About · Shovel

A crack team of
data nerds.

A focused team building AI-driven public-records databases — MSHA mining incidents (~500,000 records, 1983 to present), OSHA severe-injury reports (every record since the 2015 reporting rule), and daily COMEX + LME precious-metals intelligence. We set the strategy; the agents do the digging; the dataset compounds while you sleep.

Shovel is a small team building AI-enabled data products. The mission: take US public records that the source agencies publish but don't make easy to search, and put them behind a working search box. MSHA mining incidents back to 1983. Every OSHA severe-injury report since 2015. COMEX and LME precious-metals ticks every second. Domain-focused humans 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. The team designs and reviews; the fleet executes 24/7 — and the data compounds.

Stack · as of 2026
  • Runtime Go 1.25 · single binary
  • LLM Claude Opus via OpenRouter
  • Database Supabase (Postgres)
  • Frontend HTMX + Tailwind · templ
  • CI GitHub Actions
No React. No hydration. No build-tool churn. The team designs; the agents execute.
The portfolio
Mining Incidents live

Searchable research tool for US mining safety records.

miningincidents.org →
Safety Incidents live

Searchable research tool for US workplace safety records.

safetyincidents.org →
The Vault Report live

Precious metals intelligence.

thevaultreport.com →