Aviz Networks Presents at Networking Field Day 38

Aviz Network Copilot with Thomas Scheibe

Watch on YouTube
Watch on Vimeo

Aviz Networks introduced Network Copilot (NCP), their private AI platform built for NetOps, emphasizing their vision of “Networks for AI, AI for Networks” and enabling open networking with SONiC and LLMs. Aviz Networks, a software networking company founded in 2019, aims to revolutionize networking by separating hardware and software, similar to the server world. Their product portfolio includes Fabric Manager for managing deployments and configurations, an Observability product for deep packet inspection and data correlation, and their flagship Network Copilot. They highlight the widespread issue of data silos and manual workflows in traditional NetOps, which NCP addresses by providing a native language interface to correlate data faster, automate repetitive tasks, and offer recommendations, not self-driving networks.

Aviz Networks highlights that NCP is not a new data lake but rather a tool that bridges existing data islands. It doesn’t require training on an organization’s operational data, as this data is constantly changing and proprietary. Instead, NCP uses an LLM to translate user questions, identify relevant data sources via data connectors, and employ AI agents to process information for a comprehensive answer. A critical aspect of NCP is its private AI platform architecture, ensuring that all data remains local to the customer’s environment, addressing security and privacy concerns. This approach also means the customer controls their LLM instance, without contributing to the training of external models.

NCP is designed to be hardware vendor-neutral, working across various operating systems and hardware platforms, a significant advantage in multi-vendor enterprise environments. Aviz Networks emphasizes that they are not just an LLM company but a networking software company leveraging LLMs to solve real-world network operational challenges. The value proposition lies in its ability to quickly pull and correlate data from disparate tools, offering a more intuitive and faster way to gain insights without the need for data scientists. This significantly reduces the time spent on tasks like compliance reporting and troubleshooting, providing a tangible return on investment for customers seeking to streamline their NetOps.

Personnel: Thomas Scheibe

Aviz Networks Network Copilot Demo

Watch on YouTube
Watch on Vimeo

In this Networking Field Day session, Aviz Networks introduced Network Copilot (NCP), their private AI platform built for NetOps, emphasizing their vision of “Networks for AI, AI for Networks” and enabling open networking with SONiC and LLMs. The demonstration showcased NCP as a self-hosted software solution that integrates with existing network data sources through various data connectors, such as Cisco Catalyst Center, Nexus Dashboard, IP Fabric, Elastic, Splunk, and Zendesk. The primary goal of NCP is to centralize disparate network data, allowing users to query and correlate information through a natural language chat interface, thereby streamlining operations and reducing the need for manual data aggregation from various tools or complex scripting.

The demo highlighted NCP’s ability to perform tasks like inventory analysis and hostname validation. Users can create projects within NCP to focus on specific troubleshooting sessions or events, inviting collaborators and selectively enabling relevant data connectors to avoid data pollution. A key feature is the ability to upload static contextual information, like naming conventions or CVE lists, as files, which NCP can then use to validate device configurations or generate compliance reports. The presenters stressed that NCP doesn’t “train” on operational data in the traditional sense; instead, it uses a pre-trained LLM (like Llama 70B), fine-tuned for networking, to interpret questions and leverage AI agents to retrieve, process, and summarize data from connected sources.

While acknowledging that some functions could be replicated with scripting, the true value of NCP lies in its abstraction layer, enabling network engineers to manage diverse multi-vendor, multi-NOS environments without needing deep knowledge of every CLI or proprietary system. This empowers junior engineers by providing suggestions for troubleshooting and allows for more efficient audit reporting and capacity planning. Aviz Networks emphasized that NCP is not a CLI replacement, nor does it push configurations, but it can provide insights and facilitate data-driven decisions. The platform’s self-hosted nature with GPU requirements (like NVIDIA A100 or H100) ensures data privacy and offers a quicker ROI by automating tedious tasks, freeing up valuable engineering time.

Personnel: Madhu Paluru, Thomas Scheibe