Artificial Intelligence

1. AI Foundations

• AI vs ML vs Deep Learning vs Generative AI — the actual distinctions
• How LLMs work — tokens, embeddings, attention (high-level, no math overload)
• Training vs Inference — why inference cost dominates production conversations
• Foundation models — what “foundation” actually means

2. Generative AI / LLMs

• Prompt engineering fundamentals — zero-shot, few-shot, chain-of-thought
• Context windows — what they are, why they matter, their limits
• Hallucination — why it happens, mitigation strategies
• Model families landscape — GPT, Claude, Gemini, Llama, open vs closed weight

3. RAG & Knowledge Integration

• Retrieval-Augmented Generation (RAG) — architecture and when to use it
• Vector databases — embeddings, similarity search (Pinecone, OpenSearch, pgvector)
• Chunking strategies for document retrieval
• RAG vs Fine-tuning vs Prompt engineering — decision framework

4. Agents & Tool Use

• AI Agents — what makes something “agentic” vs a chatbot
• Tool use / function calling — how models call APIs
• Multi-agent systems — orchestration patterns
• MCP (Model Context Protocol) — the new integration standard
• Agentic coding tools (Claude Code, Copilot, Cursor) — how they actually work

5. AI in Enterprise Architecture

• Building AI-powered microservices — where AI fits in your existing architecture
• AI Gateway pattern — routing, cost control, model fallback
• Caching strategies for LLM calls (cost/latency)
• Observability for AI systems — tracing prompts, token usage, drift detection
• AWS AI stack — Bedrock, SageMaker, Q Business (relevant given your AWS focus)

6. Fine-Tuning & Customization

• Fine-tuning vs RAG vs Prompting — when each makes sense
• LoRA/PEFT — efficient fine-tuning explained simply
• Embeddings — custom embeddings for domain-specific search

7. AI Engineering Practices

• Evals — how to actually test if your AI feature works
• Guardrails — input/output validation, content filtering
• Cost optimization — token economics, model selection by task
• Versioning prompts like code

8. Responsible & Practical AI

• AI safety basics — alignment, misuse, why it matters for builders
• Bias and fairness in AI systems
• Data privacy in AI pipelines (PII handling, especially relevant to enterprise clients)
• Copyright and AI-generated content — practical guidance

9. Industry & Career Angle

• How AI is changing software architect/developer roles
• Building an AI-ready resume/portfolio (interview-prep style, like your STAR guide)
• Case study format: “How I added AI to a real enterprise system”