Nuix launches AI agent for forensic investigations

Nuix has launched the Nuix Neo AI Agent, aimed at investigations, legal review, compliance and regulatory work.

The tool lets users query large volumes of unstructured data in natural language and receive answers linked to the underlying source material. It also records the steps taken to reach a finding, allowing investigators to review and export the process behind a result.

The launch targets legal, regulatory and criminal matters, as well as compliance monitoring. Nuix software is used to analyse data including emails, chats, documents and images in cases where users may need to explain their findings to courts, boards or regulators.

Audit trail

Built on the Nuix Neo Gen AI Framework, the AI Agent works across case inventories within the Nuix Neo platform. It can read and sift through documents and other items, identify links between people, accounts, communications and transactions, and generate graph queries automatically rather than requiring users to write them manually.

Administrators can set spending limits, monitor usage, and apply guardrails to prompts and responses. Role-based access controls also remain in place when the AI Agent is used across the platform.

John Ruthven, Chief Executive Officer of Nuix, said the product was designed to make AI outputs easier to check in sensitive investigations.

"For more than two decades, organisations have trusted Nuix with their high-stakes matters. Agentic AI should raise that bar, so we built the Nuix Neo AI Agent to show its work. Trace every answer to its source. Review every step. Rely on forensic-grade data processed by the Nuix Neo platform," Ruthven said.

Target users

Nuix identified investigators, legal teams, auditors, regulators and law enforcement agencies as the main users of the product. It said the tool is intended to support professional judgement rather than replace it, with outputs tied to source material so users can verify results.

That emphasis reflects a wider debate over the use of generative AI in legal and compliance settings, where users face greater scrutiny over how conclusions are reached. In those environments, traceability and documentation can matter as much as speed, particularly when findings may later be challenged in court proceedings, regulatory reviews or internal investigations.

The AI Agent draws on more than 20 tools within the Nuix Neo platform. Users can export the full conversation with the system, including the steps taken and findings, which may help teams document how a conclusion was formed during a review.

The launch adds an AI layer to Nuix's existing investigative analytics and intelligence software. The company serves government agencies, law firms, financial institutions, corporations and regulators dealing with large, complex datasets under close scrutiny.

Its focus on unstructured data reflects a persistent challenge in investigations and compliance work, where relevant evidence often sits across fragmented sources including emails, messages, documents and transaction records. Tools that can search those materials using natural language have drawn growing interest, but buyers in regulated sectors have also sought clear controls over data access, usage and the basis for any answer generated by an AI system.

Nuix said answers produced by the AI Agent are grounded in source documents and can be checked against them, with investigators able to export both findings and the steps taken to reach them.