Video thumbnail

Panda Trade

AI-powered multi-token trading based on your risk and interests.

Panda Trade

Created At

ETHGlobal Prague

Winner of

Blockscout - Big Blockscout Explorer Pool Prize

Prize Pool

Project Description

Panda Trade is an AI-assisted multi-token trading tool designed for crypto users who want to execute smarter, more personalized trades without complex research.

The user starts by connecting their wallet and choosing a blockchain network. Then they input the amount they want to trade in USDC, select their preferred risk level (safe or risky), and choose interest categories from a multi-select list — such as Meme, DeFi, RWA, Blue Chip, Gaming, AI, Infrastructure, DAO, Low Cap, Short Term, Long Term, or High Liquidity.

Our system uses this data as input for an AI model, which returns a recommended multi-token trade – including selected tokens and suggested allocation percentages.

The user can review the proposed trade, and if satisfied, confirm it to execute the entire multi-token purchase in one step.

Panda Trade saves time, reduces decision fatigue, and offers a fun and simple way to explore crypto trading based on personal interests and risk profile — with help from the most intelligent panda in Web3.

How it's Made

Github repos: https://github.com/lebrande/panda-trade https://github.com/Cezary24/ETHGlobal-Prague-vlayer

We used VLayer for we proing that the answer really comes from LLM and it's not spoofed. We used Blockscout to get tokens data to feed our LLM engine, also we used Blockscout SDK to provide best in class UX and transactions feedback.

Other technologies:

  • Vercel
  • Odos aggregator
  • Rainbowkit
  • OpenAI
  • Next.js
  • viem + wagmi
  • Alchemy

Product presentation:

  • User starts the journey with selecting:
    • USDC amount
    • risk appetite
    • tags or topics of their today investments
  • In the second step Panda finds the best match
    • using Blockscout API data about tokens
    • sends that data to LLM
    • LLM answers with 5 matches combining Blockscout data and user preferences
  • User sees the breakout of selected tokens
    • Panda uses Odos agregator to create a multiswap
    • USDC in the input
    • all selected tokens on output
    • with proportion of Panda's choice
  • In meantime we use VLayer to generate Web Proof
    • we proove that the answer really comes from LLM and it's not spoofed
    • Then transaction is supposed to run only if the ZK proof is attached to the calldata
  • Finally user approves the ERC20 transfer and executes the trade
    • Panda uses Blockscout SDK to display feedback for all the transactions
    • toast messages pops out everytime users sings the transaction
    • last screen shows the output from Blockscout API showing transfer details
  • Moreover uses can lookup their all recent transactions
    • Panda Trade uses Blockscout SDK to present that in the popup
background image mobile

Join the mailing list

Get the latest news and updates