May 2026 Summaries

Network and infrastructure teams are increasingly moving towards agentic automation, aiming for AI agents capable of handling various network tasks autonomously. However, a significant challenge lies in the underlying data not being structured for agent consumption, leading to difficulties in synthesizing information across disparate systems. To address this, an AI-ready intent data foundation is needed, characterized by structured, relationship-rich data that can be reliably queried, stays current with network changes, and is tailored to specific organizational topologies. Infrahub is designed to serve as this foundational layer, integrating and enriching data across devices, services, and customer relationships using a knowledge graph architecture. It offers a GraphQL API and MCP interface to simplify agent queries and includes governed change processes to minimize data drift. Infrahub Skills, an AI package, aids teams in developing valid schemas and automation logic, facilitating faster implementation and ongoing optimization. Companies leading in agentic automation are proactively building these foundations, using tools like Infrahub to establish a scalable, agent-ready data model that supports efficient network management.

Network teams pursuing agentic automation face a key obstacle: existing operational data is often fragmented and lacks the relationship context needed for AI agents to safely answer cross-system questions or act on critical infrastructure. The proposed solution is an AI-ready intent-data foundation that captures not only devices and inventory but also the intended design, topology, services, customers, contracts, and dependencies in a unified, relationship-rich model. Such a foundation should support agent-friendly querying through interfaces such as GraphQL and MCP, remain current through governed changes and reconciliation against discovered network state, and reflect each organization’s specific environment rather than a generic vendor schema. Infrahub is presented as a graph-based platform for building this foundation by integrating existing tools and data sources into a governed knowledge graph, while Infrahub Skills uses AI assistants to help engineers create schemas, populate data, build automation and validation logic, analyze data, detect drift, and audit implementations. The recommended approach is to begin with a narrowly scoped production proof of concept, establish reliable intent modeling and reconciliation, and expand agentic automation as trust and capabilities grow.

Solution Architects Benoit Kohler and Phillip Simonds conducted a livestream to showcase Infrahub Skills, an open-source AI skills package designed to manage the entire Infrahub development lifecycle. They discussed the significance of Infrahub Skills in the context of large language models (LLMs), emphasizing how these skills simplify prompt engineering by storing conventions and rules in Markdown files and validators like Python scripts. This approach alleviates the challenges of context window management and enhances the shareability and testability of skills among team members. The livestream included a demonstration of setting up a new Infrahub repository, installing skills, generating schemas, menus, and objects, and integrating with Git repositories to produce artifacts. In addition to discussing the creation and utilization of Jinja2 transforms and MCP server integration for data analysis, the architects highlighted the role of skills in providing guidance while MCP servers supply data connections. The session concluded with a Q&A addressing topics such as skill creation, compatibility with other LLMs, and security concerns, encouraging viewers to explore Infrahub Skills further through available documentation and community platforms.

OpsMill has secured $14 million in a Series A funding round led by IRIS, with contributions from Benhamou Global Ventures and existing investors Serena and Partech, to advance its mission of improving infrastructure intent management through automation and AIOps. The company's flagship product, Infrahub, was designed to overcome challenges associated with managing infrastructure data necessary for effective automation, offering a scalable solution built on a graph database that supports diverse infrastructure forms and includes features like version control and CI pipelines. Since its release, Infrahub has gained traction among various industries, from global insurance companies to universities, by replacing fragmented approaches with a unified platform, leading to faster deployment and easier governance. The new funds will support engineering, product management, and expansion efforts, while also bolstering sales, marketing, and customer support initiatives. OpsMill plans to maintain its industry presence through events such as AutoCon in Munich and ONUG’s AI Networking Summit, and is actively recruiting new talent to join its growing team.

OpsMill has secured $14 million in Series A funding led by IRIS, with participation from Benhamou Global Ventures, Serena, and Partech, to expand Infrahub, its platform for managing infrastructure intent and supporting automation and AIOps. The company argues that inaccurate, fragmented infrastructure data is a central obstacle to scalable automation, and positions Infrahub as a modern alternative to older source-of-truth tools through a flexible graph-based architecture, version control, change controls, metadata, CI pipelines, and data transformation capabilities. Since Infrahub 1.0 launched just over a year ago, OpsMill reports adoption across industries including retail, insurance, manufacturing, telecommunications, cloud providers, universities, and fintech, with customers citing simplified operations and faster infrastructure deployment. The company plans to invest the new funding in engineering, product management, sales, marketing, and technical field operations, while continuing industry outreach through events such as AutoCon, ONUG AI Networking Summit, and Cisco Live, and expanding its hiring efforts.