Redgrave LLP

Redgrave LLP wanted to move past theoretical debate about generative AI in legal review and test it directly against a traditional managed review workflow. The firm chose a deliberately difficult population of roughly 45,000 real-world documents governed by a nuanced responsiveness standard tied to pharmaceutical marketing, controlled substances, and federal compliance obligations, where documents were not responsive merely for mentioning opioids or sales activity.

The firm ran a head-to-head study pitting Relativity's aiR for Review, a generative AI review workflow, against a traditional first-pass managed review using active learning performed by a 24-person team over seven business days. A subject-matter expert conducted a blind review of a random sample to establish ground truth, then reassessed a set of documents where his coding disagreed with aiR for Review's predictions, this time with visibility into the tool's rationale and citations.

aiR for Review required approximately 18 hours of attorney time versus approximately 1,123 hours for the active learning workflow, a roughly 98 percent reduction in cumulative human hours, while also achieving higher recall (88% vs. 64%) and lower elusion (1% vs. 3%). After reviewing aiR for Review's rationale on 151 disagreement documents, the expert changed 10 calls from not responsive to responsive; aiR for Review did flag more documents overall, resulting in lower precision than the active learning workflow.

• Speed and completeness are not a tradeoff here: aiR for Review was both dramatically faster and more thorough (higher recall, lower elusion) than active-learning managed review.
• Generative AI can act as a second lens on human judgment, surfacing specific documents worth a second look rather than replacing expert review outright.
• A wider recall net brings lower precision (more documents flagged for review), a tradeoff that may be justified when missing key documents carries the greater risk.