Skip to content
Open
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -21,24 +21,24 @@ keywords:

# Use AI To Build On Flow

Artificial Intelligence tools can significantly enhance your Flow development experience by providing intelligent assistance, code generation, and documentation access. This tutorial series will guide you through integrating various AI tools with Flow development to boost your productivity and code quality.
Artificial Intelligence (AI) tools can significantly enhance your Flow development experience by providing intelligent assistance, code generation, and documentation access. This tutorial series will guide you through integrating various AI tools with Flow development to boost your productivity and code quality.

## What You'll Learn

In this tutorial series, you'll discover how to:

- Configure AI-powered development environments for Flow
- Access Flow documentation directly from AI assistants
- Generate Cadence and Solidity code with AI assistance
- Debug and troubleshoot Flow applications with AI support
- Leverage AI for testing and optimization
- Build AI agents that interact with Flow using AgentKit
- Configure AI-powered development environments for Flow.
- Access Flow documentation directly from AI assistants.
- Generate Cadence and Solidity code with AI assistance.
- Debug and troubleshoot Flow applications with AI support.
- Leverage AI for testing and optimization.
- Build AI agents that interact with Flow using AgentKit.

# AI Tutorials for Flow

## Using Claude Code with Flow

Master systematic AI-powered Flow development with Claude Code, a terminal-integrated coding assistant designed for iterative blockchain development. This comprehensive guide teaches you to implement a four-stage development methodology (Idea → Visualization → Planning → Build) while leveraging unlimited context windows, subagent capabilities, and persistent project memory. Learn to configure CLAUDE.md files for Flow-specific instructions, integrate MCP servers for blockchain interactions, and implement checkpoint-based workflows that ensure reliable smart contract development from emulator to mainnet deployment.
Master systematic AI-powered Flow development with Claude Code, a terminal-integrated coding assistant designed for iterative blockchain development. This comprehensive guide teaches you to implement a four-stage development methodology (Idea → Visualization → Planning → Build) while leveraging unlimited context windows, subagent capabilities, and persistent project memory. Learn to configure `CLAUDE.md` files for Flow-specific instructions, integrate MCP servers for blockchain interactions, and implement checkpoint-based workflows that ensure reliable smart contract development from emulator to mainnet deployment.

Tutorial: [Claude Code for Flow Development]

Expand All @@ -50,7 +50,7 @@ Tutorial: [Use Flow Knowledge Base in Cursor]

## Using Chat GPT with Flow

Build your own expert AI assistant by creating a custom GPT specifically engineered to master the Flow blockchain and its Cadence smart contract language. This specialized tool will act as your personal pair programmer, providing highly accurate and context-aware answers to your most challenging development questions. By doing this, you're not just using a generic AI; you're creating a specialist trained on the exact documentation, code patterns, and best practices relevant to your work.
Build your own expert AI assistant by creating a custom GPT specifically engineered to master the Flow blockchain and its Cadence smart contract language. This specialized tool will act as your personal pair programmer, providing highly accurate and context-aware answers to your most challenging development questions. By doing this, you're not just using a generic AI, you're creating a specialist trained on the exact documentation, code patterns, and best practices relevant to your work.

Tutorial: [Use Flow Knowledge Base in ChatGPT]

Expand All @@ -62,19 +62,19 @@ Tutorial: [Data Sources]

## Eliza Integration

Learn about using Eliza on Flow, a versatile framework for constructing sophisticated AI agents that communicate with users through natural language. This guide walks you through the entire process of configuring and launching an AI agent built with Eliza directly onto the Flow blockchain. You will discover how to engineer intelligent agents capable of comprehending and addressing user prompts, all while harnessing the power of Flow's inherently secure and scalable onchain infrastructure.
Learn about how to use Eliza on Flow, a versatile framework for constructing sophisticated AI agents that communicate with users through natural language. This guide walks you through the entire process of configuring and launching an AI agent built with Eliza directly onto the Flow blockchain. You'll discover how to engineer intelligent agents capable of comprehending and addressing user prompts, all while harnessing the power of Flow's inherently secure and scalable onchain infrastructure.

Tutorial: [Eliza on Flow]

## Build AI Agents with AgentKit

Learn how to build AI agents on Flow with AgentKit, a versatile and modular developer toolkit that is not tied to any single platform. It is engineered to dramatically accelerate the process of building, deploying, and refining AI agents by supplying pre-configured environments and a library of ready-to-use templates. This guide will walk you through the steps to launch your own custom agent on Flow's EVM-compatible testnet, leveraging the powerful combination of the Langchain framework and Anthropic's Claude large language model.
Learn how to build AI agents on Flow with AgentKit, a versatile and modular developer toolkit that is not tied to any single platform. It's engineered to dramatically accelerate the process of building, deploying, and refining AI agents by supplying pre-configured environments and a library of ready-to-use templates. This guide walks you through the steps to launch your own custom agent on Flow's EVM-compatible testnet, leveraging the powerful combination of the Langchain framework and Anthropic's Claude large language model.

Tutorial: [Build AI Agents with AgentKit]

## MCP Guides

Learn how to construct a custom Flow MCP (Model Context Protocol) server or utilize an existing one to empower your AI tools. These tutorials will guide you through the process of equipping your AI applications with the unique capability to directly interact with the Flow blockchain, enabling them to perform onchain operations and access real-time data.
Learn how to construct a custom Flow MCP (Model Context Protocol) server or use an existing one to empower your AI tools. These tutorials guide you through how to equip your AI applications with the unique capability to directly interact with the Flow blockchain, which allows them to perform onchain operations and access real-time data.

Tutorial: [Flow MCP]

Expand All @@ -86,22 +86,22 @@ Tutorial: [Cadence Rules]

## Best Practices

When using AI tools with Flow development:
When you use AI tools with Flow development:

- Always verify AI-generated code against Flow documentation
- Use specific prompts that reference Flow concepts and terminology
- Combine AI assistance with your own understanding of Flow architecture
- Keep your AI tools updated with the latest Flow documentation
- Test AI-generated code thoroughly before deploying to production
- Consider the security implications of AI agents interacting with your contracts
- Always verify AI-generated code against Flow documentation.
- Use specific prompts that reference Flow concepts and terminology.
- Combine AI assistance with your own understanding of Flow architecture.
- Keep your AI tools updated with the latest Flow documentation.
- Test AI-generated code thoroughly before deploying to production.
- Consider the security implications of AI agents interacting with your contracts.

## Next Steps

After completing these tutorials, you'll be equipped to leverage AI tools effectively in your Flow development workflow. Consider exploring our other tutorial series to deepen your understanding of Flow development:
After compleyou completeting these tutorials, you'll be equipped to leverage AI tools effectively in your Flow development workflow. Consider exploring our other tutorial series to deepen your understanding of Flow development:

- [Cross-VM Apps][cross-vm-apps] - Build applications that integrate Flow EVM and Cadence
- [Native VRF][native-vrf] - Implement verifiable random functions in your applications
- [Token Launch][token-launch] - Create and launch tokens on Flow
- [Cross-VM Apps][cross-vm-apps] - Build applications that integrate Flow EVM and Cadence.
- [Native VRF][native-vrf] - Implement verifiable random functions in your applications.
- [Token Launch][token-launch] - Create and launch tokens on Flow.

## Conclusion

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,11 @@ keywords:

# Use Flow Knowledge Base in ChatGPT

[ChatGPT] is an AI assistant developed by [OpenAI] that can help with tasks such as writing, coding, and answering questions. It adapts to context and user input to provide relevant, conversational responses. ChatGPT can be integrated into developer tools or workflows to assist with documentation, debugging, and productivity.
## Overview

This guide walks you through creating a **Custom GPT** using ChatGPT that can reference the [Flow Data Sources] file to answer questions.
[ChatGPT] is an AI assistant developed by [OpenAI] that can help with tasks such as writing, coding, and answering questions. It adapts to context and user input to provide relevant, conversational responses. You can integrate ChatGPT into developer tools or workflows to assist with documentation, debugging, and productivity.

This guide walks you through how to create a **Custom GPT** with ChatGPT that can reference the [Flow Data Sources] file to answer questions.

<div style={{ position: 'relative', paddingBottom: '56.25%', height: 0, overflow: 'hidden', maxWidth: '100%' }}>
<iframe
Expand Down Expand Up @@ -50,7 +52,7 @@ You'll need a [ChatGPT Plus subscription] to use the **Custom GPT** feature.

## 📍 Step 2: Click "Create a GPT"

1. In the **Explore GPTs** screen, click the **"Create"** button in the top-right corner.
1. In the **Explore GPTs** screen, click **"Create"** in the top-right corner.

![create](./imgs/create.png)

Expand All @@ -74,7 +76,7 @@ ChatGPT may ask you to customize or verify:

- **Name and description** of your GPT
- **Instructions**: Tell it how to behave and what to prioritize (e.g., always reference the uploaded document)
- **Capabilities**: Enable file browsing, code interpreter, or DALL·E if needed
- **Capabilities**: Allow file browsing, code interpreter, or DALL·E if needed

We've found it helpful to suggest:

Expand All @@ -88,7 +90,7 @@ Please let us know if you find any other useful customization prompts!

## 📍 Step 5: Test Your GPT

Once the GPT is built, you'll be taken to a preview chat window. Test it by asking a few questions based on your uploaded document.
After the GPT is built, a preview chat window will appear. To test it, ask a few questions based on your uploaded document.

---

Expand Down
Loading