AI Engineering
AI Foundations
Beginner-first AI vocabulary and mental models for software engineers who want the words before the machinery.
foundation
What Is AI?
Explain artificial intelligence in plain English for software engineers before introducing models, training, inference, prompts, agents, or vector databases.
foundation
AI vs Machine Learning vs Deep Learning vs Generative AI
Explain the difference between AI, machine learning, deep learning, and generative AI in plain English before moving into models or LLM internals.
foundation
What Is A Model?
Explain what an AI model is in plain English for software engineers before introducing training, inference, parameters, tokens, or agents.
foundation
Training vs Inference
Explain the difference between training and inference in plain English so software engineers understand when models learn and when products use them.
foundation
Data, Datasets, Examples, And Labels
Explain the beginner data vocabulary behind AI training so software engineers know what people mean by datasets, examples, labels, and signals.
foundation
What Is A Neural Network?
Explain neural networks in plain English for software engineers before deeper deep-learning, transformer, and optimization concepts.
foundation
Parameters And Weights
Explain parameters and weights in plain English so software engineers understand where learned model behavior lives before transformer internals.
foundation
What Is A Large Language Model?
Explain large language models in plain English before software engineers move into tokens, prompts, parameters, retrieval, or agents.
foundation
Tokens And Tokenization
Explain tokens and tokenization in plain English so software engineers understand how language models read, price, limit, and generate text.
foundation
Prompts, Context, And Completions
Explain prompts, context, and completions in plain English so software engineers understand what a language model receives and returns.
foundation
Training Data vs Context vs Memory
Explain the difference between training data, context, and memory in plain English for software engineers building their first AI mental map.
foundation
Hallucinations
Explain AI hallucinations in plain English so software engineers understand why fluent model output can still be wrong or unsupported.
foundation
Embeddings In Plain English
Explain embeddings in beginner-friendly language before introducing vector databases, semantic search, retrieval, or RAG.
foundation
Vectors In Plain English
Explain vectors in plain English so software engineers can understand embeddings, similarity, retrieval, and vector search without a math-first start.
foundation
Semantic Meaning And Similarity
Explain semantic meaning and similarity in plain English before software engineers move deeper into retrieval, RAG, and vector search.
foundation
Retrieval In Plain English
Explain retrieval in AI products as the step that finds useful information before a model answers, without starting with RAG frameworks.
foundation
RAG In Plain English
Explain retrieval augmented generation in beginner-friendly language as the pattern of retrieving useful context before generating an answer.
foundation
Fine-Tuning vs Prompting vs Retrieval
Compare fine-tuning, prompting, and retrieval in plain English so software engineers know which AI improvement lever they are discussing.
foundation
Multimodal AI In Plain English
Explain multimodal AI in plain English so software engineers understand models and products that work across text, images, audio, video, and other inputs.
foundation
What Is An AI Agent?
Explain AI agents in plain English so software engineers understand model-driven workflows with goals, tools, state, steps, and boundaries.
foundation
Tool Use And Function Calling
Explain tool use and function calling in plain English so software engineers understand how models connect to external software actions safely.
foundation
What Are Evals?
Explain AI evals in plain English so software engineers understand how teams test model-backed behavior beyond a few impressive demos.