Microsoft today announced Security Copilot, a new AI-powered ChatGPT-like assistant that leverages Microsoft’s threat intelligence footprint to make faster decisions during incident response and to help to threat hunting and security reports.

“Microsoft Security Copilot is an AI-powered security analytics tool that enables analysts to quickly respond to threats, process signals at machine speed, and assess risk exposure in minutes “Redmond said.

Security Copilot responds to defenders’ security questions through a ChatGPT-like interface and continuously learns from these interactions to adapt to each business environment to advise them on the best course of action.

It enables security teams to manage complex security situations more effectively, and its main objective is to improve the capabilities of security analysts by accelerating the synthesis and interpretation of threat intelligence, allowing them to spot the activities much faster while analyzing web traffic.

Security Copilot will also help detect previously overlooked threats by correlating threat activity signals and establishing the correct connections while inspecting attack data.

It’s powered by OpenAI’s GPT-4 Advanced Large Language Model (LLM) combined with what Microsoft describes as a “security-specific model” designed by its engineers.

It also integrates data and insights from other Microsoft security tools (including Sentinel, Defender, and Intune) to provide personalized guidance for each organization.

“When it comes to security, minutes matter. With Security Copilot, defenders can respond to security incidents in minutes instead of hours or days,” said Vasu Jakkal, vice president of Microsoft Security.

“Security Copilot provides essential step-by-step guidance and context through a natural language-based investigation experience that speeds incident investigation and response.

Today’s announcement comes after the introduction the new Microsoft 365 Copilot assistant two weeks ago, also powered by GPT-4 and designed to increase customer productivity in M365 applications, from Word, Excel, PowerPoint, Outlook and Teams to Microsoft Viva and Power Platform.

As OpenAI explained upon GPT-4’s launch, “although less capable than humans in many real-world scenarios, it exhibits human-level performance across a variety of professional and academic criteria”.

“Security Copilot will simplify complexity and amplify the capabilities of security teams by summarizing and making sense of threat intelligence, helping defenders see through the noise of web traffic, and identify malicious activity,” Microsoft said.

“It will also help security teams catch what others are missing by correlating and summarizing attack data, prioritizing incidents, and recommending the best course of action to remediate various threats quickly, on time.”

While Microsoft revealed today that its new AI-based security scanning tool is currently available for private preview, the company has yet to share details regarding its public rollout.