/ CASE STUDY
Sensemaker
JUN 2023 — DEC 2025DATA SCIENTIST — MODELLING, PIPELINE, PRODUCT
Sensemaker is an insight engine for large document collections: point it at thousands of free-text snippets and it surfaces the themes, patterns, and signals that matter — turning weeks of reading into minutes of analysis. The demo below is an illustrative miniature with fictional data, recreated at small scale to show the experience. It is not the production system.
/ LIVE DEMO
ILLUSTRATIVE DEMO · FICTIONAL DATA
sensemaker.example — demo
/ CHOOSE A COLLECTION
/ UNDER THE HOOD
Documents in, themes out
Thousands of free-text snippets are embedded, clustered, and named with LLM assistance — the unit of output is a theme, not a search hit.
Evidence-first
Every theme links back to the verbatim quotes that support it, so analysts can check the roll-up against the source instead of trusting it blindly.
Weeks to minutes
The point of the product: reading programmes that took analyst-weeks collapse into a review session over ranked, sized, explained themes.
Proven in use
In active use across multiple organizations, with strong feedback from analyst teams.