0 reply
0 recast
2 reactions
1 reply
0 recast
1 reaction
Agentic Ethereum was one of the first Blockchain/AI hackathons, and the goal was to explore how autonomous AI agents could revolutionize projects on Ethereum.
We observed that currently most ecosystem projects mixing AI and Web3 were chatbots with personalities posting about Web3 based on market context (or even stealing tweets and rephrasing them), which (imo) doesn't really help users or create value other than entertainment.
Our thinking was that DeFi is the best use case for autonomous behavior driven by context, to analyze, consume data, and make decisions.
Whether you're a seasoned trader or a newcomer looking for the next gem to invest in, you'll have to (or at least should) spend time reading, gathering data, analyzing and comparing data, and understanding current sentiment, narratives, and so on...
These are time-consuming tasks that we can delegate to an AI agent. π€ 1 reply
0 recast
1 reaction
An agent is simply a system that can understand data input, pick the right tool (which can be anything from an external API to a computing method) based on context, and understand and use the result to call another tool or to provide a result if its goal is achieved. π―
For us, most of the value in agents operating with blockchains lies in the time they can save us - that's it.
With a two-week building scope, we decided to tackle one time-consuming aspect of DeFi: whale tracking. So we built Whal-E. π
Whal-E actively discovers new whale wallets, evaluates their trading performance, and maintains a curated list of high-performing traders. When these tracked whales execute trades, it analyzes multiple factors including portfolio composition, market data, and relevant news to determine if the trade should be replicated.
For users who opt in, successful trades are automatically executed across their connected wallets, with optimizations for each user's specific balance and conditions. π 1 reply
0 recast
1 reaction
