AI Engineer at Solidus AI Tech. I work on agent orchestration, high-throughput data pipelines, and the developer tools that sit on top — usually end to end, backend through UI.
// automation · blockchain · developer tools
Agent platforms, indexers, a native game, and a few on-chain apps — most built end to end, from data pipeline to UI.
A visual editor for building AI workflows by dragging blocks onto a canvas — no code. Connect any model (OpenAI, Anthropic, Google, Groq, or local through Ollama), wire in 60+ tools like Gmail, Notion and Supabase, and ship the result as an API, webhook or scheduled job. I architected the backend and built the meta-agent that turns a plain-language prompt into a working workflow.
A high-throughput indexer wired to a self-hosted Farcaster hub through a sharded pipeline, pushing events to Kafka. I built the developer APIs and a Scanner dashboard that streams live network activity.
A fast PvP trivia game for iOS, built in Swift — real-time duels, daily topics, ranks and leaderboards. It started as a Farcaster mini-app; it's now a fully standalone native app with a brand-new design.
Hides the blockchain so people can connect, chat and send funds using readable Farcaster or Base names instead of wallet addresses.
A project-funding forum where people submit Marginal Utility Curves for per-dollar impact. The backend is serverless — GitHub Gists linked through Farcaster casts, no database.
Most of what I do is making AI agents actually useful — connecting them to real APIs and MCP servers, and keeping huge responses from blowing past the model's context window.
At Solidus AI Tech I built a Python agent orchestrator, shipped 25+ specialized agents, and built Agent Forge — a visual workflow platform with a meta-agent that turns plain language into working workflows. Before that, two years at Deloitte on Salesforce → NetSuite integrations and automation.
// off the clock: gaming, marathons, and a lot of reading