Agentic Commerce: Notes From the Construction Site
Agentic commerce - where a software agent with a goal and a budget completes the transaction for a human who never loaded…
AI
Specs, Not Vibes: What I Told Digital Analysts About Engineering’s AI Agent Revolution
MeasureCamp NYC 2026 - Recap and Reflections I gave a talk at MeasureCamp NYC last week. The title was “Specs, Not Vibes”…
AI
Delete Chat? Your Data Stays Anyway
Deleting a chat doesn't delete your data. Before your prompts and files reach an LLM, the application layer copies and stores them…
Learn about LLM
Attention Head Wars: Why Your AI Misclassifies
Why do LLMs still misclassify data even with plenty of examples? Because attention heads compete. The Floofies break down what actually fixes…
Learn about LLM
Mode Collapse
When an LLM keeps giving you the same unwanted answer, it isn't being stubborn - it's mode collapse. Why models fall back…
Learn about LLM
Context Poisoning
Corrected an LLM five times and still got the same answer? That's context poisoning: the model's own earlier answers outweigh your corrections…
Learn about LLM
Attention Dilution
LLMs don't run out of memory - they lose focus. In a Thanksgiving casserole crisis, the Floofies show how key details get…
Learn about LLM
It’s All About Data
When someone asks ChatGPT to shop for them, only products with rich, structured data show up. The Floofies' Halloween special explains how…
Learn about LLM
The Great Training
Meet the Floofies - cute furry characters that stand for the parameters inside every LLM. In Episode 1 they play "guess the…
Learn about LLM
AI Analyst Prompt Engineering Beyond Coding: Context Engineering for Analytics Workflows
In this first article in our Prompting Context Engineering for Analytics series, we are sharing learnings from our experience building a multi-agent…
AI
The Rise of the AI Analyst
Just as the rise of foundation models created the “AI Engineer” role (1) transforming software engineers productivity (2), we’re witnessing the rise…
AI
The Context Engineering Stack
Context engineering has emerged as a critical discipline for production AI systems. While models grow more capable, the challenge isn’t their raw…
AI
From Code to Context: Building AI That Thinks Like an Analyst, Not a Coder
The Architecture of Understanding: Core Systems Behind AI-Native Analytics In this Part 3 of our “What it takes to make AI Native…
AI
When should you fire your AI Coding Assistant?
Coding Assistants in Action: WindSurf, Cursor and Roo’s Approach to Complex Feature Implementation …and how Generative AI changes Software Engineering In this…
AI
When to Fire Your AI Assistant: The Hidden Architecture of Cursor and Windsurf
…and how it informs the new coding paradigm for Software Engineers This article is also published as Part of Ask-Y’s series “What…
AI
What it takes to make AI Native Analytics work in the real world
When we think of Native AI Assistants today, the first thing that comes to mind are coding assistants like GitHub Copilot, Cursor…
AI
How We’re Building an AI-Native COMPANY (Not Just an AI-Native PRODUCT)
When we started Ask-Y to build our analytics platform, we made a conscious decision that would impact us more deeply than we…
AI