JND helps a government agency review 650,000 documents in a week with aiR for Review
JND ran 650,000 of 1.3 million documents through Relativity aiR for Review for a government agency. The tool identified 66,000 documents related to nine issues and 122 documents that were very relevant to those issues. JND estimated the review took 20% of the time of traditional methods — an 80% reduction in project time — and used only three attorneys.
- Agent or tool
- Relativity aiR
- Topic
- Research & Data
- Reported on
- Case study (Relativity)
- Added
- 2026-11-17
Why it matters
Research is mostly gathering, cleaning and comparing. Handing that groundwork to an agent leaves the person with the part that needs judgment: deciding what the findings mean. It is one of 317 sightings filed under Research & Data on Agent Sightings (number 72 by interest), and one of 48 involving Relativity aiR.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Relativity aiR or any similar agent and adjust the details to your situation.
I want an assistant to answer questions over our own data and show how it got each answer. The tool in the source case was Relativity aiR.
Tip: Start small: run it once on a low-stakes example, read what the agent did, and only then let it run on real work.
Source
Read the original first-hand account on Case study (Relativity): https://relativity.com/resources/customers/jnd-air-for-review-public-sector. Our summary is a paraphrase; details are in the source.
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.
Browse more like this
Related sightings
- PwC UK cuts contract review volume 73% with Contracts in Relativity aiR
- McDermott Will & Schulte and KPMG query 724,000 documents in a weekend with Assist
- KPMG uses Data Breach Response in Relativity aiR to cull 90% of a 1.5 TB incident
- 50 AI agents in Minecraft built a government, a ration ledger and a no-blame inquiry about a chicken