Skip to content

Xzar

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

Actively maintained

LegalEvaluationFor developers
xzar.si ↗
Open xzar.siAlternativesSet it up for my team
Xzar: data, price, alternatives
At a glancechecked Oct 28, 2026

not read yet

Use

For
Teams and governments wanting to test how well their AI performs on real professional decisions, such as patent examination.
Activity
Actively maintainedsite updated 2 weeks ago
How it runs
API
Used for
  • test AI agents against real patent decisions
  • build a failure report for an AI model
  • grade AI answers against actual professional outcomes
Worth knowingcomputed from what we read · each with its source
  • Has an MCP server (1 in the registry)public registry →
  • Publishes llms.txt, a file written for AI assistantsxzar.si ↗
Your datawhat they publish, each line with its page · read Oct 28, 2026

“We do not use customer submissions to train or fine-tune AI models unless separately agreed in writing or otherwise lawfully permitted and disclosed as required.”

privacy policy ↗

These are Xzar's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.

How a program reaches itfound, not claimed · read Oct 28, 2026
  • MCP serversi.xzar/xzarverified in the MCP registry
  • Stateanswers, requires sign-inchecked 2026-10-28
  • Address to connectapi.xzar.si/mcp
  • OpenAPI spec11 pathsthe spec ↗
  • API docsxzar.si/docs.htmlthe vendor's page ↗

MCP server details →

This card as JSON, for your agent →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Legalby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare Xzar with

Pick up to two.

All 10 alternatives to Xzar →

All Legal tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Xzar for?

Sign in to leave a note
Questions this page answers
  • What is Xzar?

    Scores AI agents against real past professional decisions, such as patent examiner rulings, to show where they fail. It is listed in the Atlas under Legal.

  • Who is Xzar for?

    Teams and governments wanting to test how well their AI performs on real professional decisions, such as patent examination.

  • Do people use Xzar?

    Little sign of use.

  • Is Xzar still maintained?

    Actively maintained: site updated 2 weeks ago.

  • Does Xzar train AI on your data?

    Only with your consent or on some plans, per its privacy policy (2026-10-28): “We do not use customer submissions to train or fine-tune AI models unless separately agreed in writing or otherwise lawfully permitted and disclosed as required.”

  • Is Xzar safe?

    We do not audit vendors. What Xzar publishes, read 2026-10-28: on training with your data, “We do not use customer submissions to train or fine-tune AI models unless separately agreed in writing or otherwise lawfully permitted and disclosed as required.”.

  • What are alternatives to Xzar?

    In Legal, by use: Docusign, Thomson Reuters Checkpoint Edge with CoCounsel AI, Patent PreCheck, AI Powered EB1A Eligibility Check, VeriCite.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk