Nuix Announces Neo Generative AI Framework for Governed LLM Use

PUBLISHER ARTICLE PREVIEW

From the original article

Nuix on October 7, 2026 announced the Nuix Neo Generative AI (Gen AI) Framework, a governed orchestration layer for putting generative AI to work on organizations’ structured and unstructured data. Nuix said the framework addresses the governance, confidence and auditability concerns that have limited the use of large language models (LLMs) and Gen AI in high-stakes legal, risk and investigation matters.

The framework combines audit-grade telemetry with policy-enforced guardrails to support evidentiary integrity and corporate usage controls for LLMs, according to the announcement. Nuix said it monitors and meters token usage to prevent runaway token costs, and that it manages the context window to ground answers and strengthen the reliability of AI outputs.

Under the framework, a customer’s selected LLM is connected to enterprise data that is forensically and defensibly curated by the Nuix Neo platform. Customers retain the flexibility to choose the model and provider that best fit their requirements, strategic goals and innovation appetite, while Nuix provides the governance layer that securely connects that model to the curated data intelligence layer delivered by the platform’s patented data processing engine.

Nuix said the Nuix Neo platform draws on more than 25 years of research and development to deliver forensic-grade processing of unstructured data, creating a data intelligence layer it said is relied upon by hundreds of high-profile and high-stakes organizations. The Gen AI Framework builds on that layer to operationalize the application of each customer’s selected LLM.

The framework supports two capabilities built on its enterprise-grade infrastructure: Nuix Neo BYO AI and the Nuix Neo AI Agent. Nuix said BYO AI applies repeatable workflows that systematically process every item in a dataset rather than prioritizing or sampling subsets, then produces structured reports with links back to source items and citations, while giving customers clarity and control over token usage.