Cisco launches agentic security tools for autonomous AI security
Briefly

Cisco launches agentic security tools for autonomous AI security
"The tools offer transparency and keep people involved in the decision-making process. Foundation-sec-8B-Reasoning is an open-weight reasoning model for cybersecurity use cases. The model is optimized for multistep security analysis, including threat modeling, attack path analysis, and incident investigation. The model produces explicit reasoning traces that allow analysts to understand how conclusions are reached. This supports validation, trust, and regulatory requirements in high-impact security environments."
"Cisco is also introducing the Adaptive AI Search Framework, a reasoning-driven information-retrieval system that goes beyond static, query-based searches. The framework enables AI models to iteratively refine their search strategies as new information emerges, much like a human security expert would. The third release is PEAK Threat Hunting Assistant, an open-source agentic AI assistant that automates threat-hunting preparation. It allows AI agents to collaborate to investigate threat actors and techniques, analyze internal security data, and generate customized, step-by-step threat hunt plans."
Cisco Foundation AI introduces three agentic security tools: Foundation-sec-8B-Reasoning, an Adaptive AI Search Framework, and PEAK. Foundation-sec-8B-Reasoning is an open-weight reasoning model optimized for multistep security analysis including threat modeling and incident investigation. The model produces explicit reasoning traces that allow analysts to see how conclusions are reached and supports validation, trust, and regulatory requirements in high-impact environments. The Adaptive AI Search Framework enables iterative refinement of search strategies as new information emerges. PEAK is an open-source agentic assistant that automates threat-hunting preparation, enables agent collaboration on investigations, and generates step-by-step hunt plans. All tools emphasize transparency and keep humans involved in decisions, model control, and data access.
Read at Techzine Global
Unable to calculate read time
[
|
]