1d ago · 9 min read · This is Part 3 of the AI Engineering with TypeScript series. Prerequisites: Part 1 — What is MCP? · Part 2 — MCP Fundamentals Stack: Node.js 20+ · @anthropic-ai/sdk · @modelcontextprotocol/sdk v1.x ·
Join discussion
5d ago · 5 min read · For two years, AI agents were the "next big thing" that never quite arrived. Demos were impressive. Production deployments were rare. The gap between what agents could do in a controlled demo and what they could do in the real world was enormous. Tha...
Join discussionApr 30 · 7 min read · If you have built a Claude-powered app and added tool use, you already know the problem: the model freezes at the UI level while it reasons and calls tools. Streaming alone fixes text output latency — but streaming with tool use is a different beast....
Join discussion
Apr 12 · 11 min read · Welcome to Module 6 — the last one. The course has taken you from "what even is AI" in Module 1 to the insides of a transformer in Module 4 and the everyday failure modes of LLMs in Module 5. This final module is about what happens next — where the t...
Join discussion
Mar 12 · 15 min read · TLDR: A tool is a single callable capability (search, SQL, calculator). A skill is a reusable mini-workflow that coordinates multiple tool calls with policy, guardrails, retries, and output structure. If you model everything as "just tools," your age...
Join discussion
Mar 12 · 14 min read · TLDR: These are not competing ideas. They are layers. Tools do one action. MCP standardizes access to actions and resources. LangChain and LangGraph orchestrate calls. Skills package business outcomes with contracts, guardrails, and evaluation. Most ...
Join discussion
