LLM Tutorials

What if your AI coding agent could improve itself? We tested Google's Harness^2 with OpenCode and DeepSeek on JobBench to find out whether self-improving AI agents actually perform better.

Learn how to run powerful decision models locally, explore the vLLM ecosystem, and build three practical projects using text, images, and videos.

Use Meta Muse Wonder and Olostep web API to check medical claims, explain the reasoning, and show where the evidence came from.

Learn what Gemini Embedding 2 is, how it compares to Nova, Voyage, and Qwen, and build a multimodal search app in Python with ChromaDB.

Decision models score a fixed set of answers instead of writing text. See how they work, how Jev compares, and what independent tests found.

A hands-on RAG evaluation tutorial in Python. Build an evaluation dataset, score it with the 4 core Ragas metrics, wire a quality gate into CI, generate synthetic test questions, and track scores across commits so you can tell a retrieval failure from a generation failure before your users do.

Follow this OpenAI Agents API Computer Use tutorial to build a Python QA agent that tests a checkout in a hosted browser and retests a fix in the same session.

Run a massive MoE model locally by combining GPU VRAM, system RAM, SGLang, and KTransformers for heterogeneous CPU-GPU inference.

Build an AI incident response agent with GPT-6.1 Sol, the OpenAI Agents API, and a hosted sandbox to investigate incidents, run checks, and generate structured reports.

Learn how to build a secure AI financial analyst with an OpenAI-hosted sandbox, from uploading financial data and running agent-driven analysis to generating and downloading reports, charts, and supporting data files.

Learn to edit images with Qwen Image 2.1 on a Colab A100, guide changes with text or drawings, and export selected results as a GIF.

Nodes do the work, edges decide what runs next, and shared state carries information between them. This graph engineering tutorial covers when a multi-agent graph actually beats a single loop, and walks through building a researcher, writer, and reviewer pipeline in LangGraph with a conditional retry edge.