Built a tax document classifier with Jev.

Built a tax document classifier with Jev that labels the full corpus at $0.001 per page, 34x cheaper and 6x faster than the prior LLM pipeline.

The original post

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. Wasn't the case back then, and it's proved wrong again now.

Jev classifies 100% of our tax document corpus at $0.001 per page.

34x cheaper and 6x faster than the LLM setup.

Open sourcing it:

What the author linked

• github.com/kyotofin/tax-d…
• GitHub - kyotofin/tax-doc-classifier: Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page. — Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page. - kyotofin/tax-doc-classifier

Engagement when collected

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.