Speaking twice at Dreamforce · Sept 15-17 →

Salesforce MVP Hall of Fame · Certified Partner since 2010

Tax document classification

Every page labelled by form and page type. OCR still reads the numbers. Jev only sorts.

Get the written assessment

Certified Partner since 2010 · MVP Hall of Fame · 200+ agents in production · UAE and US desks

All 100 decisions
  1. 01Models · Claude, Gemini, OpenAI, Bedrock
  2. 02Agents · Agentforce, CrewAI, ADK, A2A
  3. 03Memory · Neo4j, Cognee, RAG
  4. 04Identity · IndyKite, SSO, entitlements
  5. 05Governance · policy, audit, human override

The stack

How we would assemble it.

The honest no: if the work is a software factory with a named delivery date, we are the wrong partner.

The decision

The decision, drawn.

Choice IRS form + page kind with confidence gate

Jev · Choice

Which form is this page, and which part of the form?

  • W-2
  • 1099-NEC
  • 1099-INT
  • 1098
  • K-1
  • other

Page text after OCR: Form 1099-NEC, Nonemployee Compensation, Payer's TIN...

  • 1099-NEC0.97
  • 1099-INT0.02
  • other0.01
Choice · about $0.0504 per 1,000 decisions, estimated

The job

What has to be true.

Act at 0.90 confidence or higher. Below that, a person or a larger model.

The figure

Builder's figure. Not reproduced by us.

Measured build (self-reported)

$0.001/page, 34x cheaper and 6x faster than prior LLM pipeline (open source)

apimodels.app/jev-use-cases

Write your house rules into the request. When rules were left out, Jev got 5 of 24 right with high confidence (Huryn). Validate thresholds on labelled samples.

The brief

Name the decision your team makes a thousand times a day.

We read the process and write down where Jev fits, where it does not, and where the line sits.

Where are you?

Certified Partner since 2010 · MVP Hall of Fame · 200+ agents in production · UAE and US desks

All 100 decisions