# Chapter 0.1. What AI Actually Is (/how-ai-works/what-ai-actually-is/overview) --- type: Document title: "Chapter 0.1. What AI Actually Is" description: "What a model works from when it answers you: what it learned in training and the context window built for each reply, and why that explains memory, sure-sounding guesses, tokens and tools." status: stable order: 11 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-10-17T01:47:35Z chapter: "0.1" part: "0" expert_status: null # as the Part 0 overview: Part 0 is optional on every route, after the skip quiz objectives: - { id: CCAO-F.D2.T2, label: supporting } # Spot hallucination, inconsistency and bias. Primary: Chapter 6. Here: ideas 3 and 6 - { id: CCAO-F.D3.T2, label: supporting } # Tell the model families apart. Primary: Chapter 2. Here: 0.1.4 - { id: CCAO-F.D3.T4, label: supporting } # Manage context limits: restart, summarize or persist. Primary: Chapter 8. Here: idea 5 shows the limit, not the three moves - { id: OAI.1.2, label: supporting } # Choose a model and reasoning effort. Primary: Chapter 2. Here: idea 9 and 0.1.4 - { id: CCDV-F.D5.S1, label: supporting } # LLM fundamentals and model options. Introduced here, primary Chapter 28. Here: ideas 1, 2 and 4 word_budget: 4000 prerequisites: [ "F2" ] artifact: "AI field notes: a table of what each test showed, and where each answer came from" lab_data: "https://github.com/panaversity/agentfactory-v2-resources/releases/latest/download/brightline-lab-ch0-1.zip" delta_entries: [] # D-001 and D-004 are planned. Their notes are proposed in the README, not approved concepts: [ "0.1.1", "0.1.2", "0.1.3", "0.1.4" ] last_verified: 2026-10-16 generated: at: 2026-10-17T01:47:35Z by: process:panaversity trust_tier: unverified build_id: sha256:e1fbcb7d9a8f8b9b7cb96875022325c02c9ba4be94cef13b301cbd39a9edad85 dirty: true ksor_version: 0.0.60 --- ## The point When you ask an AI chat a question, where does its answer come from, and can you trust it? Ask it a question, and a tidy, sure answer comes back. Open yesterday's chat, and it carries on where you left off. Neither is quite what it seems. The app is what you see and type into. Inside it is a model, the trained engine that writes each reply. It was trained once, before you ever used it, and nothing you type changes it. Everything it says comes from two places. One is what it learned in that training. The other is the text the app puts in front of it for this one reply, called the context window. That is not a window on your screen. It is all the text the model can see for this reply. After this chapter you can look at any answer and say which of the two it came from. You can explain why a new chat forgets you, and what really remembers you when a chat seems to. You can say why a sure answer can still be a guess, and why the check is yours, not the AI's. And you can see how the same model, given tools, carries out work in steps. That is where Part I begins. ## Why it matters On Monday you ask an AI chat about Brightline Wholesale Supply, the book's example company. Does a $7,800 invoice from Midwest Packaging need the controller's approval? The answer comes back at once, calm and sure. Approval is needed only for invoices over $10,000, it says, so this one can be paid. It is wrong. Brightline's accounts payable policy, version 3, approved on September 1 by Dave, the controller, sets the limit at $5,000. If you had trusted the answer, the invoice would have been paid without Dave's approval. The AI had never seen that policy. It gave the limit that sounds right, and nothing inside it checked. So you attach the policy and ask again. This time the answer is right, and it quotes the policy's line. On Tuesday you open a new chat and ask once more. The answer is back to $10,000. The AI did not forget the policy overnight, because it never learned it. Monday's chat had the policy in front of it. Tuesday's new chat did not. The accounts payable manager in the Preface lost money in the same way. She pasted two batches of invoices into two new chats. The same $8,400 invoice was in both batches, and it was paid twice. Nothing was broken. Each chat saw only its own batch, so nothing ever compared the two. Neither mistake was about how clever the AI was. Both came from not knowing what it was working from. This chapter teaches you to ask that of every answer: did it come from training, or from the context window?