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

November 9, 2026

New Indicator of Compromise hunting tool added to Searchlight Investigate

November 6, 2026

Does a Ransomware Leak Site Listing Confirm a Breach?

November 4, 2026

CVE Intelligence now accessible across all Searchlight tools

November 4, 2026

Introducing Email Exposure History

October 30, 2026

Beacon: Critical Brotli Flaw Broccoli2Shell Triggers Emergency Patches

October 23, 2026

Beacon: PHP2Shell Patches Land as First Exploitation Attempts Observed

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