LLM

Fundamentals

• Language AI
• Large Language Model
• Tokenization
• Embedding
• Transformer

Model Families

• Representation Model
• Generative Model
• Multimodal LLM
• LLM Architecture Comparison
• Autoregressive Language Model
• World Models
• Reasoning Model

Application Patterns

• Representation Model vs Generative Model vs RAG
• Text Classification
• Semantic Search
• Retrieval-Augmented Generation
• Agentic RAG
• LLM Agent
• Tool Use
• Function Calling
• Model Context Protocol
• Voice AI Infrastructure
• Design-to-Code Context
• Code Connect
• Component Mapping
• Design System Drift
• Prompt Engineering
• Context Engineering
• Multimodal LLM
• Graph RAG
• Model Router
• AI Search
• Hybrid Retrieval
• Evidence-Grounded Generation
• Feed Retrieval
• Semantic Retrieval
• Generative Retrieval
• Recommendation Funnel
• Cold Start Problem
• Ranking
• Query Understanding
• Two-Tower Retrieval
• Vector Search Infrastructure
• Commonsense Knowledge Graph
• Product Recommendation System
• Multimodal Search
• Multimodal Annotation Fusion
• Foundation Model for Recommendation
• Embedding Lifecycle Management

Agents And Context

• Agentic Loop
• Agent Harness
• Coding Agent
• CLI AI Coding Assistants
• Agent Communication Protocol
• A2A Protocol
• Context Compression
• LLM Memory
• Multi-Agent System
• Agent Tracing
• Agent Evaluation
• Prompt Injection
• Indirect Prompt Injection
• Excessive Agency
• Lethal Trifecta
• Agents Rule of Two
• Untrusted Model Output
• LLM Supply Chain Security
• RAG Knowledge Base Poisoning
• LLM Security
• AI Hallucination
• LLM Threat Model and Agent Security
• AI Engineering Systems from RAG to Agents

Training And Alignment

• Fine-tuning
• Parameter-Efficient Fine-Tuning
• LoRA
• QLoRA
• Loss Function
• Model Alignment
• Reinforcement Learning from Human Feedback
• RLHF
• Direct Preference Optimization
• DPO
• Preference Learning

Inference And Deployment

• AI Model Serving
• ML Platform and Prediction Serving Patterns
• ML Platform
• Feature Store
• Training-Serving Skew
• Prediction Serving Fanout
• Model Self-Test
• Model Shadowing
• Prediction Logging
• Model Onboarding
• Annotation Platform
• LLM Inference Engineering
• LLM Cost Optimization
• Model Distillation
• AI Hardware Accelerator
• Transformer Inference Optimization
• KV Cache
• Model Benchmarking
• LLM Evaluation
• LLM Observability
• LLM-as-Judge
• Retrieval Evaluation
• Citation Quality
• Knowledge Distillation
• Quantization
• ONNX Runtime

Sources

• Hands-On Large Language Models
• Hands-On LLM - Chapter 01 - An Introduction to Large Language Models
• Hands-On LLM - Chapter 02 - Tokens and Embeddings
• Hands-On LLM - Chapter 03 - Looking Inside Large Language Models
• Hands-On LLM - Chapter 08 - Semantic Search and Retrieval-Augmented Generation
• 2026-05-23_ep216-rags-vs-agents
• 2026-05-16_ep215-the-anatomy-of-an-ai-agent
• 2026-05-04_connecting-llms-to-the-real-world-tool-use-function-calling
• 2026-04-06_a-guide-to-context-engineering-for-llms
• 2026-06-15_a-guide-to-ai-inference-engineering
• 2026-01-12_a-guide-to-llm-evals
• 2026-08-03_llm-security-basics-the-full-threat-model
• 2025-12-22_multimodal-llms-basics-how-llms-process-text-images-audio-vi
• 2026-07-14_how-llms-learn-to-be-helpful-rlhf-vs-dpo
• 2026-01-19_why-ai-needs-gpus-and-tpus-the-hardware-behind-llms
• 2025-10-20_what-actually-happens-when-you-press-send-to-chatgpt
• 2025-07-29_how-cursor-serves-billions-of-ai-code-completions-every-day
• 2026-07-01_how-openai-delivers-low-latency-voice-ai-for-900m-users
• 2026-03-18_how-openai-codex-works
• 2026-01-26_how-cursor-shipped-its-coding-agent-to-production
• 2026-07-29_how-chatgpt-optimizes-its-agent-loop-harness-api-and-inferen
• 2026-06-27_ep220-rag-vs-graph-rag-vs-agentic-rag
• 2026-07-07_chatgpt-vs-gemini-vs-claude-how-they-differ
• 2026-05-20_how-netflix-is-using-multimodal-ai-to-power-video-search
• 2025-05-01_inside-netflixs-radical-shift-to-a-single-foundation-model
• 2026-04-27_how-amazon-uses-llms-to-recommend-products
• 2026-05-05_how-instacart-built-a-search-for-billions-of-products
• 2026-05-27_how-airtable-built-the-search-layer-behind-their-ai-features
• 2026-07-28_why-doordash-instacart-and-uber-eats-integrated-llms-into-se
• 2025-09-16_how-anthropic-built-a-multi-agent-research-system
• 2026-02-09_how-yelp-built-yelp-assistant
• 2026-01-20_this-isnt-an-ai-summarizer-and-that-matters-byte-sized-design
• 2026-08-10_how-to-fight-clickbait-meta-linkedin-youtube-case-studies

Questions

• When to Use Representation Model Instead of Generative Model
• When Is RAG Better Than Fine-Tuning
• How to Evaluate LLM Systems