Popp saves 76% in token costs and gets 7x faster with Ellf and Jev

_inesmontani · x · 2026-11-19

Explosion AI (Ines Montani) posted a case study: Trevor, AI Lead at Popp, explains how the team used Typesafe's System One models with the Ellf platform for agentic NLP development — Ellf set up a robust evaluation to find where the system underperformed, then optimized Jev configs for the best precision and recall. The new pipeline costs 76% less, runs 7x faster, and is more accurate overall.

Original post →

More from coding & agent

coding & agent channel →