Back to blog

Blog Post

Significant enhancements to AI Research Assistant models

Share on social

Jan 18, 2026

Lorem ipsum

Table of contents

Share on social

Join the newsletter
Significant enhancements to AI Research Assistant models

[AI Research Model Improvements]

The new security research model can retrieve and analyze relevant information more efficiently, synthesizing insights to provide greater context

Contact sales

Introducing Searchlight AI Agent 2.0, our most capable model yet for cybersecurity investigations. Using the new model, Searchlighters can retrieve and analyze relevant information more efficiently and synthesize insights to gain greater context to support their investigations. It also supports document memory within a chat session, allowing it to reference previous points shared in the same conversation.

Key model improvements

  • New dark web search query helper tool, providing starter questions to support your investigations
  • Boosted information retrieval speed through optimized agent-to-tool separation
  • Increased agent accuracy with new query context tools for more targeted results
  • Improved answer fidelity by assigning one agent per searchable index
  • Maintain conversational context across multi-turn investigations with the addition of chat memory, eliminating the need to repeat prior steps or information

Early success stories

A US State Agency was alerted to a threat actor who claimed to have breached its unemployment-benefit accounts. Using the Cerberus AI Research Assistant, the analyst was able to query details from the initial post and instantly locate the post's original dark web source. The AI assistant tool translated the post, generated a synopsis of the thread, and extracted the key details for the wider criminal investigation team.

By pivoting on these AI-derived insights, the analyst was able to secure pivotal, new details about the threat actor's identity and operational methodology. This verified intelligence was delivered to the state's cybersecurity office, significantly accelerating the criminal investigation and enabling rapid, pre-emptive defense measures to protect public data.

Bio

Alex Blackman is the Head of Product Marketing at Searchlight Cyber, where he leads the go-to-market strategy for the company’s Preemptive Threat Exposure Management suite. With over a decade of experience serving global brands like Unilever and Allianz, Alex focuses on bridging the gap between deep technical intelligence and strategic business value. He is the voice behind Searchlight’s webinar series, helping MSSPs, enterprises, and public sector organizations identify threats before they become attacks.

Alex Blackman

Author

Alex Blackman

Head of Product Marketing at Searchlight Cyber

Alex Blackman leads product marketing at Searchlight Cyber, where he's responsible for taking the company's Preemptive Threat Exposure Management platform to market. Before joining Searchlight, Alex worked with global brands including Unilever and Allianz. He runs Searchlight's webinar programme and spends most of his time helping security teams understand why preemptive beats reactive and how that works in the Searchlight platform.

Related Blog Posts

September 3, 2026

Beacon: FulcrumSec Claims Responsibility for Manchester Airport Group Breach

September 1, 2026

Searchlight Threat + RST Cloud: Instant insights from 1,000s of threat reports

August 27, 2026

Beacon: North Korean Hackers Linked to Rust Supply Chain Attack

August 20, 2026

Beacon: Cl0p Claims Data Theft from More than 40 Companies

August 19, 2026

wp2shell: Discovering One of 2026’s Biggest Zero-Days, and the Future of Exposure Management

August 14, 2026

Beacon: OpenAI's Astra Paused Due to Hacking Use Concerns

Never miss a beat

Get all news and updates about Searchlight Cyber, directly in your inbox.

Subscribe
Please enter a valid email address.
Background Gradient