AI Fundamentals
Build a practical understanding of modern AI concepts and learn how they apply to institutional finance.
Build the vocabulary.
Short explainers for the ideas that keep showing up in institutional AI work.
Large language models (LLMs)
A beginner-friendly guide to the machinery behind ChatGPT, Claude, Gemini, and Llama.
12 min read
Prompt engineering
A practical guide to steering large language models.
15 min read
Retrieval-augmented generation (RAG)
How grounding language models in external knowledge reduces hallucination and keeps responses current.
15 min read
AI agents
How language models move from answering questions to pursuing goals, using tools, and completing multi-step tasks.
15 min read
Context windows
How much text a language model can hold in mind at once, why bigger is not always better, and what happens when you run out of room.
12 min read
Knowledge graphs
How structured relationships between entities give AI systems grounded, queryable knowledge that goes beyond text retrieval.
14 min read
Hallucinations
Why language models make things up, what causes confident but wrong output, and the techniques that reduce it.
12 min read
Reasoning models
How test-time compute lets language models think through hard problems, and what the trade-offs look like.
13 min read
Embeddings
How text becomes numbers, why similarity in vector space mirrors similarity in meaning, and the infrastructure that makes retrieval possible.
13 min read
Model Context Protocol (MCP)
The open standard for connecting AI models to external tools, data sources, and services through a universal interface.
13 min read
Explore AI terminology through an A–Z reference.
Frequently asked questions
Ten guides: large language models, prompt engineering, retrieval-augmented generation, AI agents, context windows, knowledge graphs, hallucinations, reasoning models, embeddings and the Model Context Protocol.
No. The guides are beginner-friendly, with optional Go deeper sections for readers who want the technical detail.
In series order. Each part builds on the ones before it, starting with large language models.
Yes. Every guide has a Download the PDF button; enter your work email and we send it to your inbox.
Join Pascal Academy
Learn directly from the Pascal team through live workshops.