Powered by
MOMENTUM
MEDIA
An “industry-first” benchmark report from NetDocuments has revealed that giving AI structured context about legal matters could cut the cost of generating accurate answers by almost half.
NetDocuments has found that law firms can significantly reduce the cost of producing accurate AI-generated answers by giving artificial intelligence structured legal context, with the savings potentially translating to “nearly $1 million” a year for larger firms.
In what it describes as an “industry first”, the intelligent document management provider has published its Legal Context Engineering Benchmark report, examining how structured legal context can influence the cost and quality of AI-generated answers.
The report found that NetDocuments’ legal context graph could cut the cost of producing a correct AI answer by 48 per cent, while maintaining essentially the same level of answer quality.
For a 2,000-person law firm generating around 4 million AI questions each year, NetDocuments estimated that those efficiency gains could translate into “nearly $1 million” in annual savings, highlighting the potential financial impact of more efficient AI use.
The intelligence document management provider rolled out its legal context graph at the end of May, designed to map the relationships between “every matter, document, and communication within a firm” and connect hundreds of millions of records into a unified, intelligent knowledge layer for legal teams.
NetDocuments CEO Josh Baxter said the findings could help law firms move beyond the “spending without limits” and “cutting without strategy” dilemma, arguing that the right context could allow firms to spend less while still producing better AI answers.
“As AI shifts to consumption pricing, the industry is swinging between two extremes: spending without limits and cutting without strategy,” Baxter said.
“We’ve believed from the beginning that context is the lever that changes that equation. This benchmark is the first proof. Get the context right, and firms spend less to get better answers. That’s not a feature. That’s a new foundation for how legal AI should work.”
The benchmark outlined two potential paths for firms using the legal context graph: they could pocket the efficiency gains as cost savings or reinvest them into deeper AI reasoning and improved outputs.
For firms choosing the latter approach, the results suggest they could improve answer quality while still reducing their overall AI expenditure.
NetDocuments found that reinvesting some of the efficiency gains could improve answer quality by 7 per cent while still cutting overall costs by 18 per cent.
Scott Kelly, vice president of product at NetDocuments, said the legal industry’s AI conversation was increasingly moving away from simply asking what the technology can do and towards understanding how firms can get greater value from it.
“Over the past six months, the conversation in legal has shifted from AI capabilities, which are ubiquitous, to context, which is essential for quality AI outcomes,” Kelly said.
“This benchmark gives firms the confidence to ensure AI investment creates lasting value for their lawyers, their business and their clients.
“We’re moving the conversation from assumption to evidence by demonstrating how structured legal context can help firms get significantly more out of their connected AI tools at lower cost.”
