AI Bootcamp - Tool
DOPE CEOs · AI Bootcamp
Back to Resources
Resource 01 · The Glossary · Reference anytime

The AI words that make you fluent.

Half the reason AI feels over your head is nobody defined the words in plain English. Here they are. Don't memorize this — recognize it. Keep it open while you work, and the illusion of complexity collapses.

The core mechanics
WordWhat it actually meansWhy you care
ModelThe "brain" — Opus, Sonnet, or Haiku. Each is a different version of Claude.Picking the right one saves money and time.
TokenThe chunks of words AI reads and writes. Roughly 1 word ≈ 1.3 tokens.Tokens = your usage. Long prompts burn credits faster.
Context WindowHow much Claude can "see" at once — its short-term memory in one chat.Hit the limit and it forgets the beginning. Start a fresh chat.
Knowledge CutoffThe date the AI stopped learning. It doesn't know what happened after.For "today's" info, use search or Perplexity.
System PromptThe hidden instructions that shape how Claude behaves before you say a word.This is what skills and projects edit — the "personality layer."
Multi-ModalThe AI can handle text, images, voice, and PDFs — not just text.Drop in a screenshot, a PDF, a voice note. Use it.
The 3 ways AI gets it wrong
WordWhat it meansThe fix
HallucinationWhen AI confidently makes something up that isn't true — fake stats, fake citations.Tell it: "Don't guess. Say 'I don't know' and flag with [VERIFY]."
SycophancyWhen AI agrees with you when it shouldn't. The yes-man trap.Tell it: "Don't tell me what I want to hear — tell me what a smart skeptic would say."
BiasWhen AI gives a skewed answer based on its training data.Tell it: "Argue against yourself. Make the strongest case for the opposite."
The features & the ladder
WordWhat it meansWhy you care
MemoryWhat Claude remembers about YOU across chats. (Different from context window.)Curate it. Bad memories = bad outputs.
ArtifactA clean output Claude builds in a side panel — doc, code, dashboard, design.Can be shared, edited, re-used.
ProjectA workspace with its own files, instructions, and chat history.Rung 2 of the ladder. Standing context.
ConnectorA bridge between Claude and another app — Gmail, Drive, Notion, QuickBooks.Rung 3. Claude gets hands.
SkillA custom reusable behavior you trigger by name.Rung 4. Reusable procedures.
CoworkClaude with agentic capability — multi-step work autonomously.Rung 5. The top of the ladder.
ThinkingWhen Claude shows its reasoning before answering. Slower but smarter.Toggle on for hard questions.
Deep ResearchClaude searches the web for 10–30 min and returns a report.When you'd otherwise pay a research analyst.
The big concepts
WordWhat it means
Agent vs ChatbotA chatbot drafts the email. An agent drafts it, sends it, and follows up in 3 days. The difference is whether AI can take action.
Vibe CodingBuilding software by describing what you want in plain English. (Lovable, Replit, Bolt.)
The 4 DsAnthropic's AI-fluency framework: Delegation, Description, Discernment, Diligence.
The 3 ModesAutomation (AI does it), Augmentation (AI thinks with you), Agency (AI runs on its own). Live in Augmentation.
You don't need to memorize these. You need to recognize them when someone says them.