Same Prompt, Same Data: Claude's Fabric App Beats Its Dashboard at One-Fifth the Cost
adnan_hashmi · x · 2026-10-30
The author gave Claude the same Excel dataset and design brief previously used to test Claude Dashboards, this time asking for a Fabric App (Microsoft's code-first web apps inside Fabric, currently in preview).
Results:
- One message produced a report called Margin Ledger at roughly one-fifth of the build cost, and it's a better report
- Data was loaded into a Fabric lakehouse with a Direct Lake semantic model; every number is a DAX measure anyone with workspace access can verify
- The dataset was the ZoomCharts Power BI Challenge e-commerce profitability workbook: 9,109 order lines across 2024–2025
Takeaway: Claude built both, so the difference comes from what each platform hands the model — a good semantic model makes output more reliable. A public, no-login copy of Margin Ledger is available.
More from coding & agent
- OpenClaw's Trail of Bits audit confirms 23 vulnerabilities, all fixed — steipete · 2026-10-30
- Supabase hits 13M users as ~70% of new activity comes from AI agents — ycombinator · 2026-10-30
- Zero evals is fine at first: nail UX, then build evals with domain experts — Al_Grigor · 2026-10-30
- DeepMind essay: agent coordination, not solo competence, will flip the economy — krishnan · 2026-10-30
- Tessl framework: right skill lifts agent accuracy 20%, but activation drops to 40% — bibryam · 2026-10-30
- 7 free open-source tools that replace paid apps, from local voice cloning to spyware checks — dr_cintas · 2026-10-30