Context Engineering
Forget prompt engineering - it’s all about putting the right stuff in context.
“Everything is Context Engineering” [Ref] is the word on the street. Is it true? We think so.
That is, it’s all about putting reference material in the context window (e.g., RAG).
In other words, it’s all about leveraging in-context learning.
Even when we give agents access to tools, the tools are used to search and retrieve data that we’ll put into an LLM’s context.
The LLM application stack that we all use to build, ship, and share using the in-context learning design pattern.
Now, everyone is talking about Context Engineering, from Tobi Lutke to Andrej Karpathy to LangChain to Phil Schmid.
In other words, context engineering is making the rounds!
At AI Makerspace, after teaching the core prototyping patterns of prompting, RAG, agents, andd fine-tuning for years, we totally agree that Context Engineering is the right way to think about building, shipping, and sharing production LLM applications.
In this event, we break down how Context Engineering has achieved the next layer of abstraction over Prompt Engineering, and how this new layer is similar to the way that LangGraph abstracted LangChain.
What is the new mental model that we should use for Context Engineering? What is the taxonomy that we should think about when reaching into our production AI Engineering toolkit?
First we’ll expand our idea of “Prompt Engineering Best Practices” to the larger idea of “Context Engineering Best Practices.”
To accomplish this, we’ll consider all of the thing that we can put in context, including instructions, developer prompts, user prompts, state, short and long-term memory, retrieved information, tools, definitions of required structured output, and more! Moreover, we’ll outline and deep dive each of the common strategies that the industry is talking about, including: write, select, compress, and isolate. Finally, we’ll discuss why it matters to think about context from a higher vantage point, and focus in on how it allows us to build fundamental more powerful and more automagical production LLM applications.
Of course, we’ll built one of these agentic-RAG-optimized context applications live to demonstrate the power of understanding Context Engineering patterns!
This should be a fun one - join us live to get your Context Engineering questions answered!
📚 You’ll learn:
Why it makes sense that Context Engineering is the new Prompt Engineering
How to master Context Engineering across Prompting, RAG, and Agent design patterns
What kinds of “Contexts” we can put into our LLM applications
How Context scales with multi-agent systems, test-time compute, and reasoning
Actions we can take for optimizing context including write, select, compress, and isolate
AI Makerspace’s Best-Practices of Context Engineering
How to build, ship, and share complex production apps with high-level context in mind
🤓 Who should attend the event:
AI Engineers and Leaders looking to build production LLM systems 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 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.