Use it with Claude Code
No install, no code, no API to learn. Give Claude Code (or any coding agent) one URL and ask crash-baseline questions in plain English. It makes the calls, reads the result, and hands back the rate with its confidence interval — plus a link that opens the tool on the matching view.
Setup
- Put your API key in the environment (request one):bash
export HUMANBASELINES_API_KEY="hbk_..." - Point Claude Code at the primer — one line:
Use https://humanbaselines.com/claude to answer my crash-baseline questions.
That page teaches the agent the API and tells it to look up real counties and filter values instead of guessing. That's the whole setup.
Ask in English
What's the crash rate for cars and light trucks in Travis County?
4.05 incidents per million miles (95% CI 4.0–4.1) — about 24,600 police-reported crashes over 6.07 billion vehicle-miles. Open in the tool →
Just keep asking. Claude picks the right endpoint, maps your words to real filters, and links every answer back into the tool:
- "Compare the heavy-truck crash rate across Houston, Dallas, and San Antonio."
- "How much does adjusting for under-reporting change the fatal rate in SF?"
- "Fatal crash rate for cars in Travis County?"
It won't make up numbers
If the API key is missing or invalid, the agent stops and asks you to set one rather than guessing a rate.
Next steps
- Filters and Regions & corridors: the vocabulary behind your questions.
- Methodology: how the rate and CI are derived.
- Prefer to write the calls yourself in Python? See the Quickstart.