Imagine managing a racing team during a championship race. 

Success is not determined by a single driver alone. It depends on a highly coordinated team operating in real time. Engineers analyze telemetry continuously. Strategists predict changing track conditions. Pit crews execute precision adjustments. Analysts identify risks before they become failures. Every team member specializes in a different function, yet all must work together dynamically to keep the car performing at peak efficiency under constantly changing conditions. 

Modern network operations face a very similar challenge. 

Today’s large-scale infrastructure networks are living, constantly evolving systems. Traffic patterns shift unpredictably. AI is reshaping workloads and infrastructure demands. Multivendor environments generate overwhelming volumes of telemetry while operational data remains siloed across domains. Even with automation in place, operations teams often remain trapped in reactive workflows, manually troubleshooting incidents, correlating alarms across disconnected domains, and resolving issues only after services are impacted. 

It’s no longer enough to simply automate individual tasks. Instead, teams must enable intelligent operational teamwork at machine speed. 

This is where Cisco Crosswork Network Automation is changing the paradigm of network operations. 

At Cisco Live, we are introducing the next evolution of the Cisco Crosswork Network Automation ste: Cisco Crosswork® AI, a secure, scalable multi-agentic framework designed to act as an extension of your network team. Much like a championship racing team, specialized AI agents work together continuously, reasoning through problems, identifying risks, troubleshooting complex issues, validating operational intent, and recommending corrective actions in real time. 

Cisco Crosswork Network Automation is the heartbeat of our Agile Services Networking architecture for AI connectivity, enabling teams to operate resilient, AI-ready networks at scale. 

Cisco Crosswork AI is a transformative multi-agentic AI framework integrated within Cisco Crosswork Network Automation, debuting with a powerful team of specialized agents designed to tackle the most demanding operational challenges.  Crosswork AI  Cisco AI Canvas(the that’s part of ), to provide unified, cross-domain management. 

• Deep network troubleshooting: Like race engineers diagnosing performance anomalies in real time, these agents reason through complex issues, evaluate hypotheses, and pinpoint root causes with precision to reduce mean time to repair (MTTR), minimizing service downtime.  
• Risk factor detection: Similar to strategists anticipating tire degradation or changing track conditions before they impact race performance, these agents uncover hidden combinations of variables that trigger network degradation, helping resolve issues proactively before services are affected.  
• Configuration drift remediation: Much like the team members who help ensure every race car component remains calibrated to exact specifications throughout the race, these agents continuously detect configuration drift, identify variances using AI trained on device configurations, and provide remediation recommendations to maintain operational consistency.  

This extensible framework supports an expanding ecosystem of agents, both out-of-the-box and customized, with the ability to bring your own agents through the agent development kit (ADK). With capabilities such as agent evaluation, a knowledge graph, and an agent catalog, the framework establishes a strong operational foundation for agentic operations, enabling networks to evolve from automated systems to intelligent operational teams. 

Crosswork AI multi-agentic architecture has already been recognized on the industry stage. The platform was featured in the TM Forum Catalyst project “Game X,” selected as a Moonshot project, an honor reserved for initiatives demonstrating transformative potential for the telecommunications industry. This recognition underscores how Crosswork AI can power next-generation, AI-driven network operations at scale.

In racing, winning is not about excelling in a single lap. Success depends on orchestrating the entire race lifecycle, from pre-race planning and strategy simulation to live telemetry analysis, pit-stop execution, and continuous optimization throughout the race. 

The same principle applies to modern network operations. 

The true value of Crosswork lies in its ability to manage the entire network lifecycle, from device onboarding to end-to-end service delivery including planning, orchestration, assurance, optimization, and troubleshooting. 

Crosswork enables organizations to: 

• Unify visibility: Similar to how race engineers maintain complete visibility into vehicle performance, tire conditions, fuel strategy, and competitor positioning, Crosswork provides comprehensive end-to-end visibility across topology, telemetry, and service health with AI-enhanced operational clarity.  
• Correlate insights: Just as racing teams transform thousands of telemetry signals into strategic race decisions, Crosswork converts multisource telemetry, service, and state data into actionable intelligence that improves operational precision and business outcomes.  
• Drive action: Like a smooth, perfectly timed pit stop that restores peak performance without disrupting the race, Crosswork enables effective, streamlined lifecycle operations through automated provisioning, AI-guided remediation, and closed-loop operational workflows.  

The platform continuously translates business and operational intent into network reality. 

The modern network is rarely a single-vendor environment. Crosswork leverages standard APIs and protocols, including NETCONF, RESTCONF, TAPI, OpenConfig, and native YANG data models, as well as streaming telemetry from gRPC, BGP-LS, and gNMI, to enable effective automation across multivendor environments.  

By adhering to open, industry-recognized interfaces, Crosswork allows for interoperability without vendor lock-in, enabling teams to easily adopt new technologies, platforms, and domains.  

This commitment to openness is backed by independent, real-world validation across top-tier service provider, public sector, and enterprise multivendor networks across the world. In the European Advanced Networking Test Center (EANTC) interoperability showcase, Crosswork successfully automated services across a diverse ecosystem of vendor devices, demonstrating multivendor richness in a live, heterogeneous environment.  

We recognize that real-world networks often include legacy systems and specialized devices that do not support standardized interfaces. To solve for multivendor automation in any environment, Crosswork provides an open SDK for customized packages and agents to handle proprietary integrations, helping ensure no device or domain is left behind. 

Whether your environment is built on the latest standards-based platforms or includes a mix of legacy and proprietary systems, Crosswork delivers consistent, end-to-end automation, protecting existing investments while accelerating modernization.  

This multi-agentic evolution is more than just a feature update. It is a fundamental shift in how network assurance and automation are approached.  

We look forward to showcasing these innovations at Cisco Live 2026 in Las Vegas and demonstrating how Cisco Crosswork AI, part of our broader Cisco vision for agentic operations, can help organizations accelerate their journey toward resilient, intelligent, and autonomous networking. 

Visit us at the Secure Global Connectivity area inside the World of Solutions to experience the multi-agentic framework in action and discover how Cisco Crosswork AI can help you operate with the precision, intelligence, and coordination of a championship-caliber network operations team.

Streamline automation and assurance with the power of agentic AI

Additional resources: 

• Cisco Crosswork AI At-a-Glance 
• Cisco Crosswork Network Automation blogs, reports, and more 
• What is network automation?