AI Agents in Networking and Security Survey Insights
Examining engineers' expectations and the reality of AI agents for networking and security, including commercial and open-source solutions.
Overview
A recent survey examined engineers' expectations regarding AI agents for networking and security, highlighting the gap between expectations and available commercial/open-source solutions. The findings reveal strong demand for automation and monitoring tools, with security remaining a key concern.
What Is an AI Agent?
An AI agent is an autonomous software system that independently perceives, reasons, and acts to achieve specific goals. Unlike traditional software, these agents dynamically adapt through learning and experience, utilizing tools like web search, APIs, and code execution.
Key Survey Findings
Preferred AI Agent Functions
- Configuration automation (37%): Top choice, indicating demand for infrastructure management tools.
- Network monitoring agents (32%): High interest in performance tracking and operational insights.
- Threat and vulnerability agents (22%): Significant focus on security monitoring.
- Code generation agents (9%): Lower priority compared to operational automation.
Top Tasks for AI Agents
Engineers prioritized:
- Troubleshooting network issues
- Automating repetitive tasks
- Security monitoring
- Generating reports
Available Solutions
Open-Source Options
Cisco DevNet aggregates open-source networking and security AI agents here.
Commercial Offerings
- Cisco AI Assistant: Analyzes policies, generates reports, and provides product documentation.
- Other vendors: Nanites AI, DevAI, Selector AI, and Aviz AI offer specialized agents.
Security Concerns
As AI models evolve, security and compliance risks increase. Key concerns include:
- Incorrect instructions from agents
- Hallucinations
- Tool selection errors
Despite risks, AI agents can enhance automated defense systems and assist security teams in incident response.
Additional Resources
Explore more at Cisco DevNet AI Hub.
Related News
Beginner-Friendly AI Agent Projects to Learn and Build
Explore five practical AI agent projects for beginners, covering scheduling, coding, content creation, research, and search functionalities.
Claude Sonnet 4 5 Advances AI Agents Toward OS Like Capabilities
Anthropic's Claude Sonnet 4.5 coding model demonstrates how AI agents could evolve into dynamic operating systems, raising questions about future app development and security.
About the Author
Dr. Lisa Kim
AI Ethics Researcher
Leading expert in AI ethics and responsible AI development with 13 years of research experience. Former member of Microsoft AI Ethics Committee, now provides consulting for multiple international AI governance organizations. Regularly contributes AI ethics articles to top-tier journals like Nature and Science.