Skip to main content
usedby
Search tools, companies

How Verra uses Upstage

90-100%

Accuracy for critical fields

As published on upstage.ai. Captured by usedby on Oct 8, 2026.

What happened

Verra uses Upstage's Information Extract to pull structured data from its historical PDF project documents, replacing hand-written regex rules with a JSON schema-driven extraction pipeline that its developers can maintain and extend themselves.

Summary written by usedby from the source page, in English. The figures are those of Upstage and Verra, not ours.

  • 80-90%“Accuracy results were about 90- 100% for critical fields and 80-90% for secondary fields.”
  • 7,000“In the initial phase, the system extracted data from more than 7,000 pages across roughly 50 documents.”

Verra’s developers now provide a simple JSON schema that describes the fields they want. The AI interprets the schema, locates the correct information, validates the extraction, and produces structured output. No regex. No hand-coded rules.

From the page. upstage.ai, captured Oct 8, 2026

What the story claims, and what we checked

We compared the story with its live page on Oct 8, 2026.

  • The figure: 90-100%CheckedThe figure is on the page; its label is our wording.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of Verra.
  • Verra uses UpstageCheckedConfirmed line. Latest check across sources: Oct 8, 2026.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

70%“70% Reduction in Manual Processing: AI automated data extraction”Hanwha Life uses Upstage. Another customer of Upstage30 minutes“saves about 30 minutes of manual work per single-facility application”Tricura Insurance Group uses Upstage. Another customer of UpstageConnectWave uses UpstageAnother customer of Upstage