Deep Agents
When building agents for production, it’s no longer acceptable to build shallow, naive agents.
An LLM agent runs tools in a loop to achieve a goal [Ref].
Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, “Manus”, and “Claude Code” have gotten around this limitation by implementing a combination of four things: a planning tool, sub agents, access to a file system, and a detailed prompt. ~ LangChain
What exactly is a “deep” or “long-running” or “ambient” agent, and what makes them different, and better?
According to LangChain, there are four characteristics:
Detailed system prompt
Planning tool
Sub agents
File system
With their new Deep Agents package, we can build these more easily than ever before.
It’s also worth noting the key acknowledgement in the Deep Agents package:
Acknowledgements: This project was primarily inspired by Claude Code, and initially was largely an attempt to see what made Claude Code general purpose, and make it even more so.
This is interesting, especially in the context of Anthropic releasing the Claude Agent SDK recently.
We’re excited to dig into the idea of Deep Agents, and to go deep enough to connect them to some of the emerging trends and best practices that we continue to see role out from thought leaders throughout the coding agent space!
🤓 Who should attend
Anyone interested in building, shipping, and sharing agents at the edge of what’s currently possible!
AI Engineers building production AI applications who want to stay up-to-date on the latest in the Lang-X ecosystem.
AI Engineers and AI Engineering leaders who are curious about how emerging best-practices for context engineering learned from coding agents continues to diffuse to other parts of the AI landscape.
Speaker Bios
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Columbus, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.