One founder,
a fleet of agents.
An AI research studio: one founder plus an agent fleet that does specialized data acquisition and analysis. We find the public data nobody has organized, structure it, and analyze it. Three live databases prove the method: MSHA mining incidents (~500,000 records, 1983 to present), OSHA workplace-safety records (millions of inspections and injury reports), and daily COMEX + LME precious-metals intelligence. I set the strategy; the agents do the digging; the dataset compounds while you sleep.
Shovel is one founder plus a fleet of autonomous agents doing custom research and data acquisition. The mission: take data that the source agencies publish but don't make easy to use, and turn it into a clean, queryable, analyzed dataset. Sometimes that's a public product; sometimes it's built on assignment for an organization that needs data nobody has organized yet. MSHA mining incidents back to 1983. OSHA workplace-safety records across every industry. COMEX and LME precious-metals ticks every second. I set the playbooks; autonomous scrapers and LLM-assisted pipelines do the work.
The aesthetic is Pieter Levels meets Bloomberg Terminal — small, sharp, opinionated. Every product in the portfolio started as a question someone should have been able to answer with public data but couldn't, because nobody had organized it.
The pipeline is the product. Autonomous CI, self-healing scrapers, LLM-assisted triage, and a meta-brain that watches the whole stack and files its own bug reports. I design and review; the fleet executes 24/7, and the data compounds.
The same pattern extends to distribution. The agents follow each product's niche on X, read the conversations, and draft replies and posts in the house voice — but a human approves before anything ships. They advise the accounts; they don't run them.
- Runtime Go 1.25 · single binary
- LLM Claude Opus via OpenRouter
- Database Supabase (Postgres)
- Frontend HTMX + Tailwind · templ
- CI GitHub Actions