> 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/execution-engine.md).

# Execution Engine

Agent Forge's execution engine brings your workflows to life by processing blocks in the correct order, managing data flow, and handling errors gracefully.

{% hint style="info" %}
Every workflow execution follows a deterministic path based on your block connections and logic, ensuring predictable and reliable results.
{% endhint %}

### Documentation Overview

### Key Concepts

#### Topological Execution

Blocks execute in dependency order, similar to how a spreadsheet recalculates cells. The execution engine automatically determines which blocks can run based on completed dependencies.

#### Path Tracking

The engine actively tracks execution paths through your workflow. Router and Condition blocks dynamically update these paths, ensuring only relevant blocks execute.

#### Layer-Based Processing

Instead of executing blocks one-by-one, the engine identifies layers of blocks that can run in parallel, optimizing performance for complex workflows.

#### Execution Context

Each workflow maintains a rich context during execution containing:

* Block outputs and states
* Active execution paths
* Loop and parallel iteration tracking
* Environment variables
* Routing decisions

### Execution Triggers

Workflows can be executed through multiple channels:

* **Manual**: Test and debug directly in the editor
* **Deploy as API**: Create an HTTP endpoint secured with API keys
* **Deploy as Chat**: Create a conversational interface on a custom subdomain
* **Webhooks**: Respond to external events from third-party services
* **Scheduled**: Run on a recurring schedule using cron expressions

#### Deploy as API

When you deploy a workflow as an API, Agent Forge:

* Creates a unique HTTP endpoint: `https://staging.Forge.io/api/workflows/{workflowId}/execute`
* Generates an API key for authentication
* Accepts POST requests with JSON payloads
* Returns workflow execution results as JSON

Example API call:

```bash
curl -X POST https://forge.aitech.io/api/workflows/your-workflow-id/execute \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"input": "your data here"}'
```

#### Deploy as Chat

Chat deployment creates a conversational interface for your workflow:

* Hosted on a custom subdomain: `https://your-name.simstudio.ai`
* Optional authentication (public, password, or email-based)
* Customizable UI with your branding
* Streaming responses for real-time interaction
* Perfect for AI assistants, support bots, or interactive tools

Each deployment method passes data to your workflow's starter block, beginning the execution flow.

### Best Practices

#### Design for Reliability

* Handle errors gracefully with appropriate fallback paths
* Use environment variables for sensitive data
* Add logging to Function blocks for debugging

#### Optimize Performance

* Minimize external API calls where possible
* Use parallel execution for independent operations
* Cache results with Memory blocks when appropriate

#### Monitor Executions

* Review logs regularly to understand performance patterns
* Track costs for AI model usage
* Use workflow snapshots to debug issues

### What's Next?

Start with [Execution Basics](file:///execution/basics) to understand how workflows run, then explore [Logging and Cost Calculation](file:///execution/advanced) to monitor and optimize your executions.