bAIbysitter

bAIbysitter

A nanny agent that watches over your agent 🍼🤖, preventing any loss of money 💰 or slip-ups 🚫 by analyzing its transactions, facilitated by a network of sentinel agents and a multi-sig safe wallet

Created on 15th February 2025

•

bAIbysitter

bAIbysitter

A nanny agent that watches over your agent 🍼🤖, preventing any loss of money 💰 or slip-ups 🚫 by analyzing its transactions, facilitated by a network of sentinel agents and a multi-sig safe wallet

The problem bAIbysitter solves

The Problem
Agents are losing a lot of money by making bad transactions! Don’t blame them—they’re doing their best, but language models aren’t the best choice for making deterministic decisions.

There are various risks: hacks that manipulate the agent’s prompt to send its funds, rug pulls in tokens, agents investing in protocols without knowing the risks, or simply making poor market analysis decisions.

The Solution
Let’s give your agent a helping hand. Our goal is to protect the agent from transactions that could result in financial loss. To achieve this, we analyze the transactions the agent intends to send along with its reasoning. These transactions are then evaluated by a network of specialized bots/agents covering all the key risk areas: security, DeFi, and market errors.

How It Works
When a user’s agent wants to make a transaction, it sends it to our core app along with its reasoning in natural language. Our core app then forwards this transaction to a group of specialized bots/agents (DeFi, security, NFT pricing, etc.), which analyze whether the transaction could lead to a financial loss.

Next, our agent compares the bots’ responses with the original intent of the user's agent, rationally assessing whether the transaction aligns with the agent’s goal and if it poses a financial risk.

To implement this workflow, we use Safe Wallet multisig. The user's agent signs the original transaction, and then, based on the analysis, our agent applies the second signature to either authorize or block the transaction.

On our website, we have set up three bots for testing: one that analyzes if the token's risk level matches the type of investment we want to make (high, medium, or low risk), one that alerts us if someone is trying to drain our account such as through a prompt injection and a contract analyzer to detect malicious addresses.

Challenges we ran into

I had issues with different WebSockets for connections it was complicated to make multiple bots work together and handle concurrent calls without interrupting ongoing processes.

On the other hand, ensuring seamless communication between all services was a challenging task since the system consists of four distinct parts: the front end, the core app, three separate bots, and the babysitter agent. However, we managed to get everything working in the end.

Tracks Applied (5)

Smart Account Tooling - Connecting AI Agents with Safe: Core Infrastructure & Developer Tooling

Our project aligns with the track by building a core infrastructure that acts as a bridge between AI agents and Safe sma...Read More

Smart Account Tooling - Best Tools/Infra for Agent x Safe Communication

Our project aligns with the track by building a core infrastructure that acts as a bridge between AI agents and Safe sma...Read More

AI Advancement: Best-in-class

We're actively adapting this project by building a seamless integration platform where all agents can easily connect, le...Read More

Smart Account Tooling: Humans X AI

We fulfill this requirement by integrating an AI Agent as a second signer in our Safe multisig setup. When a user’s agen...Read More

Track: AWS Partnership

we deploy our proyect in AWS ec2 to get the ifra running

Discussion

Builders also viewed

See more projects on Devfolio