platoseedplatoseed
Autonomous Electrical Engineering
Our first product, Stillwind Search, makes finding an electronic part as easy as writing a text message. The search engine turns natural language queries into fine-grained specifications that are matched against our proprietary database of millions of parts. This is the first step towards autonomous electrical engineering.
Stillwind offers an autonomous electrical engineering product focus, starting with a search engine that converts natural language queries into fine-grained specifications to find electronic parts from a proprietary database. The goal is to enable faster, more exact part selection and serve as the first step toward autonomous electrical engineering.
Stillwind Search converts natural language queries into precise specifications and matches them against a proprietary database of millions of electronic parts. The product emphasizes semantic plus exact search, real-time digital and analog circuit modeling, and firmware-in-the-loop testing. It also highlights a spatial reasoning layer for placing and routing components and mentions real-time simulations of analog circuits to support fast trial-and-error development.
Who it’s for: Electrical engineers, embedded software developers, and hardware designers seeking faster, more exact part discovery and early-stage autonomous electrical engineering tooling.
In development with a waitlist for Stillwind Search; mentions of ongoing research and product development in areas like data foundation, semantic+exact search, and real-time simulations.
Co-founder & CEO @ Stillwind. Previously researched quantified complexity theory. Worked in Quantitative Engineering @ DRW. Studied CS @ ETH Zurich.
Co-founder & CPO @ Stillwind. Previously developed deep learning optimizers at ETH Zurich. Worked on Augento's RL, and databases at SMA. Studied CS B.S. at ETH Zurich, and was enrolled in Data Science M.S. at ETH Zurich.
Co-founder & CTO @ Stillwind Did CS at ETH Zürich. Did open source work on libp2p.
Co-founder & Chief Engineering Officer @ Stillwind. CS @ ETH Zürich. I’m a full-stack software engineer but specialize in networks, systems programming, and ML.
Improving your AI agents with reinforcement learning.
Augento offers reinforcement learning-based fine-tuning to align AI agents with user feedback, replacing traditional prompt engineering. It integrates with existing systems via a two-line code change, collects prompts/outputs in a UI, and enables high-level user guidance to post-train a model that can be swapped in with one click. They seek early design partnerships and testers.
Formerly “P2P Industries”, “Augento”
Next-Generation Power Electronics
AI to understand engineering work
