I hosted a session with Michael Struwig, Head of AI at OpenBB, who shared a fascinating approach to RAG systems that leverages the browser as a data layer. This conversation explored how financial data platforms can connect agents to sensitive data without traditional APIs, creating more secure and flexible AI-powered analysis tools.
I hosted a session with Adit, CEO of Reducto, to explore the challenges and solutions in document ingestion for AI systems. This conversation covered parsing complex documents, handling tables and forms, optimizing data representation for language models, and addressing the long tail of edge cases that make production-ready AI systems difficult to build.
I hosted a session with Will Bryk from Exa who shared insights about the evolution of search technology, how AI is changing search requirements, and the technical challenges of building a semantic search engine. This session explores how traditional search engines like Google differ from next-generation semantic search systems designed for AI applications rather than human users.
I hosted a session with Beyang Liu, CTO of Sourcegraph, to explore how the evolution of AI models has fundamentally changed how we should approach building agent systems. This discussion revealed why many best practices from the chat LLM era are becoming obsolete, and how the architecture of effective agents requires rethinking context management, tool design, and model selection from first principles.
I hosted a special session with Daniel from Superlinked to explore how we can improve retrieval systems by applying lessons from recommender systems. This conversation revealed critical insights about the limitations of current search approaches and how to build more sophisticated retrieval architectures that handle diverse data types beyond just text.
I hosted a session with Simon, CEO of TurboPuffer, to explore how vector search works at scale for RAG applications. We discussed the economics and architecture of object storage-based vector databases, performance considerations, and real-world implementations from companies like Notion, Linear, and Cursor.
I hosted a session with Vitor from Zapier to discuss how they dramatically improved their feedback collection systems for AI products. This conversation reveals practical strategies for gathering, analyzing, and implementing user feedback to create a continuous improvement cycle for RAG systems and AI applications.
This is part of the Context Engineering Series. I'm focusing on agent frameworks because understanding form factors and complexity levels is essential before building any agentic system.
Field note from a conversation with my friend Nila, who helps companies navigate AI implementation decisions: nila.is. Nila focuses on implementations and workflows; I focus on writing down strategy and execution patterns on this blog.
When companies say they want to build agents, I focus on practical outcomes. What specific functionality do you need? What business value are you trying to create?
This is part of the Context Engineering Series. I'm focusing on rapid prototyping because testing agent viability quickly is essential for good context engineering decisions.
If your boss is asking you to "explore agents," start here. This methodology will give you evidence in days, not quarters.
Most teams waste months building agent frameworks before they know if their idea actually works. There's a faster way: use Claude Code as your testing harness to validate agent concepts without writing orchestration code.
Two core insights:
This is part of the Context Engineering series. I'm focusing on compaction because it's where theory meets practice—and where we desperately need empirical research.