Case study: Popp cuts token costs 76% and runs 7x faster with Ellf and Jev

_inesmontani · x · 2026-11-19

Explosion AI published a new case study: Trevor, AI Lead at Popp, shares how his team used Typesafe's System One models plus the Ellf platform for agentic NLP development. Ellf set up a robust evaluation to locate weak spots, then optimized their Jev configs for maximum 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 →