# Glossary: the words, in plain English

Skim the first section now. Leave the later section until a word comes up.

## Words you need now

**Agent**
An AI you chat with that can also do useful work when you give it access and clear instructions. For this guide, think of it as a careful assistant, not a magic employee.

**Brief**
The clear instructions you give before work starts: what you want, who it's for, what good looks like, and what must not happen.

**Connector**
A safe link between your AI tool and another account, such as email, calendar or files. Start read-only, check permissions, and remove anything you don't use.

**Context**
Everything the AI can see right now: your message, the chat so far, files, pasted notes and connected sources. Better context usually means better output.

**Draft, confirm, execute**
The core safety habit. The AI drafts, you check, then you choose whether anything is sent, saved, booked or changed.

**Guardrail**
A rule that keeps the AI inside safe lines, such as "never send without showing me first" or "do not invent prices".

**Hallucination**
The AI improvising a confident answer that is wrong. Check names, numbers, dates and facts before anything leaves your hands.

**Least access**
The smallest permission set that still gets the job done. If read-only is enough, don't grant write access.

**Memory**
Saved facts and preferences the AI can use in later chats, such as your tone, business name or preferred format.

**Prompt**
What you type to the AI. A clear prompt gets a clearer answer.

**Read-only vs read and write**
Read-only lets the AI look but not change. Read and write lets it act. Start read-only unless you have a strong reason not to.

**Session**
One continuous chat. If a session gets messy or long, ask for a handover note and start fresh.

**Skill**
A saved repeatable workflow. Instead of re-explaining a weekly report or inbox triage every time, you keep the steps and reuse them.

**Triage**
Sorting a pile into buckets so you know what needs action, what is information only and what can wait.

## Words you might hear later

**Agent harness or multi-agent system**
A setup where several agents work together, with one leading and others doing specific pieces. Useful for bigger builds, not needed for the everyday wins.

**Automation tool**
A service that connects several apps and runs a recipe. Useful later when work needs to hop across systems or run on a schedule.

**Coding agent**
A specialist AI tool that can build or edit software. Handy later for custom tools, not required for this guide.

**Connector standard**
A shared way for tools to expose safe actions to AI. You don't need to know the protocol to use the habit: trust the source, check permissions, start small.

**Context window**
How much the AI can hold in one chat before older material starts to fall away. If it forgets or drifts, start a fresh session with a handover note.

**Context drift**
When a long chat slowly gets worse because old instructions and side paths pile up. Starting clean is usually faster than arguing with it.

**Dashboard or cockpit**
One calm page that holds your priorities, live work, blockers and parked items. Build it manually first, then connect read-only, then schedule a brief if it earns trust.

**Handover note**
A short summary the AI writes so you can move a job into a fresh session without losing the thread.

**Large language model**
The kind of trained system behind most chat tools. You don't need the theory to use it well.

**Local model**
An AI that runs on your own machine instead of a hosted service. Useful for some private work, but often less convenient.

**Model**
The engine doing the thinking. Different models have different strengths, costs and speeds.

**Orchestrator**
A lead agent that breaks a bigger job into pieces and pulls results together.

**Permissions**
The exact abilities you grant when connecting a tool, such as read email or create calendar event. Read the list before approving.

**Prompt injection**
A malicious or accidental instruction inside content the AI is reading, such as an email that tries to make it leak data. This is why connected work stays draft-confirm-execute.

**Scheduled task or morning brief**
A recurring job that drafts an update at a set time. Use it only after the manual and read-only versions are useful.

**Workplace-controlled AI setup**
A company-managed setup where sensitive data stays inside approved systems. If you handle regulated or confidential work, ask for this path.

**Standing instructions**
Rules the AI reads before every chat, such as your tone, format and safety defaults.

**Sub-agent**
A helper agent given one part of a bigger job by a lead agent.