@nedwize built a tax-document classifier with Jev on top of an existing LLM ingestion pipeline. They say Jev classifies 100% of their corpus at $0.001 per page, 34x cheaper and 6x faster than the LLM setup, and that they are open-sourcing it.

Nakshatra Saxena (@nedwize) published this on 2026-09-18. @nedwize built a tax-document classifier with Jev on top of an existing LLM ingestion pipeline. They say Jev classifies 100% of their corpus at $0.001 per page, 34x cheaper and 6x faster than the LLM setup, and that they are open-sourcing it. Built a tax document classifier with Jev. We ingest thousands of tax documents using an LLM pipeline I built last tax season. I read multiple articles as late as April this year claiming AI fails at tax document classification. How Jev or TypeSafe is used, in the post's own words: “Built a tax document classifier with Jev.” The post does not name a separate audience. It is for people reading what @nedwize shows here (it links to github.com; it includes media).