The Importance of the Data Behind AI in Networks (Sponsored)

Why It Matters

Because AI’s value in network operations is proportional to data fidelity, mastering data pipelines lets operators automate troubleshooting, reduce downtime, and extend AI benefits across security and application layers.

Key Takeaways

• Data quality is the true "secret sauce" for AI.
• Selector AI blends generic ML models with network-specific context.
• Agents enable engineers to issue intent instead of writing code.
• Open architecture builds customer confidence and accelerates adoption.
• Platform can ingest any telemetry, expanding beyond networking.

Summary

The podcast episode spotlights Selector AI’s view that the real power behind network‑focused artificial intelligence lies not in the algorithms themselves but in the quality and richness of the underlying data. Hosts Eric Cho and Scott Robot interview chief data scientist Surya and senior engineer Joby to explain how the company’s platform turns raw telemetry into actionable insights for network operators.

Surya emphasizes that data science, not hype‑driven AI, is the scientific foundation of their solution, describing the “secret sauce” as the data fed into a generic machine‑learning engine. Joby illustrates the shift from hand‑coding to intent‑driven agents, noting that engineers now tell an agent what they need rather than write lines of code. The team also stresses an open architecture, publishing their model pipeline to build customer confidence.

Key quotes include Surya’s line, “the secret sauce is in your data,” and Joby’s observation, “I’m not typing code; I’m telling an agent what I want to see.” Their discussion of a “data hypervisor” layer shows how network‑specific context—BGP pairs, ASNs, flow records—is enriched before entering a domain‑agnostic AI core, enabling the platform to handle any telemetry.

For network operators, the message is clear: investing in clean, comprehensive data pipelines unlocks AI‑driven automation, anomaly detection, and cross‑domain insights. Selector’s approach suggests that vendors who expose their methodology and support multi‑layer data ingestion will accelerate adoption and deliver measurable operational savings.

Original Description

When applying AI to network operations and automation, a strong data foundation is essential. In this sponsored episode, Eric Chou and Scott Robohn are joined by Surya Nimmagadda, Chief Data Scientist; and Joby Rudolph, Senior Distinguished Engineer, both from Selector. They discuss the importance of transparency in their data and how it can instill confidence in their customers, how the Selector modeling language carries customer-specific priorities and preferences to allow them to see what's most important to them, and how Selector's core AI model combines with the data hypervisor layer to acquire a network-specific personality.

This episode was recorded live at the Selector AI Summit for Network Leaders.

Links:

Surya Nimmagadda on LinkedIn - https://www.linkedin.com/in/surya-nimmagadda-301b195/

Joby Rudolph on LinkedIn - https://www.linkedin.com/in/jobyrudolph/

Selector - https://www.selector.ai/

AI for Network Leaders March 2026: https://www.selector.ai/ai-for-network-leaders-powered-by-selector-march-2026/

Network Automation Nerds is part of the Packet Pushers network. Visit our website to find more great networking and technology podcasts, along with tutorial videos, the Human Infrastructure newsletter, and loads more resources for building your IT career. https://packetpushers.net