Sluicebox cuts LCA agent costs 51-80% by switching to NVIDIA Nemotron 3 Ultra
NVIDIAAI · x · 2026-09-23
NVIDIA published a customer story on Sluicebox, an NVIDIA Inception startup whose AI agent "Lucy" automates product carbon footprint analysis across electronics and semiconductor supply chains, tackling fragmented and missing BOM data.
After moving core workflows to Nemotron 3 Ultra, versus its previous production model:
- Supplier-data extraction accuracy: 87.7% (vs 84%) at 0.20x the cost
- Component classification: 83.5% (vs 80%) at 0.49x the cost
- Emission-factor matching: 72.0% good-match rate (vs 69.1%), completed in 5.3 seconds
- Overall costs down 51-80%, responses up to 2x faster
Engineers can now gauge the carbon impact of design and supplier choices in real time rather than through retrospective assessments.
More from coding & agent
- Microsoft's Agensh Scales Multi-Agent Systems to 1,024 Agents Without a Central Orchestrator, Boosting Test-Pass Rate to 55% — andrew_n_carr · 2026-09-23
- One reference image to a flyable three.js scene — wild single-image 3D demo — majidmanzarpour · 2026-09-23
- Viral demo claims 'GPT-6' can drive browser Paint to draw, unverified — alexcovo_eth · 2026-09-23
- Parallel coding agents merge cleanly and silently break every test — RunAI_Coder · 2026-09-23
- Getting phone-captured text into your computer: OCR, vision models, agentic pipelines — silenceimpaired · 2026-09-23
- Free Bots: a persistent 3D city where AI agents work, earn, buy land and build houses — Daniel_Farinax · 2026-09-23