Watch on YouTube
Watch on Vimeo
Alex Vizzari, Product Manager at Fortinet, presents the company’s shift toward redefining mobility through the integration of Generative AI and Agentic AI within the networking ecosystem. By uniting the FortiManager provisioning tool with FortiAIOps, Fortinet has created a unified NOC that utilizes specialized AI agents to handle complex backend tasks. These agents facilitate seamless communication across the Fortinet Security Fabric and are capable of transforming high-level intent, such as a hand-drawn network diagram, into functional configurations like IPsec VPNs. This evolution aims to move beyond simple troubleshooting to a model where AI agents proactively exchange telemetry to correlate network issues with security postures, ensuring true visibility across the data lake.
A major feature of this AI-driven approach is the enhancement of day-to-day operations and incident response. Users can query the Generative AI for specific station health summaries, which then provides a detailed breakdown of issues such as DNS failures, radius errors, or uplink bottlenecks. A unique capability discussed is the automated packet capture (PCAP) integration; when an issue is identified, the system can trigger a capture directly on the FortiGate firewall, retrieve the file, and perform a deep analysis of the trace. This service is vendor-agnostic, allowing administrators to upload PCAP files from competitors for analysis, which significantly reduces the time Level 1 and Level 2 support teams spend manually sifting through large data sets.
The presentation also demonstrates the practical application of Agentic AI in complex SD-WAN environments. For instance, if a user experiences poor performance with a specific application like Salesforce, the AI agent can map the entire topology, analyze active sessions, and evaluate SLA metrics such as jitter, latency, and packet loss. In scenarios where a policy might prioritize low latency while ignoring packet drops, the AI agent can detect this discrepancy and propose an optimized policy change. This allows the system to intelligently shift traffic to more stable links, ensuring that the network self-optimizes to maintain application performance without requiring manual intervention from the IT staff.
Personnel: Alex Vizzari
Thank you for being part of the Tech Field Day community! Our mailing list is a great way to stay up to date on our events and technical content, and we appreciate your signup.
We promise that we’ll never spam you, send ads, or sell your information. This list will only be used to communicate with our community about our events and content. And we’ll limit it to no more than one message per week.
Although we only need your email address, it would be nice if you provided a little more information to help us get to know you better!
