Aviz Networks details Network Copilot deployment and connector options
2 companies named across 3 categories, one of 635 articles referencing Aviz Networks. Previous coverage: Aviz Networks Details ONES Max Scaling for Multi-tenant GPU Networks (Jul 2026).
Companies mentioned
Best suited for
- Seniority
- Staff
- Job function
- Application Management / Integration / Middleware
- Persona
- Platform / Infrastructure Engineer
- Buyer role
- Technical Implementer / Administrator
- Decision stage
- Where to buy
- Adoption curve
- Early Adopters
- Technology maturity
- Emerging Exploration
- Industry
- Information Technology / Software & Services / IT Services / AI Infrastructure
Our classification, not the publisher's statement. Best suited for, not only for.
Aviz Networks’ December (APAC) Office Hours recap focuses on how Network Copilot™ can be deployed, configured, and used, with emphasis on roles and permissions, data connector behavior, and agent and LLM options through live Q&A and a short demo.
Research Overview
The session was a virtual, interactive format for participants to ask questions and experiment with Network Copilot™. Aviz presented the discussion through open Q&A and a brief real-world demo rather than slide-based material.
The organizers stated the event used no slides and no recordings, while a short summary was shared after the session. The recap centers on AI-powered networking, multi-vendor intelligence, and an explanation of how Network Copilot™ works under the hood.
Key Findings
Participants discussed deployment and bring-up on-site, along with how Network Copilot™ tasks can run in parallel using roles, permissions, and projects. The session also covered how data connectors operate, including normalization, MCP, and API approaches.
The discussion included how file uploads can provide context using RAG, and how agents work inside Network Copilot™. Aviz also addressed available agent options, building custom agents, and an SDK walkthrough, alongside LLM choices in NCP and prompting techniques.
Technical Breakdown
The recap describes data connector components in terms of normalization and different integration approaches, including MCP and API methods. It also states that RAG can use file uploads to supply context for tasks.
On the agent side, the session discussed options for agents, how custom agents can be built, and an SDK walkthrough covering how agent functionality is implemented. For model usage, Aviz discussed LLM options within NCP and provided pros and cons during the session.
Operational Impact
The operational focus tied Network Copilot™ use to on-site deployment and working through configuration elements such as roles and permissions. The recap frames these topics as practical items covered during live interaction.
Aviz also highlighted a hands-on element through a 10-minute demo that walked through a real-world use case. The session format included live Q&A throughout and a session summary distributed after the event.
Leadership Perspective
The recap lists Madhu Paluru, Director of Engineering, and Cody McCain, Director of Product Management, as speakers. Paluru is described as leading Aviz’s GenAI-powered Network 3.0 stack and moderating within the SONiC community.
McCain is described as leading AI-driven solutions at Aviz that simplify networking operations and infrastructure automation. The recap also includes career background spanning networking and cybersecurity roles, as well as work related to CNI and Kubernetes.
The December (APAC) Office Hours recap presents Network Copilot™ as a set of deployable components that can be configured through roles and permissions, data connectors with normalization and integration options, and agent and LLM choices, demonstrated via live Q&A and a short real-world demo; this “Blog Signals brief” is a fact-based summary of the vendor blog.
Blog post, originally published at aviznetworks.com.