# Xzar (xzar.si)

Scores AI agents against real past professional decisions, such as patent examiner rulings, to show where they fail.

- Atlas card: https://inite.ai/en/atlas/xzar.si
- Site: https://xzar.si
- For: Teams and governments wanting to test how well their AI performs on real professional decisions, such as patent examination.
- Categories: legal
- Use 0/100 · alive 100/100

## Used for

- test AI agents against real patent decisions
- build a failure report for an AI model
- grade AI answers against actual professional outcomes

## Price

Not read yet.

## For developers

- OpenAPI: https://xzar.si/openapi.json (11 paths)
- API docs: https://xzar.si/docs.html
- MCP server: si.xzar/xzar (namespace; auth on 2026-10-28)
- Read 2026-10-28

## MCP server, measured daily

Server: https://api.xzar.si/mcp, checked every day since 2026-10-28 (6 checks).

- Answered: measuring, 6 daily checks so far
- Median first answer: 158 ms
- Sign-in: OAuth (the client signs the user in)
- Method: https://inite.ai/en/atlas/mcp/report

## Your data

- Certifications stated: none
- Training on your data: conditional (https://xzar.si/privacy.html)
- Read 2026-10-28

---

Source: INITE Atlas, https://inite.ai/en/atlas/xzar.si. JSON: https://inite.ai/api/atlas/xzar.si. MCP: https://inite.ai/api/mcp (atlas_lookup).