Pranav Agrawal·6d agoLearning AI Agents When AI Writes the Code: A CV Chatbot in Plain PythonWhen Claude and GPT write most of the code, how do you actually learn this stuff? I built a CV chatbot from scratch in plain Python, and…
Pranav Agrawal·Oct 26Context Engineering Explained: What Goes Into an AI Agent’s Context WindowAn AI agent can have the right tools, the right data and a well-written prompt, and still give a wrong answer forty turns into a task. The…
InGenerative AIbyPranav Agrawal·Oct 24MCP Explained: A Universal Standard for Connecting AI Agents to ToolsHow MCP servers, clients, and hosts work together, with practical examples and a simple Python implementation.
Pranav Agrawal·Oct 23The ReAct Pattern Explained: How AI Agents Reason Before They ActIn Part 3, function calling gave an agent the power to act. But being able to act is not the same as knowing what to do. ReAct closes that…
Pranav Agrawal·Oct 22Function Calling Explained: How a Language Model Operates External ToolsA language model can only produce text. This article explains how that text becomes a reliable, structured instruction that your code can…
Pranav Agrawal·Oct 19Chatbot, Workflow, or Agent? A Decision Framework for LLM ApplicationsIn Part 1 we found out an agent is just a model, some tools and a loop. Which raises an awkward follow-up: if it’s that simple, why not…
Pranav Agrawal·Oct 18What an AI Agent Actually Is: A Loop, a Model and Some Tools“AI agent” is one of those phrases that sounds either like science fiction or like marketing, depending on who’s saying it. But underneath…
Pranav Agrawal·Jul 18Gaussian Mixture Models: Guide to Soft ClusteringImagine you’re handed a fish that could be a big salmon or a small tuna. Ask K-means and it will answer instantly, with total confidence…
Pranav Agrawal·Jun 11Classification Metrics: Why 99% Accuracy Can Still Be UselessA tour of accuracy, precision, recall, F1, and the two curves that finally tell you the truth for a classification model.
Pranav Agrawal·May 30How a Language Model Actually Reads: Tokenization from ScratchTransformers, Part 1. Before attention, before embeddings, before any of the parts everyone talks about, there’s one unglamorous step that…