IBM Corp. is focused on developing AI agents that execute across systems rather than merely assist at the edges. These agents are designed to integrate with legacy and modern tools, orchestrating processes across the full sprawl of enterprise infrastructure, according to Ritika Gunnar, general manager for data and artificial intelligence at IBM. Instead of replacing entire software stacks with AI-native applications, IBM blends agentic functionality into existing systems. That strategy includes leveraging fixed workflows, enabling agent-based enhancements and allowing customers to scale into full orchestration when needed, according to Gunnar. To help enterprises get started, IBM has unveiled a lineup of prebuilt AI agents in areas such as human resources, sales and procurement, with more planned in customer care and finance, according to Gunnar. These domain-specific agents can be customized, integrated and orchestrated using IBM’s frameworks. “[We have] a new interaction paradigm to work across this multi-agent orchestration framework, across all those systems, whether those be agents, tools or anything else underneath that. It is about [being] open … hybrid … because we know agents are going to run everywhere. Your systems are going to exist in many different forms, in agentic and non-agentic.” The agentic strategy converges with IBM’s push to unlock unstructured data. IBM’s watsonx offerings aim to bridge IT and business needs by enabling users to build intelligent AI agents grounded in enterprise data, according to Gunnar. “We believe that we’re going to see an explosion of the 90% of unstructured data that today has been untapped; you’re untapping a whole new set of intelligence that’s now available.”