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.
The main idea: When AI tools do messy tasks, they can either stay focused or get confused by too much information.
This is part of the Context Engineering Series that shows how to build better AI tools based on what I've learned from coding assistants and business systems.
I've been helping companies build agentic RAG systems and studying coding agents from Cognition, Claude Code, Cursor, and others. These coding agents are probably unlocking a trillion-dollar industry—making them the most economically viable agents to date.
This series shares what I've learned from these teams and conversations with professional developers using these systems daily, exploring what we can apply to other industries.
If you want hands-on help, I recommend reaching out to my friend Nila: nila.is. Please mention you came from me.
Related Series
Coding Agents Speaker Series: Deep insights from the teams behind leading coding agents including Cognition (Devin), Sourcegraph (Amp), Cline, and Augment. While this Context Engineering series focuses on technical implementation patterns, the Speaker Series reveals strategic insights and architectural decisions.
RAG Master Series: Comprehensive guide to building and scaling retrieval-augmented generation systems. Context Engineering principles directly enhance RAG implementations—structured tool responses and faceted search are foundational RAG optimization techniques.
The core insight: In agentic systems, how we structure tool responses is as important as the information they contain.
This is the first post in a series on context engineering. I'm starting here because it's the lowest hanging fruit—something every company can audit and experiment with immediately.
These are example questions we tackled in office hours across previous cohorts. Office hours are not currently running.