DeepLearning.AI

**DeepLearning.AI** launched **Transformers in Practice**, a new course taught by **Sharon Zhou** (VP of Engineering & AI at AMD) covering LLM internals from both model and systems perspectives.

The course teaches why hallucinations occur and how techniques like **RAG** and constrained generation mitigate them, alongside GPU inference optimizations including **KV caching**, **quantization**, **flash attention**, and **speculative decoding**.

Interactive visualizations are used throughout to build intuition for transformer mechanics including token-by-token generation, sampling, and attention—topics typically difficult to grasp through theory alone.

**DeepLearning.AI** launched **AI Prompting for Everyone**, a new course taught by **Andrew Ng** covering practical AI prompting techniques for non-technical professionals.

The course teaches skills including web search and deep research modes, AI-assisted brainstorming, and creating images, websites, and simple apps with no coding required.

The course targets professionals in any role — marketers, salespeople, students, and founders — who want to get more accurate and useful results from AI tools.

**DeepLearning.AI** launched a new short course 'Build Interactive Agents with Generative UI' taught by **CopilotKit** CEO Atai Barkai, covering fullstack agent apps that render dynamic UIs.

The course teaches how to connect **LangChain** agents to a **React** frontend via the **AG-UI protocol** to generate charts, forms, and cards on demand.

Learners will also build canvas-style apps with shared agent-user state and use **MCP Apps** to connect agents to external tools and data sources.

**Andrew Ng** launched **AI Prompting for Everyone** on **DeepLearning.AI**, teaching practical prompting for web search, writing, image creation, and no-code app building.