Frontend ownership and full-stack delivery
Sherlock AI
An AI-powered smart contract security product. I owned its frontend and built full-stack AI workflows from repository analysis through findings and remediation.
Project context
Sherlock AI is Sherlock’s development-stage security product for Web3 teams. It analyzes smart contract code during development so teams can catch risky logic and likely vulnerabilities earlier.
I was responsible for all frontend implementation, building it from scratch while collaborating closely with a designer on UI/UX and contributing to product decisions as the system evolved. Together, we turned a technically dense security workflow into an interface teams could use throughout development.
My work extended beyond the interface. I implemented end-to-end product features and contributed to model integration, prompting, and benchmarking across the AI analysis workflow.
The product integrates with engineering workflows such as GitHub repositories, commits, and pull requests, giving teams visibility into vulnerabilities and attack paths tied to the code they are releasing.
My contribution
- Owned all frontend implementation, building it from scratch with Next.js and TypeScript.
- Delivered end-to-end features across repository setup, analysis runs, findings review, code context, and remediation.
- Integrated AI models and worked on prompting and benchmarking to improve analysis quality.
- Collaborated closely with a designer on UI/UX and contributed product and interaction decisions as requirements evolved.
Customers
Sherlock AI is used by Web3 engineering teams and is presented by Sherlock alongside protocols and ecosystems including Aave, Ethereum Foundation, Arbitrum, MegaETH, Sky.money, Optimism, Tempo, and Centrifuge.
“We’ve tried many different AI audit tools, and none come even close to Sherlock AI. Other tools are either good at PR runs or manual runs. Sherlock AI is by far the best combination of both.”