Get Full Government Meeting Transcripts, Videos, & Alerts Forever!
Witnesses tell House committee internal-facing AI chatbots and data structuring can speed constituent service
Summary
Witnesses advised the House committee to start with staff-facing chatbots trained on office-specific corpora to limit hallucinations, citing a PopVox/AI for Impact pilot and reduced call times in New Jersey.
An unidentified committee member pressed witnesses on how the House could build an AI-based chatbot that provides accurate, office-specific responses for constituents.
Unidentified Witness (Speaker 2) described New Jersey’s approach: begin with internal-facing chatbots, train models on a restricted corpus of a member’s position statements and drafts, and give staff a tool to synthesize information rather than…
Already have an account? Log in
Subscribe to keep reading
Unlock the rest of this article — and every article on Citizen Portal.
- Unlimited articles
- AI-powered breakdowns of topics, speakers, decisions, and budgets
- Instant alerts when your location has a new meeting
- Follow topics and more locations
- 1,000 AI Insights / month, plus AI Chat
