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.
More from coding & agent
- Google Sheets becomes a live CV lab: 100k cells, ~500k formulas, zero code — fofrAI · 2026-11-19
- Microsoft launches agent controls, a runtime policy control plane for enterprise agents — krishnan · 2026-11-19
- Buyer's checklist: if a self-written agent skill misfires, can you roll back? — krishnan · 2026-11-19
- Nous Research ships Hermes Enterprise with Microsoft, tops OpenRouter at ~2T tokens/day — krishnan · 2026-11-19
- Case study: Popp cuts token costs 76% and runs 7x faster with Ellf and Jev — _inesmontani · 2026-11-19
- opencode now serves 44% of its 16T daily tokens on its own GPUs — AccBalanced · 2026-11-19