Tools Don’t Extend an Agent. They Define It.
A 6.7-billion-parameter model, given a handful of tools, beat a model 26 times its size on a range of zero-shot tasks, from factual lookups…
Category
Agentic AI
posts
26
PART II — ReAct: The Architecture That Unified Agentic Reasoning
Most discussions of ReAct frame it as a clever prompting technique. It isn’t. ReAct is the first time we gave language models a structure…
Machine Learning Types Are the Wrong Abstraction for Agentic Systems
Executive Summary We still classify machine learning systems by how they are trained. Supervised. Unsupervised. Reinforcement learning. That taxonomy made sense when models were…
PART I — Why Most Agents Fail: The Architectural Blind Spots Behind CoT and Tool-Only Models
Modern agent demos look impressive until you load them with real work. Real constraints. Real ambiguity. Real environments. That’s when most agents collapse. And…
Context Engineering vs Prompt Engineering
"Prompt engineering" is the wrong mental model for where agents are going. It made sense when the product was a chat box. It breaks…
When AI Gives Advice, It Becomes Decision-Support Software
In late April 2025, OpenAI shipped an update to GPT-4o and within days had to pull it back. The model had become a flatterer.…