Award: Data Access Alternatives: Artificial Intelligence Supported Interfaces (DAA)

Award Date: 8/20/2024
Project Title: Data Access Alternatives: Artificial Intelligence Supported Interfaces
Project Performer: BrightQuery, Inc.
Project Partners: Westat, Google, Stanford Artificial Intelligence Laboratory (SAIL), MIT Center for Collective Intelligence, University of Chicago Data Science Institute
Award Amount: $1,411,547.00
Objective: This project seeks to develop and pilot an AI “chatbot” that answers natural language user questions based on public data products from federal statistical agencies. In the first part of the pilot, the team is building a Retrieval Augmented Generation (RAG) based system that is compatible with and builds on the open-source framework behind Google’s Data Commons. The chatbot will focus on types of data products that represent how statistical agencies publish public data.(1) public use files, (2) data tables, and (3) analytical reports. These features are designed to make public data more accessible, useful, and relevant for a broad range of users, including those in science, policy, journalism, and more. In addition to a pilot tool, this project will record lessons learned about the size of input data tables, making statistical data “AI ready”, and engineering issues encountered while building the pilot tool.
Period of Performance: August 2024 – August 2025
Point of contact: Jose Plehn | BrightQuery, Inc. | jplehn@brightquery.com

Lessons Learned

Request for Solutions (closed)