Build useful AI products with today’s models: prompt engineering, calling LLM APIs, structured outputs, retrieval-augmented generation with vector databases, tool use and AI agents, plus safety and cost.
Course Curriculum
| 1. Prompt Engineering | |||
| 1.1 How to talk to LLMs: roles, context and examples | 00:12:00 | ||
| 1.2 Prompt patterns: few-shot, chain of thought, templates | 00:12:00 | ||
| 1.3 Prompting in Arabic | 00:09:00 | ||
| 2. Building with LLM APIs | |||
| 2.1 Calling LLM APIs from Python | 00:12:00 | ||
| 2.2 Structured outputs and JSON | 00:09:00 | ||
| 2.3 Streaming, tokens and cost control | 00:09:00 | ||
| 3. RAG | |||
| 3.1 Embeddings and vector databases | 00:12:00 | ||
| 3.2 Chunking and indexing documents | 00:10:00 | ||
| 3.3 Building a RAG chatbot over company documents | 00:15:00 | ||
| 3.4 Improving retrieval quality | 00:09:00 | ||
| 4. Agents & Tools | |||
| 4.1 Tool use and function calling | 00:12:00 | ||
| 4.2 Building an AI agent step by step | 00:15:00 | ||
| 4.3 Agent frameworks: LangChain, LlamaIndex and MCP | 00:10:00 | ||
| 4.4 No-code automation with AI: n8n and Make | 00:10:00 | ||
| 5. Shipping AI Products | |||
| 5.1 Evaluation and testing AI features | 00:09:00 | ||
| 5.2 Safety, privacy and responsible AI | 00:09:00 | ||
| 5.3 Building a simple AI web app with Streamlit | 00:12:00 | ||
| 5.4 Final project: AI customer-support assistant with RAG | 00:30:00 | ||
Course Reviews
No Reviews found for this course.






Up Academy Data & AI Team