agent Manual

Manually execute an autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
Any of
property name*
additional property
any

Responses

Request samples

Content type
application/json
null

Response samples

Content type
application/json
null

Execute Agent Manual

Manually execute an autonomous agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
Any of
property name*
additional property
any

Responses

Request samples

Content type
application/json
null

Response samples

Content type
application/json
null

Get Agent Analytics

Get detailed analytics for an agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Get Agent Analytics

Get detailed analytics for an agent.

Authorizations:
HTTPBearer
path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Get Agent Templates

Get available agent templates and configurations.

Responses

Response samples

Content type
application/json
null

Get Agent Templates

Get available agent templates and configurations.

Responses

Response samples

Content type
application/json
null

templates

List Templates

Get list of all workflow templates.

query Parameters
Category (string) or Category (null) (Category)

Filter by category

Difficulty (string) or Difficulty (null) (Difficulty)

Filter by difficulty

Search (string) or Search (null) (Search)

Search term

Connection (string) or Connection (null) (Connection)

Filter by required connection

Responses

Response samples

Content type
application/json
{
  • "success": true,
  • "data": null,
  • "message": "string"
}

Get Categories

Get all template categories.

Responses

Response samples

Content type
application/json
{
  • "success": true,
  • "data": null,
  • "message": "string"
}

Get Template

Get a specific template by ID.

path Parameters
template_id
required
string (Template Id)

Responses

Response samples

Content type
application/json
{
  • "success": true,
  • "data": null,
  • "message": "string"
}

Use Template

Create a workflow from a template.

Authorizations:
HTTPBearer
path Parameters
template_id
required
string (Template Id)

Responses

Response samples

Content type
application/json
{
  • "success": true,
  • "data": null,
  • "message": "string"
}