# How Tripinsurance uses LlamaIndex

**50–75%**: “Reduced claim processing time from 20–40 minutes to just 10 minutes per claim, achieving a 50–75% improvement.”

As published on [llamaindex.ai](https://www.llamaindex.ai/customers/revolutionizing-medical-insurance-analysis-with-agentic-claim-estimation). Captured by usedby on 2026-10-07.

- Company: [Tripinsurance](https://www.usedby.ai/companies/tripinsurance.md)
- Tool: [LlamaIndex](https://www.usedby.ai/tools/llamaindex.md)

## What the story says

A travel insurance provider, working with the consultancy Scaleport AI, uses LlamaIndex and LlamaParse in an Insurance Case Analysis Agent. The agent parses medical reports in varied formats, including scans and handwritten documents, and estimates claim amounts. It also checks exclusions, assesses adequacy, and searches for similar cases.

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

> Reduced claim processing time from 20–40 minutes to just 10 minutes per claim, achieving a 50–75% improvement.

- **twice as many**: “Enabled the team to process twice as many claims without compromising accuracy.”

> The Insurance Copilot developed with Scaleport AI has significantly improved our claims processing speed and efficiency. We've reduced handling time by 50–75%, allowing us to process twice as many claims while maintaining high accuracy.
>
> Evgenii Fursov, CEO of Tripinsurance & Paramatrix

## What usedby checked

We compared the story with its live page on 2026-10-07.

- Checked: the figure 50–75% is printed word for word on the page, near the name of Tripinsurance.
- Checked: the passage quoted above is copied word for word from the page, near the name of Tripinsurance.
- Checked: Tripinsurance uses LlamaIndex. Confirmed line. Latest check across sources: 2026-10-07.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/tripinsurance-llamaindex · How we check: https://www.usedby.ai/methodology