What is an AI agent? A plain-English guide
Chatbots answer questions. Agents get things done. Here is what makes an AI agent different, how it works, and why that matters for you.
Learn
Guides for every level
Start at the beginning or jump to the deep end. Every guide is labeled by level so you know what to expect.
Learning paths
Follow a path
Each path mixes short guides with free tools you can use straight away.
Spend less using AI
Understand what you are paying for, then compare the cost of finished work, not single answers.
Can your computer run it?
Run AI models on your own hardware, and check what fits before you download.
Does your AI remember?
How AI memory and retrieval work, how to test them honestly, and how to keep them accurate.
- What is RAG? Teach AI to use your own documents Guide
- Why an installed AI memory system can still forget Blog post
- How to test AI memory without feeding it the answer Blog post
- AI Memory Recall Test Kit Free tool
- Better AI memory starts with keeping decisions current Blog post
- Project Handoff Builder Free tool
All guides
Browse by level
Writing better prompts: a simple framework
Most disappointing AI answers come from unclear requests. This six-part framework helps you ask for exactly what you want, every time.
Running AI models on your own computer: a beginner's guide
You don't always need the cloud to use AI. Here is what running a model locally means, what hardware you need, and how to get started safely.
Quantization explained: what Q4, Q5 and Q8 really mean
Quantization is how big AI models fit on ordinary computers. Learn what the labels mean, what you trade away, and how to choose.
Agent permissions: why least privilege matters
The more an AI agent can do, the more carefully its access should be designed. A practical guide to scoping permissions, approval gates and safe defaults.
What is RAG? Teach AI to use your own documents
AI models only know what they were trained on. Retrieval-augmented generation (RAG) lets them answer from your own files. Here is how it works, when to use it and how to start.
Codex, Claude, Llama and Ollama explained for beginners
Understand the difference between an AI model, an assistant, a local model runner, and an API before deciding what to use or pay for.
How to route AI work without wasting money
Match tasks to suitable tools, understand subscriptions and API bills, and compare the cost of completed work rather than the price of one answer.
No guides at this level yet. More are on the way.