The Everything Feed - All Packet Pushers Pods HN801: Will a Natural Language Interface (NLI) Replace Your CLI?
Oct 17, 2025
Scott Robon, host of the Total Network Operations podcast and a network automation expert, dives into the potential of natural language interfaces (NLIs) replacing command-line interfaces (CLIs). He discusses real-world vendor developments in NLIs and the challenges of LLM variability versus deterministic outputs. The conversation shifts to the implications of running AI infrastructure and the crucial role of data engineering. Robon emphasizes the ongoing need for engineers to understand automation tools while assuring that current AI is about augmentation, not replacement.
AI Snips
Chapters
Transcript
Episode notes
NLI For Networks Is Already Materializing
- A natural language interface (NLI) for networks is real and being built by multiple vendors, not just a single hype product.
- NLIs pair LLMs with specialist models to translate plain English into actionable network queries and commands.
Control Reduces LLM Variability
- LLMs are inherently non-deterministic but you can steer them with parameters like temperature and sampling to reduce variability.
- Vendors also chain models and techniques to increase consistency for operational use cases.
Tune Models For Operational Consistency
- Tune model parameters (temperature, sampling) to make outputs repeatable for critical network tasks.
- Combine or chain specialized models rather than relying on a single general LLM for determinism.