Production Gen AI, LLMOps and Capstone: concepts and vocabulary | Complete Generative AI: From Foundations to Production
A self-paced 26-week learning path with 15 modules: AI foundations, Python, machine learning, transformers, LLMs, prompts, APIs, embeddings, RAG, frameworks, agents, customization, multimodal AI, Spring Boot with React, and production LLMOps. Includes 15 practical assignments and three portfolio projects.
Prerequisites: Begin with basic computer skills. Programming is introduced in Weeks 2–3. Use a local Python environment for coding labs; Java and React experience helps in Weeks 21–22. Model downloads, provider accounts and deployment resources are optional learner-managed dependencies. The 26-week schedule is suggested; reading estimates exclude independent project work.
Learning goals
Evaluation and regression testing
Prompt and model versioning
Guardrails and content safety
PII protection and privacy
Caching, latency and cost
Monitoring and observability
Azure deployment and CI/CD
Capstone architecture, testing and documentation
Understand the foundations
Production readiness is a collection of measured properties: correct authorization, useful answers, bounded failures, reliable operations and a maintainable release process. Version prompts, models, embedding indexes, datasets and configuration together so an evaluation result can be reproduced. Maintain held-out cases for ordinary use, unsupported questions, malicious source instructions and permission boundaries. Include a deterministic baseline and human review for ambiguous judgments; an automated model judge is another imperfect measurement instrument.
Connect the ideas
Cache keys must include user or permission scope, source version, prompt version and model settings where these affect output. A shared cache can leak private answers even when retrieval is secure. Redact personal data from logs, set retention rules and verify deletion paths. Track error rates, queue length, time to first token, completion latency, usage and evidence-support failures. Use budgets and degraded modes when a provider is unavailable. A timeout message is safer than a fabricated successful answer.
Checkpoint: explain these concepts in your own words, then describe one failure that the design must detect. Use synthetic or permissioned data throughout the course.
01. Introduction to Artificial Intelligence · Week 1
02. Python Programming for Gen AI · Weeks 2–3
03. Mathematics and Machine Learning Foundations · Week 4
04. Deep Learning and Transformers · Weeks 5–6
05. Large Language Models (LLMs) · Weeks 7–8
06. Prompt Engineering · Weeks 9–10
07. Generative AI APIs and Application Development · Week 11
08. Embeddings and Vector Databases · Weeks 12–13
09. Retrieval-Augmented Generation (RAG) · Weeks 14–15
10. LangChain, LlamaIndex and AI Frameworks · Week 16
11. AI Agents and Agentic AI · Weeks 17–18
12. Fine-Tuning and Model Customization · Week 19
13. Multimodal Generative AI · Week 20
14. Gen AI with Java Spring Boot and React · Weeks 21–22
15. Production Gen AI, LLMOps and Capstone · Weeks 23–26