The vocabulary the exams and the daily work both assume you already have. Every entry gives the definition, the source it is drawn from, and the misreadings that follow from getting it wrong.
94 concepts in Artificial Intelligence, page 1 of 5
Matching a solution type to a business need, the constraints that decide it, the steps to get it into an organisation, and how to measure whether it worked.
Artificial Intelligence
Attacks that target the model itself, rather than the software around it, and why several of them have no clean fix.
Artificial Intelligence
What changes when a model is given tools, memory and several steps to itself, and why the danger is in the permissions, whatever the intelligence.
Artificial Intelligence
Diagnose common AI agent failures and control retries, duplicate actions, invalid tool calls, plan drift and ambiguous tool results.
Artificial Intelligence
Design AI agent memory with clear ownership, source records, expiry and retrieval. Separate conversation summaries from authoritative application state.
Artificial Intelligence
The standards an AI system gets audited against, what data governance means once a model is involved, the review routine that keeps a deployed system accountable and the tooling that does each job.
Artificial Intelligence
What a team does on the day its system produces something it should not have, the decisions worth making months before that day, and when the law requires the incident to be reported.
Artificial Intelligence
Artificial intelligence, machine learning and deep learning are three nested categories, and the difference between them decides what a team can promise about a system.
Artificial Intelligence
Run a bounded agent over fictional orders, validate tool requests and use SQLite transactions to prevent duplicate actions after a lost response.
Artificial Intelligence
Build a small retrieval pipeline, filter stale and private documents, measure recall and precision, and optionally generate an answer with checked citations.
Artificial Intelligence
Gemini Enterprise Agent Platform, formerly Vertex AI, with Model Garden, the RAG offerings, custom agents and the rename the exam now expects.
Artificial Intelligence
What an evaluation can establish about a model, why the method used to test a model decides the answer as much as the model does, and what a dangerous capability evaluation is for.
Artificial Intelligence
The case that rising capability could produce harm of a different order, the serious objections to it, and why both camps ask for much the same work.
Artificial Intelligence
The criteria that actually separate one model from another, and what temperature, top p and output length do to the answers that come back.
Artificial Intelligence
How generated content is marked, why detecting it after the fact does not work, and what the law now requires.
Artificial Intelligence
Four context management strategies for LLM applications, which are external storage, relevant selection, careful compression and isolated task contexts.
Artificial Intelligence
Learn what context engineering means, how it differs from prompt engineering and how to assemble instructions, retrieval, memory and tools for an LLM.
Artificial Intelligence
The property of a system that lets people correct, interrupt or shut it down, why optimisation works against it, and what keeping it costs in a product.
Artificial Intelligence
Why unbounded consumption is a safety problem before it is a finance one, where the money in an agent run actually goes, and the limits that decide what the worst case looks like before somebody else decides it.
Artificial Intelligence
Agent Search for finding things, and the Customer Engagement Suite for handling conversations, with the four parts of the suite and what each one is for.
Artificial Intelligence