Core AI Concepts

Learn the core concepts behind prompting, embeddings, chunking, and multi-model workflows.

These concepts help you build better workflows in StackAI. Start with prompting, then add retrieval and orchestration patterns.

If you are new to LLM workflows, start with prompts and embeddings first.

Start with the fundamentals

Concept

Prompt Engineering Write clearer instructions, structure prompts, and improve output reliability.

Page

Prompt Engineering

Concept

Instruction vs Prompt Separate stable system behavior from task-specific user input.

Page

Instruction vs Prompt

Concept

Embeddings Understand how text becomes vectors for semantic search and retrieval.

Page

Embeddings

Go deeper into retrieval and orchestration

Concept

Chunking Split content into useful units for stronger retrieval quality.

Page

Chunking

Concept

Using Multiple LLMs Design workflows that route, compare, or chain multiple models.

Page

Using Multiple LLMs

Recommended order

1. Learn Prompt Engineering.

2. Learn Instruction vs Prompt.

3. Learn Embeddings and Chunking.

4. Apply them in Using Multiple LLMs.

Next step

When you are ready to build, move into Get Started with Workflow Builder or follow the Stack AI Curriculum.