Examples

End-to-end walkthroughs: a real question, the commands that answer it, and the output. Each one runs against the live database, so the numbers in the page are numbers the CLI actually returned.

They're written for use with Claude Code or any agent that can run a shell. The pattern is always the same, and it's the pattern worth copying:

fetch to disk → look at what came back → build.

The middle step is the one people skip. Every example here shows what it caught.

Available now

Competitive landscape: TL1A

Three commands and a script produce a landscape spreadsheet, a bullseye chart and supporting statistics for a target with 48 assets, 67 trials and 58 deals.

Shows how to page past the per-entity --limit cap, and catches three defects in the raw pull before they reach the chart: one asset listed twice under two ids, one Phase 3 asset that belongs to a different disease entirely, and one developer split across two spellings.

Suggest one

These are meant to cover the questions people actually bring to the data. If the one you need isn't here, say so, it's a good signal for what to write next.