Nuix launches AI agent with built in audit trail
Nuix announces in a press release the Nuix Neo AI Agent, which answers natural language questions about data used in legal, regulatory and criminal investigations. The agent links answers to source documents and records each analysis step, creating an audit trail that investigators can export with the complete conversation and findings.
The software reads documents, images and other case materials, then traces connections among people, accounts, communications and transactions. It uses more than 20 tools within the Nuix Neo platform, works across case inventories and enforces access controls based on user roles.
The agent runs on the Nuix Neo Gen AI Framework, which connects a supported large language model selected by the customer to data processed by the Nuix Neo platform. Administrators can limit spending, monitor usage and control prompts and responses.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Legal AI Weekly, Cybersecurity AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Legal AI
Oct 21 Harvey Opens Connector Library to Legal Teams Oct 21 Canadian Judicial Council Issues AI and Digital Evidence Guidelines Oct 21 Mary Technology Connects Litigation Software to Harvey Oct 21 Legora Raises $550 Million at $8.8 Billion Valuation Oct 21 August Launches Products for Fixed Fee Legal ServicesMore from Cybersecurity
Oct 22 Cyware Launches AI Agents for Threat Intelligence Prioritization Oct 22 Chrome Adds Gemini Scam Detection and ClickFix Warnings Oct 22 Railway says attacker may have obtained customer secrets in attack aimed at AI inference providers Oct 21 Anthropic uses Claude to find 493 attack surface issues Oct 21 OpenAI Proposes Cybersecurity Rules for Advanced AILegal AI Weekly
The source for the Legal AI software news, analysis, emerging applications: contract review, e-discovery, research.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Nuix Showcases Neo Financial Crime Tools at Sibos 2026
Nuix Named RiskTech100 2027 Disruptor
Casepoint Adds AI Agents for Legal Document Review
TalentNeuron Adds AI Agents to Synapse Workforce Analysis
Incognia Launches AI Agent Detection for Financial Institutions
Daily AI Brief: the AI news that matters, in your inbox.