🤖Why an Intent Recognition Engine?
The first Intent Recognition Engine for web3, designed for Agents and Humans.
Last updated
The first Intent Recognition Engine for web3, designed for Agents and Humans.
Last updated
From the first day we started working on Brian one year and a half ago (this was a hackathon project; here is the full story), we have been firmly convinced about how, in a few years, most of the on-chain transactions would be either be performed by autonomous AI Agents or users via intent-based apps, like our non-custodial Brian App.
To achieve that and unleash tons of new possible use cases on top of both technologies, we need a better system to recognize any intent of Web3 interactions from users and agents, whether it is a transaction to make, a request for information, or data of a protocol, or a smart contract to deploy.
That’s how we started building an “Intent Recognition and Execution Engine” that can power the next generation of autonomous Agents and intent-based apps for users. The Brian architecture (Fig. 1), which represents the end-to-end flow of our API, can be split into two components:
The Intent Recognition Engine: the component that receives the textual input and, via the Brian AI models, understands what the user/agent intent is.
The Intent Execution Engine: the component that builds the API output via a series of existing off-chain tools and, for TXs, on-chain aggregators/solvers in the market.
While working on the Intent Recognition Engine and talking with partners in the space, we explored this specific AIxWeb3 niche, and we quickly realized that an element was missing in this market: no one has released a domain-specific model tailored for web3 yet. It is well-known in the scientific community that smaller domain-specific models can achieve better performance at lower inference costs than larger models.
