AI research

How we build the AI behind Nixi

Whitepapers, benchmarks, and methodology notes from the team. Each piece spells out exactly which models we tested, how we tested them, and why we shipped what we shipped.

AI research11 min

Should AI-Generated Medical Notes Get a Second Opinion? Benchmarking the Judge-LLM Pattern (April 2026)

A second LLM that reviews the first model's medical note against the source transcript improved overall quality from 7.8 to 8.9 / 10, but only when the judge prompt is correctly designed. Nixi AI validation study with full architecture comparison.

Mahsa Yarahmadi25 April 2026Read

AI research12 min

Choosing the Right LLM for Medical Note Generation: A Multi-Model Benchmark (April 2026)

Nixi AI benchmarked 12 LLMs on German consultation transcripts: medical fact extraction, hallucination rate, latency. Results, trade-offs, and model recommendations for clinical documentation.

Mahsa Yarahmadi25 April 2026Read

Ready to get your evenings back?

Join the clinicians using Nixi AI to finish documentation in minutes. Not hours.

Start 14-day free trial Book a demo