LIVE ON ARC TESTNET

Documentation

Everything you need to know about using CiteFlowAI, whether you are researching topics or registering your own intellectual property.

What is CiteFlowAI?

CiteFlowAI is a decentralized AI research terminal designed to fix the creator compensation problem in generative AI. Currently, AI models are trained on millions of articles, but the original authors receive no compensation when their work is used to generate answers.

CiteFlowAI changes this by introducing Pay-Per-Prompt Citations. When our AI agent synthesizes an answer using a registered knowledge base, it explicitly cites its sources and uses Circle Programmable Wallets to instantly execute USDC nanopayments to the original creators on the Arc Testnet.

For Researchers (Users)

1. Connect a Web3 Wallet (No Seed Phrase Needed)

You don't need a crypto extension like MetaMask to use CiteFlowAI. We use Circle's User-Controlled Wallets to generate a secure Web3 wallet bound to your email address, which acts as your universal login!

  • Click Connect Wallet in the top navigation bar.
  • Enter your email address and verify with the One-Time Password (OTP).
  • Create a secure PIN code to authorize future transactions.
  • You are now invisibly authenticated to our backend! Your wallet address is your identity.

2. Get Testnet USDC

Since CiteFlowAI currently operates on the Arc Testnet, you need free Testnet USDC to pay for AI prompts.

  • Copy your connected wallet address from the top navigation bar.
  • Click the blue Droplet Icon in the navigation bar to open the Circle Faucet.
  • Paste your address and request USDC on the Arc Testnet.
  • Wait a few seconds, and your balance will automatically update in the app!

3. Ask the AI

Once your wallet is funded, you can query the AI. You set a "Max Budget" for the prompt (e.g., $0.50).

  • The funds are temporarily authorized using your PIN code.
  • The AI retrieves relevant articles from our vector database and writes an answer.
  • Based on which articles were actually cited, the smart contract settles the payment, distributing the exact citation fees to the respective authors.

For Creators (Authors)

1. Universal Identity (Circle + Supabase)

There are no separate "user" or "creator" accounts, and absolutely no passwords. Your Circle Wallet is your entire identity. The moment you connect your wallet via the navbar, our backend automatically maps your address to your creator profile. You never have to manually configure payment settings!

2. Registering Articles

Navigate to the Register Work page. Here, you can upload the contents of your research, blog posts, or intellectual property.

  • Provide the Title, URL, and the full content of your article.
  • Set your own Citation Price in USDC (e.g., $0.10 per citation).
  • Your content is chunked, embedded into our Vector Database, and made available to the AI agent.

3. Tracking Earnings

The Dashboard provides a live view of your intellectual property.

  • View all your registered articles.
  • See exactly how many times each article has been cited by the AI.
  • Watch your USDC balance grow in real-time as users interact with the network.

Circle Web3 Architecture

CiteFlowAI is built on top of Circle Web3 Services to provide a seamless, gasless experience for non-crypto native users while maintaining decentralized settlement.

  • User-Controlled Wallets: We use Circle's Web SDK to generate embedded wallets via Email OTP. No seed phrases are required.
  • Master Treasury Escrow: To prevent forcing researchers to manually sign 5 separate transactions to pay 5 different authors, CiteFlowAI uses a Master Treasury Wallet. Researchers sign a single PIN-authorization for their "Max Budget" which is routed to the Treasury.
  • Programmatic Smart Contract Routing: Once the AI agent finishes a task and determines which sources were cited, our backend securely uses Circle's Developer-Controlled Wallets API to execute batch nanopayments from the Treasury directly to the cited authors.
  • Arc Testnet: All transactions are executed securely on the Arc Testnet using USDC.