Enterprise AI Agents: From Prototypes to Production

What is the Workshop About?

Large language models (LLMs) have evolved from standalone generative systems into agentic AI systems capable of planning, reasoning, tool use, and multi-agent collaboration. Enterprises are increasingly adopting AI agents to automate and orchestrate complex workflows, from IT operations, supply chain optimization and planning, to employee productivity. While early deployments focused on proof-of-concept prototypes, the past year has marked a clear shift toward production-grade enterprise AI agents. This transition has been enabled by a wave of new technologies, including multi-agent orchestration, memory and state management, skill-based and modular agent architectures, advances in reasoning and verification techniques, and deeper integration with enterprise data and workflow platforms, which together make scalable, reliable agent systems feasible in practice. At the same time, moving agents into production introduces new technical and organizational challenges, such as reliability under uncertainty, rigorous evaluation and benchmarking, security and governance, and system design for long-running, autonomous operation.

This workshop aims to bring together researchers and practitioners to examine how enterprise AI agents can successfully move from prototypes to production.

Workshop Focus Areas

We’ll dive into three core themes:

1. Agent architectures and systems, e.g., multi-agent frameworks, memory systems, and skill-based agent design;

2. Enterprise applications and deployments, e.g., real-world case studies and infrastructure for agents from industry;

3. Evaluation and governance, e.g., benchmarks and trust mechanisms.