Smart LLM Routing
Building LLM apps is easy, but scaling them without setting a pile of money on fire is hard. You really don't need the massive brainpower of GPT-5 for every single user query. Routing is how we fix th
Jun 26, 20264 min read
Command Palette
Search for a command to run...
Latest articles
Using Simulators to Evaluate Multi-Turn AI Agents
Building a multi-turn conversational AI is surprisingly easy right now. Evaluating it is incredibly hard. For single-turn tasks, a standard static dataset works fine: you just feed in a prompt and ass
Jun 19, 20264 min readWhy Grep Won't Save Your RAG Pipeline
I’ve been reading through a recent paper titled "Is Grep All You Need? How Agent Harnesses Reshape Agentic Search". It’s a provocative piece with a premise I normally love. The authors claim that simp
Jun 9, 20263 min readHarnessing Conversational AI
I’ve been spending the last few weeks messing around with open-weight models to build conversational interfaces. By now, the new reality is obvious: generating natural language is no longer the bottle
May 24, 20263 min readVectorless RAG
If you’ve built anything with LLMs in the past couple of years, you’ve probably wired up a Retrieval-Augmented Generation (RAG) pipeline. The playbook is burned into our brains: take a PDF, smash it i
May 17, 20265 min readThoughts on Advanced Chunking Strategies for RAG
I’ve been thinking a lot recently about the "chunking problem" in Retrieval-Augmented Generation. If you've played around with the llm CLI tool or built anything with vector embeddings, you've probabl
May 4, 20263 min readAll You Need is a Good Chunking
If you’ve spent any time building Retrieval-Augmented Generation (RAG) prototypes, you inevitably hit the exact same wall. You wire up a great embedding model, point it at an excellent local LLM, and
May 3, 20264 min readAI Agent Experience (AX)
In an article I recently co-authored, we argued that a fundamental shift is underway in product design. The traditional principles of User Experience (UX), which rest on direct user control and manipulation, are becoming obsolete with the rise of tru...
Jul 14, 20251 min readThe Messy Reality of Evaluating GenAI Systems
For years, evaluating traditional machine learning models, while never simple, followed a well-trodden path. Your team knew the drill: assemble a labeled dataset, define success with metrics like precision and recall, and track performance. The core ...
Jun 29, 20257 min read