Braden GM Morning Scorecard
AI dealership analytics dashboard with privacy by design
- Rows parsed in browser
- ~5,000
- Raw rows leaving browser
- 0
One line summary
72 hour take home for Braden Auto Group. Parses ~5,000 dealership sales rows fully in the browser, computes 14 KPIs plus 5 chart cuts, and sends only aggregated JSON to a serverless Claude route to generate a structured findings panel and a morning briefing in dealership voice.
Status
Detailed case study is in progress. The summary above and the metadata in the header are accurate. Architecture diagrams, hardest technical challenges, and full results writeups are being authored in the coming days.
72 hour take home for Braden Auto Group. Parses ~5,000 dealership sales rows fully in the browser, computes 14 KPIs plus 5 chart cuts, and sends only aggregated JSON to a serverless Claude route to generate a structured findings panel and a morning briefing in dealership voice.
Role
Full Stack AI Engineer.
Stack
- Next.js
- Vercel
- PapaParse
- Anthropic Claude API
- TypeScript
Headline metrics
- ~5,000 Rows parsed in browser
- 0 Raw rows leaving browser