What is an Agent?
OpenAI just released their “Practical Guide to Agents.”
Harrison Chase from LangChain released an Agent Framework Comparison and a corresponding blog entitled “How to think about agent frameworks.”
According to the OG text on AI, we can define AI itself as:
“The study and design of rational agents.”
According to Chip Huyen’s book on AI Engineering, we learn about agents that:
“An agent is characterized by the environment it operates in and the set of actions it can perform.”
At AI Makerspace, we’ve been curious about defining an “agent” or “agentic reasoning behavior” for years now, following the journey of many agent framework tools.
In face, we have our own definitions for both “agent” and “multi-agent system”
Def Agent:
A system that can leverage (or emulate) reasoning (or equivalent processes) to make dynamic decisions in an application flow
Def Multi-Agent System:
A system that can leverage reasoning from multiple independent agents to make dynamic decisions in an application flow
In this event, we’ll compare what we’ve learned from every one of our agent framework (and reasoning!), including:
Agents: LangChain vs. OpenAI Assistants (11/22/23)
LangGraph and OpenGPTs: Building Agent-Forward Applications with LangChain (2/21/24)
Agentic RAG with LangChain (03/20/24)
Data Agents with LlamaIndex (04/17/24)
Multi-Agent RAG (05/15/24)
DSPy: Advanced Prompt Engineering? (6/19/24)
Multi-Agent Crews with CrewAI (06/26/24)
Monitoring Agents with AgentOps (07/03/24)
Mixture of Agents: Multi-Agent meets MoE? (7/31/24)
What is an Agent IDE? (08/24/24)
DSPy: Advanced Agents? (08/28/24)
Better Agents with LlamaIndex Workflows (09/11/2024)
Swarm: Multi-Agent Orchestration (10/23/24)
Teaching LLMs to Use Computers (11/20/24)
On-Prem Agentic RAG: Report Generation (11/27/24)
AG2: AutoGen, Evolved (12/4/24)
On-Prem Agents with LangGraph Platform (12/18/24)
Agent Evaluation with RAGAS (1/22/25)
smolagents: Small Agents? (2/5/25)
Enterprise Agents with OpenAI (4/2/25)
Tangentially, we have also covered:
Coding Agents
**Cursor: An AI Engineer’s Guide to Vibe Coding and Beyond (2/26/2025)**
Codex (4/23/25)
Large Reasoning Models (which leverage “agentic reasoning” behavior at test-time)
Large Reasoning Models (1/15/25)
DeepSeek-R1 (2/12/25)
COCONUT: Chain of Continuous Thought (2/19/25)
We’ve spent a lot of time studying agent frameworks in the last 18 months. We have opinions about what it means to be “agentic” or “agent-like,” we have clarity on the differences between “coding agents” and “code agents,” and we have pattern-matched our way to an understanding of the agentic reasoning we see in both systems engineered from agent orchestration frameworks and at test-time in reasoning models like DeepSeek-R1 or OpenAI’s o1 or o3.
Most of all, we’re curious to break down what sort of best-practices and consensus we can glean from the industry’s ongoing discussion today sparked by this “OpenAI vs. LangGraph” battle on the front of Agent Engineering, outlined very well by swyx and team at Latent.Space (building off of their work just last month!)
Join us for a rich discussion about agent framework, reasoning, and more!
📚 You’ll learn:
What everyone agrees that an agent is not.
What an agent definitely might be.
Many definitions for the word “agent.”
🤓 Who should attend the event:
AI Engineers and Leaders looking to grok Agents in 2025
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 Dayton, 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 YouTube 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.