NetBox Labs ships AI copilot designed for network engineers, not developers

Six months ago, NetBox Labs first previewed its AI copilot to help accelerate network operations. Today, it hit general availability.

NetBox Labs is the commercial steward of open source NetBox and delivers a platform of composable products spanning network discovery, assurance, observability and AI operations. Companies including ARM, Cisco, CoreWeave, J.P. Morgan, and Kaiser Permanente use the platform to operate and automate complex network infrastructure.

NetBox Copilot is an AI agent that provides a natural language interface for infrastructure management. Network engineers can query infrastructure data, investigate changes for troubleshooting and compliance, and assess dependencies before maintenance windows. For NetBox Cloud and NetBox Enterprise customers, the agent can execute write operations, allowing it to modify infrastructure records through natural language commands.

The time it took for the preview of NetBox Copilot AI to reach general availability was deliberate. NetBox Labs spent the intervening months building enterprise governance controls that let organizations bring their own AI models and maintain data sovereignty. The company implemented the write operations that allow Copilot to modify infrastructure records, not just query them. The system’s behavior was refined based on beta customer feedback to improve accuracy and reliability in production environments.

The timing reflects market pressure. Organizations are attempting to automate infrastructure management while simultaneously deploying AI data center capacity at unprecedented speed.

“NetBox is usually the starting point for automation projects,” Kris Beevers, CEO and co-founder of NetBox Labs, told Network World.

Natural language for network engineers

Beevers explained that network operations teams face two fundamental barriers to automation. First, they lack accurate data about their infrastructure. Second, they aren’t software developers and shouldn’t have to become them.

“These are not software developers. They are network engineers or IT infrastructure engineers,” Beevers said. “The big realization for us through the copilot journey is they will never be software developers. Let’s stop trying to make them be. Let’s let these computers that are really good at being software developers do that, and let’s let the network engineers or the data center engineers be really good at what they’re really good at.”

That vision drove the development of NetBox Copilot’s natural language interface and its capabilities.

Grounding AI in infrastructure reality

The challenge with deploying AI in network operations is trust. Generic large language models hallucinate, produce inconsistent results, and lack the operational context to make reliable decisions. NetBox Copilot addresses this by grounding the AI agent in NetBox’s comprehensive infrastructure data model.

NetBox serves as the system of record for network and infrastructure teams, maintaining a semantic map of devices, connections, IP addressing, rack layouts, power distribution and the relationships between these elements. Copilot has native awareness of this data structure and the context it provides.

This enables queries that would be difficult or impossible with traditional interfaces. Network engineers can ask “Which devices are missing IP addresses?” to validate data completeness, “Who changed this prefix last week?” for change tracking and compliance, or “What depends on this switch?” for impact analysis before maintenance windows.

For NetBox Cloud and NetBox Enterprise customers, Copilot moves beyond read operations into workflow automation. The agent can execute approved changes through natural language commands like “Add another server to the NYC data center,” writing directly to the infrastructure database.

Access control is enforced through NetBox’s existing role-based access control model. Users can only query or modify data according to their assigned permissions. This architecture decision solves a critical enterprise requirement: AI agents must respect the same security boundaries as traditional interfaces.

Beevers explained that NetBox is agnostic when it comes to LLM providers. The architecture allows NetBox Labs to focus engineering resources on infrastructure-specific capabilities while benefiting from rapid improvements in base models. The company maintains specialized agent harnesses optimized for network operations. These differ from general-purpose code generation or enterprise productivity agents because network operations require domain-specific constraints, validation logic, and operational workflows.

“We went from Sonnet 3.5 or whatever up to Opus 4.6. Copilot just gets better and better,” Beevers explained. “What it means is we focus mostly on the integration of the agent with our portfolio, the data governance stuff, the specialized behavior of these agents in networks and infrastructure management.”

From interactive to autonomous operations

Copilot currently operates as an interactive agent responding to user queries and commands. Beevers said that NetBox Labs is developing autonomous agents that will execute routine infrastructure tasks without human intervention.

The roadmap envisions agents that follow change management processes automatically, responding to triggers like capacity thresholds or configuration drift. These agents would operate under constraints defined by network teams, executing only approved actions within defined parameters. Management would occur through Copilot’s interface, but execution would be autonomous.

“I actually think the majority of the work, like the grunt work that engineers in these teams are doing these days, will start to get picked up by autonomous agents over time,” Beevers said. “We got a lot of stuff coming this year. The team has grown a lot, so we’re building a ton of stuff.”