RXed AI News

AI to the bone.
Audited 2026-07-31 · RXed table v1.0

Legora

Visit legora.com
“The collaborative AI powering lawyers to review and research faster, draft smarter, and advise with precision” — the vendor’s own words

Best-in-class tabular review and 12-jurisdiction research on an $866M war chest — but there is no eval surface, an independent rubric ranks it last of the big three, and the price only exists behind a sales call.

The verdict, read by Jan · AI clone of Jan’s voice, generated locally with his consent.
Best for: Mid-size firms (10–100 lawyers) doing high-volume, multilingual or cross-border document review — you get the best review surface in legal AI at a reported third of Harvey's price, if you accept a sales-led buy and verify output yourself.
Scope17/20
Quality6/10
Where the quality sits
8Reactive
5Retrieval & Memory
8Orchestration
6Validation
6Models
SpecialistResearchAutomation & AgentsProductivityPaid
Vendor
Legora (formerly Leya) · legora.com
Origin
US — New York
Pricing
Not published — sales-led. Third-party estimates ~€260–740/user/month (reported $300–800), ~10-seat minimum ≈ €26k+/year floor; Agent Pro moved to consumption-based pricing 06/2026
Users (official only)
100,000+ lawyers at 1,500+ law firms and in-house legal teams across 50+ markets (source, 2026-07-28)

Element scores

Reactive
Retrieval & Memory
Orchestration
Validation
Models
Primitives
Compositions
Deployment
Emerging
Tap or hover any element to see why it got that score.

Strengths

Tabular Review is the category-standout surface: a data room becomes a grid, each document a row, each prompt a column, so you verify 200 contracts side by side instead of interrogating a chat box. Legal Research covers 12 jurisdictions with source-level citations and the strongest multilingual range in the pair (native Arabic building with Al Tamimi since 06/2026). The Agent plans, executes, reviews and delivers end-to-end, and adoption is verifiable: GÖRG reports 96.81% weekly active usage across 380+ lawyers.

Honest dings

The only published independent rubric (HAQQ, disclosed vendor benchmark) ranks Legora last of the big three at 34.5/50 vs Harvey's 38.2, losing 9 of 11 categories. No customer-facing eval or regression-testing surface exists — on a tool selling trustworthy legal output, that is the biggest hole in the passport. Pricing is behind a sales call with a ~10-seat minimum, Law.com documents a growing build-your-own countercurrent ('wrappers' criticism), and reviewers note long documents past a few hundred pages grind in the grid.

Prices and details change — this passport is re-verified at least quarterly.
Sources (12) — every claim traceable

Every audit lists the research it rests on — transparency and traceability are the product. Tools evolve: each audit is a snapshot of its audit date, and re-audits supersede older versions (kept below for reference).