Revolut's Real-World Lessons in Deploying GenAI
nathanbenaich · x · 2026-07-19
Revolut's Nikolay Donets shared practical insights from their large-scale AI rollout: - The company now has **twice as many GenAI use cases as traditional ML**, spanning **40+ countries** and **200+ products**. - They encountered deployment issues like "**a model in the fallback chain silently failing, leaving the team completely blind**." - Generative model costs are also substantial, with **frontier models costing up to 8x more than alternative solutions**. - At a scale of **25,000 calls per month**, their voice assistant has increased issue resolution speed by **8x**.
More from coding & agent
- Freerange adds static numeric-range proofs for UI code without running the app — cnakazawa · 2026-07-21
- pen.dev lets developers compare frontier models in parallel on frontend design tasks — yakuzeg · 2026-07-21
- ComfyUI slowdown may come from models reloading from disk instead of RAM — J6j6 · 2026-07-21
- ZooData’s API takes a URL and returns structured data in the same request — dr_cintas · 2026-07-21
- ZooData turns any web page into structured JSON for agents with one API call — dr_cintas · 2026-07-21
- Side-by-side model test lands both answers on the first try, then shifts to loop engineering — glenbeer · 2026-07-21