2025 has been declared "the year of agents", but so were 1994, 1998, and 2016. In fact, the history of agents is a story of recurring peaks and valleys. We'll situate agents and multi-agent systems as a software paradigm alongside Objects, Actors and Microservices, examine the role LLMs and compound AI systems can play, and build a taxonomy of the various protocols and frameworks around and identify gaps enterprises need to navigate. The core thesis: agents aren't magic, they're software. And like all good software, they need a foundation of solid engineering principles of abstraction and reliability because those who don't learn from the past are doomed to be swallowed by "The Bitter Lesson" or to re-implement JADE.
Speaker
Aditya Kumarakrishnan
Technical Fellow @Walmart in Applied AI
Aditya is a self-described lover of shaving yaks, an admirer of Chesterton's fences and enjoyer of obscure references. Along with his extensive experience in building complex distributed systems to big data and real-time ML instructure, Aditya tries to bring a first-principles, historically grounded and formally sound perspective to solving problems.
As one of the technical fellows at Walmart Global Tech., he's helped lead various marquee AI initiatives at Fortune 1 scale and is now focused on building foundational enterprise agent platforms and establishing best practices for agent builders.
Some relevant topics he's especially passionate about are: metal working, types & functional programming, spending time in the wilderness, process science, tropical fruits and like many of you -- AI agents.
