Intent-centric Wallet via Account Abstraction and AI Agent

Inspiration

The current Web2 is based on Apps, which are isolated and closed. As a result, few super Apps become giant platforms and suppress other innovative and thriving small business to maximize their self-interests for centralization and monopoly. With the barriers among Apps, users have to go through each App by themselves to find and get what they need, which is extremely inconvenient and inefficient. Therefore, to enable users to directly meet their demands, we need Web3 to make Apps fully interconnected, interoperable, and composable with each other without barriers and isolation. However, the threshold, complexity and difficulty of user interactions and operations in Web3 are still too high to make Web3 usable for the ordinary users. For instance, if users want to convert USDT stablecoin in Ethereum into ARB token on Arbitrum, they need to find a suitable cross-chain bridge, connect to their account, then transfer their USDT and gas fee from Ethereum to Arbitrum, and then find a suitable DEX to exchange USDT for ARB with gas fee. It's so challenging, complicated, and troublesome for most users to understand and finish these steps by themselves. They have no way to simply express "I want to convert USDT into ARB", and then directly get ARB without taking all those actions above by themselves. In order to do so, Web3 should support AI agent to intelligently analyze user demands and automatically run Apps to perform the corresponding operations in Apps for users, so users don't need to manually do so by themselves.

What it does

Enabled by account abstraction (AA) and AI agent, our project upgrades the user interfaces in crypto wallets and achieves demand abstraction as the ultimate way of user interaction in Web3 more natural, straightforward, and efficient than the current Web2 interaction based on Apps. With demand abstraction, users can directly express and meet their demands without going through specific accounts, DApps, and blockchains. After users specify their demands via user interface, text, or speech as inputs in our wallet, our underlying AI agents will intelligently understand and analyze what users need, generate the best solution schemes to meet the demands of users and match the DApps and chains according to the solution scheme. After users check and approve the solution scheme, their AA account will automatically execute the solution scheme including running the corresponding DApps and operating multiple crypto assets to make transactions for users, and finally get what users want as execution results back to them. In this way, users can directly get what they need easily. Our demand abstraction solution is fully open and decentralized. Although we will make a wallet as a sample to demonstrate and validate our demand abstraction, the demand abstraction functionality is open to all wallets to call and use. The third-party agents in AI and bundlers in AA are fully permissionless and decentralized, opening to all nodes to run and compete. After getting the execution results from third-party agents and bundlers, users can self-verify their correctness via the smart contract of AA as validation like zero-knowledge proofs.

How we built it

Web3 and Blockchain: Based on blockchain, Web3 can break the barriers and isolation of Web2 Apps for full interconnectivity, interoperatblity, and composablity among Web3 Apps. Web3 can also support automatic execution within Apps, so users don't need to manually operate each App by themselves.
AI Agent: AI can intelligently understand the inputs of users via interface, text or speech to precisely analyze and get the demand of users. To meet user demands, AI will find, compare, choose, and combine all different Apps to generate the best solution schemes including what operations should be performed on which Apps. Account Abstraction: The decentralized bundlers enabled by account abstraction based on ERC-4337 can run their AI agent to generate the solution schemes for users. After getting users' authorization, they will execute the solution scheme to run and operate different Apps for users. Finally, they will get what users need back to users as the execution results. Different bunlders will compete with each other, so users can choose the best one to best meet their own demands. Zero-knowledege Proofs: Users can easily and quickly verify the correctness and effectiveness of both solution schemes and execution results provided by the bundlers. Users can also protect the privacy of their demands from being known or leaked by bundlers when getting and analyzing the demand of users.

Challenges we ran into

Security: As AA and AI are emerging new technologies, we will have high standards of security development and testing to make our project as secure and reliable as possible without fatal bugs. We will also do internal and external auditing for our code before launching our product in public. Privacy: As our project will collect and handle personal identity and sensitive trading information for our users to provide personalized and intelligent Web3 services for them, we will make our wallet fully non-custodial and self-sovereign to protect the privacy of our users. We will also apply privacy-preserving techniques like ZKP to prevent personal data and information from being leaked by any third party including ourselves. Integrity: As our project will use AI to recommend and execute the optimal solutions for our users to directly meet their demands, we need to ensure the solutions we recommend are really the best, and the execution results we get after running those solutions are really correct. In order to do so, we will enable users to use AA to self-verify the effectiveness and correctness of the solutions and their execution results we provide via techniques like ZK.

Accomplishments that we're proud of

We got the prize from Arweave

What we learned

Compared with the existing Web3 and AI projects without our demand abstracrtion, our demand abstraction is directly based on user demands rather than specific Apps or blockchains. Users just need to express what they want and we will take all the following steps and actions for them to meet their needs, so they can directly get what they want without going through the detailed process behind by themselves. In this way, we can attract and benefit more users to better use Web3 easily even if they can’t operate crypto assets and DeFi protocols on blockchain well. There are also some products trying to directly meet the demands of users called intent-centric like Unibot and Anoma. Compared with these intent-centric projects, we further upgrade intent-centric to demand abstraction with AA and AI. Under the current intent-centric projects, users still need to know blockchain and Web3 well as they need to express very specific intentions like "buy and stake ETH in Lybra Finance." However, new crypto users may not know ETH staking or Lybra Finance as they just want to trade and earn. Therefore with AA and AI, our demand abstraction allows users to just specify their demands like "I want to earn stable returns with low risks", then we will analyze their demands and give the corresponding solution schemes like "buy and stake ETH in Lybra Finance”. After getting the approval of users, we will execute the solution scheme for users to meet their needs accordingly.

What's next for Intent-centric Wallet via Account Abstraction and AI Agent

The goal of our marketing is to attract both Web2 and Web3 users, so we will make different marketing strategies for different groups of users accordingly. For users from Web2, our highlight is we can provide more natural, straightforward, and frictionless usage experience based on their demands better than Web2 based on Apps. For existing Web3 users, we will emphasize we will greatly lower the threshold, complexity, and difficulty of user interactions and on-chain operations on Web3. Tell and then get what you need. So easy and simple. We will launch our token to motivate and assist our users, bundlers, and Apps for a thriving ecosystem in our demand abstraction. Our token will facilitate users to pay for transaction fees, solution generation, and automatic execution. We will also reward ecosystem partners, seed users, and community contributors to encourage more people to join, improve, and contribute to the ecosystem of our demand abstraction. We plan to launch the first version by the end of this year with unique, innovative and valuable use cases. They can onboard the first round of new users and we will start building our user community to preserve them. With more users, we can attract more developers and with their Apps, and thus attract more and more users to form a positive cycle with network effect.

Built With

• abstraction
• account
• ai