Alejandro AO - Videos
Back to Channel
Pi Agent – Crash Course | Minimal Coding Agent
Pi Agent is a lightweight terminal harness that gives you a powerful coding assistant without the bloat. Unlike traditional agents with built-in sub-agents, plan modes, and permission popups, Pi st...
DeepSeek V4: SOTA Coding Agent at 12x Lower Cost
DeepSeek V4 Pro matches GPT-5.5 and Opus 4.7 on agentic coding benchmarks at 3x lower cost. In this video, we compare Terminal-Bench, SWE Verified, and MCPAtlas scores across all SOTA models, analy...
GPT-5.5 - 25x More Expensive than Open Models
A quick overview of OpenAI's GPT-5.5 announcement—comparing it against open source models on benchmarks and pricing to see if it's actually worth using in your apps. 🤓 Topics Covered - GPT-5.5 ben...
Kimi K2.6: Open Source BEATS GPT-5.4 & Opus?
In this video, we take a deep dive into Kimi K2.6, the latest open-source foundation model from Moonshot AI. We explore how it stacks up against GPT-5.4 and Claude Opus 4.6, walk through key benchm...
MiniMax M2.7 vs GPT 5.4 (Real Coding Tasks)
In this video I take a look at MiniMax M2.7 right after the open weights dropped and compare it against GPT 5.4 on practical software tasks. I go through the benchmark context briefly, then test bo...
How to Evaluate and Test Agent Skills
This video walks through a practical workflow for evaluating and testing agent skills so you can improve them without breaking what already works. I use the Hugging Face `$model-trainer` skill as t...
Gemini Embedding 2: Multimodal Retrieval Demo with ChromaDB
Gemini Embedding 2 just dropped, and this release is a big step for multimodal retrieval workflows. In this video, I walk through what is new, key limits to know before you build, benchmark highli...
Best LLMs for UI design?
In this video I run a live UI beauty comparison across four models: Claude 4.6, GPT-5.2, MiniMax M2.5, and Kimi K2.5. Instead of benchmarking architecture or feature completeness, I focus on visual...
Fine-Tune an Open Source LLM with Claude Code/Codex (Hugging Face Model Trainer Skill)
In this video I show how to fine-tune a small open source model with Codex using the Hugging Face model trainer skill and HF Jobs. We train `Qwen/Qwen3-0.6B` into a customer-support ticket router o...
GPT-5.3 Codex vs Claude Opus 4.6: Real Coding Tasks
In this video, I compare GPT-5.3 Codex and Claude Opus 4.6 using a benchmark overview plus 4 real engineering tasks. Connect with me 🤗 - X: https://x.com/_alejandroao - LinkedIn: https://www.linke...
Kimi Code vs Claude Code vs Codex - NEW Best For Coding?
Hands-on comparison of Kimi K2.5 vs GPT 5.2 vs Opus 4.5 on coding tasks. I tested all three models on physics simulations: Maxwell's Demon thermodynamics experiment and a hand-gesture controlled ga...
Claude Code Skills & skills.sh - Crash Course
Learn everything about Agent Skills - the open standard for AI agent customization adopted by Anthropic, OpenAI, Microsoft, GitHub, and Cursor. This tutorial covers what skills are, how to install ...
MedGemma 1.5: Google's Open-Source Medical AI with 3D Imaging (Tutorial)
Run Google’s new MedGemma 1.5 locally for private, GPU‑accelerated medical AI. In this video, we break down what MedGemma 1.5 is, how its open‑weight 4B model runs on consumer hardware, and where i...
Create a Local Claude Cowork with Open Models
Tutorial to build an Open Cowork, a local, privacy-first alternative to Claude CoWork --- Connect with me 🤗 - X: https://x.com/_alejandroao - LinkedIn: https://www.linkedin.com/in/alejandro-ao/ -...
Create an Open Deep Research Multi-Agent in Python (Step by Step)
Build a complete multi-agent deep research system with open-source models: use Hugging Face Inference Providers, Firecrawl MCP tools for web search and scraping, and smolagents for agent coordinati...
Intro to Agents - Create an Agent from Scratch (No Frameworks)
Build an LLM agent from scratch in Python using Hugging Face Inference Providers. --- Connect with me 🤗 - X: https://x.com/_alejandroao - LinkedIn: https://www.linkedin.com/in/alejandro-ao/ --- L...
Intro to AgentKit - Create a RAG Agent
Build and deploy an OpenAI AgentKit workflow end-to-end: design a production-ready RAG agent in AgentBuilder with guardrails and the built-in File Search (Anna Karenina), preview with evals and tra...
Intro to ChatGPT Apps - The NEW App Store??
Here is intro to ChatGPT Apps with the OpenAI Apps SDK. We cover how ChatGPT apps extend the Model Context Protocol (MCP) with tools and UI schemas, handle OAuth 2.1, test locally, deploy a remote...
ChromaDB Crash Course - Intro to Vector Databases
Master vector databases and embeddings in Python: map text to high-dimensional vectors, spin up a local ChromaDB, run end-to-end CRUD on collections and points, search by meaning, and persist your ...
Python Project: AI Image Generator App
Build a Tinder-style AI image generator in Python with Streamlit and Google’s Gemini API: set up the project with uv, design a clean Streamlit UI (prompt, image uploader, generate button), and tran...
Image Generation with Nano Banana - Python Tutorial
This is an image generation tutorial with Google's new model Gemini 2.5 Flash (aka “Nano Banana”). We will learn how to set up the google‑genai Python SDK, get an API key from Google AI Studio, cal...
MCP Servers for VS Code (Crash Course)
Supercharge GitHub Copilot in VS Code with the Model Context Protocol (MCP): install and configure MCP servers (including Firecrawl), wire up custom tools over STDIO, and build a Python MCP server ...
MCP Security | Malicious MCP Servers (Protect Yourself)
We cover security concerns of MCP servers, especially those using the STDIO transport. You'll learn how to spot malicious MCP servers and protect yourself from them. You'll also learn how MCP agent...
RAG Project: Build an AI Onboarding Chatbot with Streamlit, LangChain, and ChromaDB
In this comprehensive video, you'll learn how to build a fully functional AI-powered onboarding chatbot tailored for new employees at a fictional company (Umbrella Corporation). The tutorial walks ...
#4 Allan Guo | 19-yo YC Founder - Willow Voice
Interview with Allan Guo: Building Willow Voice, the Next-Gen AI Voice Dictation App Backed by YC --- 🔗 Links - 📣 Willow Voice: https://willowvoice.com/?ref=AAO40 - 🤓 Allan Guo: https://www.linked...
Generate UI Tests with TestSprite MCP Server + TRAE
We’ll go step by step through the process of using some tools for generating Apps with AI (vibe coding): generating a clear Product Requirements Document (PRD) with TRAE, coding the app in Next.js ...
Tutorial: Auth for Remote MCP Servers (Step by Step) | OAuth 2.1 with ScaleKit
In this tutorial, I’ll show you how to secure your MCP (Model Context Protocol) servers with OAuth 2.1 authentication, using FastAPI and ScaleKit. You’ll learn step by step how to implement authent...
GPT-5 for Developers: API Changes, Pricing, Model Router & Security
GPT-5: New API Features, Pricing & Security Explained: In-depth exploration of everything you need to know about GPT-5, focusing on the technical changes, new API features, pricing models, and adva...
Deploy Remote MCP Servers in Python (Step by Step)
🚀 MCP Servers over Streamable HTTP (Step-by-Step Guide) Want to connect remote tools to your AI assistant like microservices? Meet MCP (Model Context Protocol) — the protocol that lets your LLM-bas...
Anthropic: How to Build Multi Agent Systems
How Anthropic Built a Multi‑Agent AI Research System + Tips for Your Own! Links - Anthropic’s article: https://www.anthropic.com/engineering/built-multi-agent-research-system - Writing Wikipedia...
Local MCP Servers for Cursor (Step by step)
In this video, you'll learn how to create a custom MCP (Model Context Protocol) server in Python, mock-integrate it with Confluence, and expose custom tools to the Cursor code editor. The tutorial ...
LlamaExtract Tutorial: Convert PDF & Images into JSON
How to Extract Structured Data from Unstructured Files Using Lama Extract (LlamaIndex) This video is a comprehensive tutorial on using LlamaExtract, a tool by LamaIndex, to automatically extract s...
Vibe Coding For Engineers (make it ACTUALLY work)
Here is a better way to do Vibe Coding with AI IDEs like Cursor, Copilot, Tree, and Windsurf. In this video, you’ll learn how to vibe code while building secure, useful, and maintainable code. We’...
How to Build an MCP Client GUI with Streamlit and FastAPI
In this video, you'll learn how to build a graphical user interface (GUI) for an MCP client using Streamlit in Python, and connect it to a FastAPI backend. The tutorial covers the full process—fr...
Create an MCP Client in Python - FastAPI Tutorial
In this tutorial we cover how to create an MCP client in Python using FastAPI. We will take inspiration from the Claude Desktop application to make our LLM call the MCP tools from our MCP server an...
Create MCP Clients in JavaScript - Tutorial
In this video, we cover how to create an MCP client that can connect to any MCP server. We will build this from scratch by showing you how to turn a simple chatbot into a chatbot that supports MCP ...
Learn MCP Servers with Python (EASY)
In this video, I explain what an MCP server is, how it works and how to create an MCP Server that we will use with Claude Desktop and Claude Code. 🔗 Links --- 🚀 Complete AI Engineer Bootcamp: http...
![Advanced RAG with LlamaIndex - Metadata Extraction [2025]](https://i.ytimg.com/vi/yzPQaNhuVGU/mqdefault.jpg)
Advanced RAG with LlamaIndex - Metadata Extraction [2025]
Learn advanced Retrieval-Augmented Generation (RAG), focusing on techniques such as metadata augmentation and metadata filtering using LlamaIndex. This will help you improve your RAG models for bet...