AITP Chicago Meeting on Getting Better AI Results

You're Invited to an Informational presentation and discussion.

Date:  August 25, 2026      Time:  5:30-8:00 PM

Location:  TBD

Save the Date  -  Registration to open soon!

Topic:   The Knowledge Advantage: Why Some People Get Better AI Results Than Everyone Else

Everyone has access to the same AI models -so why do some people get dramatically better results? The answer isn't better prompts. It's better context.

Most AI advice focuses on prompt engineering: crafting the perfect question. But the real unlock is context engineering, systematically curating your knowledge so AI tools have the right information to work with. The difference between a generic AI output and one that feels like it was written by a domain expert isn't the model. It's what you feed it.

In this talk, we'll explore how building a "second brain", a structured personal knowledge management system using tools like Obsidian, fundamentally changes the quality of your AI interactions. Through live demonstrations, I'll walk through practical workflows for research synthesis, code generation, technical writing, and strategic decision-making, each showing the dramatic gap between prompting AI cold versus prompting it with curated context.

This isn't a talk about AI theory or model benchmarks. It's a practical playbook for knowledge workers at every level on how to build the missing layer between you and AI, and start getting results that actually reflect your expertise.

Presenter:  Arun Lakshmanan

Arun Lakshmanan is a Senior Specialist Solutions Architect at Amazon Web Services, where he specializes in OpenSearch, observability, and AI/ML technologies, including semantic search and large language models. He regularly speaks at technology conferences on search relevancy, vector databases, and practical AI applications.

With over two decades of experience spanning software engineering, architecture, and team leadership, Arun has helped organizations across retail, media, and enterprise sectors implement search and analytics solutions at scale. He brings a practitioner's perspective to AI—focused less on hype and more on what actually works when the tools meet real-world workflows.