OnRecord - verificarion for spoken claims

Problem statement: In founder pitches, vendor demos, and partner calls, people make confident, specific, checkable claims — market sizes, competitor pricing, "we're the only ones who do X." Almost none of it is verified before a decision is made. Verification is manual and slow: listen back, work out which claims are checkable, open twenty tabs, then try to remember whether this person said something different eight months ago. The evidence is public. The bottleneck is that nobody can traverse it fast enough. Target user: Analysts, angel investors, and operators evaluating founder pitches, vendor demos, and partner calls. Adjacent: journalists and podcast producers doing pre-publication verification, enterprise vendor diligence, and comms teams reviewing their own executives. How native.builder was used: Built end to end in native.builder. Product Architect scoped the PRD, data model, and Edge Function architecture before any code was written — it surfaced four design problems in my brief, including an ambiguity about which Bright Data product the pipeline needed. Task Planner produced the dependency graph. Builder agent generated the React application, Supabase schema, and Edge Functions across ten incremental prompts, and diagnosed a stale Vite dependency cache without intervention. The UI, data model, verdict logic, and contradiction detection are complete and demonstrated on fixture data. The Speechmatics transcription Edge Function is built and deployed; the multipart submission format is still being resolved. Tools: native.builder, Supabase (Postgres, Storage, Edge Functions, Realtime), Speechmatics Batch API, Bright Data (SERP API, Web Unlocker), AI/ML API, React, Vite, Tailwind.