> For the complete documentation index, see [llms.txt](https://whitepaper.aitech.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://whitepaper.aitech.io/agentforge/introduction/what-is-agent-forge.md).

# What is Agent Forge

Agent Forge is a visual workflow editor that enables you to build AI-powered applications by connecting blocks on a canvas. Drag and drop components to create chatbots, automation workflows, and data processing pipelines without writing code.

### What Makes Agent Forge Powerful

**Multi-Model AI Support** - Connect to OpenAI, Anthropic, Google, Groq, Cerebras, and local models through Ollama. Switch providers without rebuilding workflows.

**60+ Pre-Built Tools** - Gmail, Slack, Notion, Google Sheets, Airtable, Supabase, Pinecone, and more. Extensible architecture allows custom tool integration.

**Flexible Execution** - Run workflows via chat interface, REST API, webhooks, scheduled jobs, or trigger from external systems.

**Lite and Workflow Modes** - Start fast in a conversational workspace, then switch into the full workflow builder when you need visual orchestration, debugging, and deployment.

**Powered by $ACN** - Use ACN for wallet top-ups, exclusive yearly subscriptions, and staking-based deployment access for agents and workflows.

**Production Deployment** - Deploy as APIs. Built-in monitoring, logging, and error handling.

**Real-time Collaboration** - Work simultaneously with team members on the same workflow, like Google Docs for AI development.

Connect multiple AI models, integrate with 60+ services, and deploy production-ready applications through an intuitive visual interface designed specifically for AI development.

### Core Building Blocks

**Processing Blocks**

* **Agent** - Execute AI model inference with any LLM provider
* **API** - Connect to REST endpoints and external services
* **Function** - Run custom JavaScript for data processing

**Logic Blocks**

* **Condition** - Create branching logic based on data evaluation
* **Router** - Route execution paths using AI-powered decision making
* **Loop** - Iterate over collections sequentially
* **Parallel** - Execute multiple operations concurrently

**Output Blocks**

* **Response** - Format and return final workflow results
* **Evaluator** - Validate outputs against defined criteria

### Built-in Integrations

**AI Models**: OpenAI, Anthropic, Google, Groq, Cerebras, Ollama

**Communication**: Gmail, Slack, Telegram, WhatsApp, Microsoft Teams

**Data Sources**: Notion, Google Sheets, Airtable, Supabase, Pinecone

**Web Services**: Firecrawl, Google Search, Exa AI, Perplexity

**Development**: GitHub, Jira, Linear, browser automation

### Use Cases

**AI Assistants** - Build chatbots with web search, calendar access, and email capabilities

**Content Generation** - Create blog posts, social media content, and marketing materials

**Data Processing** - Extract insights from documents, analyze datasets, and generate reports

**Process Automation** - Automate business workflows with event-driven triggers

**API Orchestration** - Combine multiple services into unified endpoints

### Key Features

**Multi-Provider AI Support** - Switch between OpenAI, Anthropic, Google, and local models without rebuilding workflows

**Real-time Collaboration** - Work simultaneously with team members on the same workflow

**Production-Ready** - Built-in error handling, logging, and monitoring for production deployments

### Getting Started

Ready to build your first workflow? Our Getting Started guide will walk you through creating a customer support assistant in under 10 minutes.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://whitepaper.aitech.io/agentforge/introduction/what-is-agent-forge.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.