Build AI things
Build real AI products: assistants that act, answer from your own docs, and serve a niche.
AI Agents 101
What an agent actually is, when to use one (and when a single prompt wins).
OpenBuild a Niche Assistant
Pick one task you do weekly. Ship a focused AI assistant for it. End with something you actually use.
OpenRAG: Answers grounded in your own docs
The technique that turns "AI hallucinates about my docs" into "AI knows my docs cold".
OpenMemory & Tool Use
How agents remember and how they reach into the world. The two skills that separate "demo" from "shipped".
OpenData & Vector Foundations
The layer under every good RAG system: embeddings that mean something, chunking that respects structure, vector stores you can query honestly, and retrieval quality you can measure before users measure it for you.
OpenMCP & Tool Protocols
Give your agent hands it can trust: tool schemas that validate, an MCP server any client can discover, security boundaries that respect privilege, and compositions that turn single tools into workflows.
OpenMultimodal & Voice AI
Build with text, image, and audio together: the modality tradeoffs, a voice pipeline that survives real conversation, vision flows that understand documents, and the Arabic-first choices that make it all work for your users.
OpenComputer Vision Basics
From pixels to products: how machines see, train a real classifier, know when to use off-the-shelf vision APIs instead, and run vision in production with honest metrics and camera privacy rules.
OpenShip an AI-powered product
The timeless decisions of productizing AI — memory, surface, and reach are yours to pick.
Open