Verifiable AI Agents on Ethereum: Trustless Automation via MCPChain

AI agents are black boxes, risky for high-stakes use. MCPChain builds Ethereum's on-chain trust layer, enabling verifiable, auditable AI. Discover how to unlock secure, accountable automation for DeFi & beyond. Build bots you can prove and trust.

AI agents promise revolutionary automation, but today they operate as unaccountable black boxes, risky for DeFi, DAO governance, and enterprise. This talk introduces MCPChain: an on-chain trust layer for AI. It enables agents to securely access off-chain tools and verifiably log interactions. MCPChain features a decentralized Tool Registry, a curated “app store” where tool providers

• 45-minute systems interview, focus on responding to real world problems with an unhealthy service, such as a web server or database. The interview will start off at a high level troubleshooting a likely scenario, dig deeper to find the cause and some possible solutions for it. The goal is to probe your knowledge of systems at scale and under load, so keep in mind the challenges of the Facebook environment.
• Focus on things such as tooling, memory management and unix process lifecycle.

More specifically, linux troubleshooting and debugging. Understanding things like memory, io, cpu, shell, memory etc. would be pretty helpful. Knowing how to actually write a unix shell would also be a good idea. What tools might you use to debug something? On another note, this interview will likely push your boundaries of what you know (and how to implement it).

Interview is all about taking an ambiguous question of how you might build a system and letting

Student: Deeptanshu Sankhwar Project: Modernize iD Editor Session Management with IndexedDB Milestone 1 Focus: Replace localStorage with IndexedDB as the default session store, including data migration, resilience, and unit-tested abstractions. This plan incorporates findings from PR #10619.

• Codebase Familiarization (Targeted Review):

HorizonML explores decentralized model training by implementing and benchmarking data-parallel, layer-parallel, and tensor-parallel strategies across simulated nodes. The project aims to challenge centralized AI training pipelines by laying the groundwork for a modular, trustless training framework.

https://github.com/Deeptanshu-sankhwar/horizonml/blob/main/assets/HorizonML.pdf

1. Cudos Foundation
2. Stacks Foundation
3. Ethereum Foundation
4. VeChain
5. BNB Chain
6. Conflux
7. Provenance Blockchain
8. Stellar Foundation

The chi-square ($\chi^2_{\text{}}$) test allows you to compare the number of organisms your group collected (observed) to what would be expected based on the total class data. It helps assess whether your sample differs significantly from the expected class distribution.

Team Member: Solo Project

Below is the task breakdown in logical order, ensuring we get a working MVP quickly and refine it iteratively.

✅ 1. Set up the Go project structure

• Initialize a Go module (go mod init chaoschain)
• Define core packages (e.g., core, crypto, p2p, state, validator, producer)
• Identify dependencies (e.g., go-ethereum, gorilla/mux, openai, jsonrpc)

Length: 350 hours

Full Name: Deeptanshu Sankhwar