Hi everyone! Crystal lets you search and analyze 300k+ government datasets using plain English. For example, prompting "Air quality since 2020 in NYC" will find the most relevant datasets and analyze them, providing a short report with key statistics extracted from the data based on your question.
We felt like AI is great at web search today, but not so much for actually combing through hard-to-reach data, so Crystal aims to bridge the gap for anyone needing deeper quantitative insights into various topics. The tool goes one step beyond browsing web articles and html content, and actually goes into XLSX/CSV/JSON/XML files to find relevant info. We're hoping anyone who uses public data as a resource, like researchers, consultants, journalists, etc. will find it helpful.
Crystal is straightforward - it's in alpha, so there's only a few queries per person, and the app itself is in its infancy. Each query can take a few minutes. We're invested in making this better for people, and we'd love feedback + beta signups - you can provide either via https://www.askcrystal.info or down below! If you'd like to partner with us more closely or have other thoughts, please email us at [email protected]. Thanks!
We felt like AI is great at web search today, but not so much for actually combing through hard-to-reach data, so Crystal aims to bridge the gap for anyone needing deeper quantitative insights into various topics. The tool goes one step beyond browsing web articles and html content, and actually goes into XLSX/CSV/JSON/XML files to find relevant info. We're hoping anyone who uses public data as a resource, like researchers, consultants, journalists, etc. will find it helpful.
Crystal is straightforward - it's in alpha, so there's only a few queries per person, and the app itself is in its infancy. Each query can take a few minutes. We're invested in making this better for people, and we'd love feedback + beta signups - you can provide either via https://www.askcrystal.info or down below! If you'd like to partner with us more closely or have other thoughts, please email us at [email protected]. Thanks!