Skip to lesson
Lesson 19 / 2015 min readUp to date as of 19 October 2026

AI glossary and how a model works

Find a term and check an example

Look up an unfamiliar term and read its short definition. The model explanation helps distinguish context, memory and verified information.

Reading time is approximate. Allow extra time for the exercises; practice estimates are shown with the workshops.

After this lesson
  • Find the term you need in the glossary
  • Explain it to your team with a simple example
Section being translated

The chrome and course program are available in English. Deep training modules (prompt library, AI glossary, playbooks) are being translated - some content below is still in Polish.

Edition date and feature availability

Material revised: 19 October 2026; The interface and folder guide was revised on 19 October using supplied screenshots and OpenAI’s public plugin repositories; this does not reverify product access. The models in Chat, Work and Codex were checked on 16 October 2026, and the GPT-5.5 retirement date and Word access rules on 14 October 2026; other prices and availability were not fully reverified. Check the documentation and your account before using a feature: access depends on plan, region and administrator settings. Use the examples for practice and review the results yourself.

See how it works

What does the model do, and what does a tool do?

  1. Context

    Instructions and materials available for the task.

  2. Model

    Generates a proposal and may plan tool use.

  3. Tool

    Performs an action such as calculation or file reading.

  4. Review

    A person checks result, sources and action scope.

A concrete example

The model proposes a sum formula. A tool calculates it. A person checks that the correct rows and currency were used.

Does tool use remove all errors?

No. A tool may correctly execute an incorrect instruction or process wrong data.

Bonus - AI glossary

AI glossary in plain English

In shortThe 44 most-used AI terms - explained without assuming a technical background.

Filter by category or type a term. Every entry has a short (one-line) and long version.

Basics
Tool
An operation an agent can perform.
+

Examples include reading a file, calculating a total or preparing a draft. An available tool is not permission to do anything with it.

Business
App connection (connector)
Access to a service within granted permissions.
+

For example, a drive connection provides access to permitted documents. Check the account and permissions. A skill describes how to work; a connection determines which sources can be reached.

Basics
AI (Artificial Intelligence)
Systems performing tasks that require human intelligence.
+

A broad field including machine learning and content generation. In business today "AI" usually means generative AI, i.e. large language models (LLMs) like ChatGPT, Claude, Gemini.

Models
GPT-6 (Astra, Sol, Luna)
OpenAI's newest model family (September 2026).
+

Astra (3 Sep 2026) - the most capable, for hard tasks. Sol and Luna (22 Sep 2026) - cheaper models with near-Astra quality: Sol for everyday work and agents, Luna for fast tasks at scale. Choose a model by testing quality, time and usage on your own process. Check access and limits in your account; API billing and limits are separate. See lesson 13 for a worked cost example.

Basics
Usage cap
The usage available in a plan.
+

Check the limit and reset time in your account. Rules depend on the product, plan and model; do not assume team-wide pooling.

Dev
API billing
Separate billing for model and tool usage.
+

API has its own prices and limits. Measure tokens, tool calls and iterations. A prompt instruction does not replace application-level cost controls.

Models
LLM (Large Language Model)
The engine behind ChatGPT and similar tools.
+

A model trained on billions of texts to predict the next word. The GPT-6 (Astra, Sol, Luna) and GPT-5.6 (Sol, Terra, Luna) families, Claude, Gemini - all LLMs. "Large" = hundreds of billions of parameters.

Basics
Token
A unit of text processed by a model.
+

A token can be a word fragment, character or whole word. Counts depend on the language, text and tokenizer; a word-to-token ratio is only an estimate.

Basics
Prompt
The instruction you write for the AI.
+

Prompt engineering means giving the model: role, context, goal, format and constraints. A good prompt helps, but the result still needs review.

Models
Context / Context window
Context is information used to produce an answer; the window limits how much fits.
+

Think of a workbench holding instructions, conversation and sources. It is not an archive or a guarantee that every sentence was used. For a large file, identify the relevant section and check what made it into the answer.

Security
Hallucination
When the model confidently states something made up.
+

The model must always predict the next word - even without a real answer. Cure: turn on web search, ask for sources, verify facts.

Models
Temperature
A sampling parameter, where supported by the model.
+

Lower temperature does not guarantee truth. Availability and supported values depend on the model. Ask for sources and verify results regardless of this setting.

Dev
RAG (Retrieval Augmented Generation)
AI + your knowledge base.
+

Instead of retraining the model you plug it into your documents. It retrieves chunks and answers from them. That's how internal company chatbots work.

Dev
Fine-tuning
Additional model training on examples.
+

First compare prompting, retrieval and evaluation results. Fine-tuning can help with repeatable formats or behaviour, but needs suitable data and quality evaluation.

Dev
Embedding
Text turned into numbers (a vector).
+

Lets you measure similarity between texts. The basis of RAG and semantic search - you search by meaning, not keywords.

Models
Agent
An AI that runs multi-step tasks on its own.
+

Doesn't just answer - plans, uses tools (calendar, mail, browser), checks results, iterates. Work mode in ChatGPT is an example of an agent for working with company files and apps.

Dev
MCP (Model Context Protocol)
A standard for connecting AI to external tools.
+

An open protocol (from Anthropic) - lets you plug any tool into the agent: Slack, Notion, databases, your own APIs. ChatGPT Work and Claude already use it.

Dev
API
An interface through which programs exchange data and request actions.
+

For example, an app requests an order status and receives structured data. APIs are not exclusive to AI. Access may require authentication, and calls can have separate costs.

Models
GPT (Generative Pre-trained Transformer)
The architecture behind OpenAI models.
+

"Custom GPT" in ChatGPT is different - your own assistant with files and instructions. Note: OpenAI is retiring custom GPTs (creating new ones is planned to end on 26 Oct 2026, existing ones run until 11 Dec 2026). Their successor is the plugin - see lesson 09.

Models
Multimodality
AI understands text, image, voice, video.
+

Today's models see photos, hear voice and generate images. In practice: paste an error screenshot - it explains. Paste an invoice - it turns it into a table.

Business
Custom Instructions
Persistent instructions for ChatGPT (Settings → Personalization).
+

You write once: "I'm an accountant at a Polish manufacturing company, answer concisely, in English, with numbers." Applies to all conversations. Cheapest hack for better answers.

Business
Memory
ChatGPT remembers facts about you across chats.
+

You can say "remember that our product is called X." Turn it off in settings. WARNING: don't put sensitive data into memory.

Business
Projects
Folders with files + instructions for repeatable work.
+

You upload documents (offer, terms, customer base), set an answer style - ChatGPT remembers everything within that project. Great for teams.

Business
Workspace
An organisation’s working space with members and settings.
+

Workspace describes where and with whom you work. Business and Enterprise are plan names, not synonyms for the space. Check the account, membership and access before working. See lesson 03 for plans.

Security
DPA (Data Processing Agreement)
A GDPR data-processing agreement.
+

Required by GDPR with your AI vendor. OpenAI provides a DPA for Business / Enterprise / API. Without a DPA you can't process personal data.

Security
Hallucination vs. fact
A plausible sentence is not evidence.
+

Separate what the source supports from interpretation. A higher sales value does not prove a campaign worked. Request the source, open it and check the claim, date and units.

Dev
Inference
Each model call (each answer).
+

More inferences = more cost. In business we measure cost per process ("1 handled ticket = 0.05 EUR"), not per person.

Models
Open-source LLM
Publicly available models (Llama, Mistral, Qwen).
+

You can run them on your own server - data never leaves the company. Requires IT and GPUs. Good for sensitive industries (healthcare, legal, defense).

Business
Plugin (package)
A package of instructions and integrations for tasks.
+

A plugin may include skills, apps and reference material. Installing a package does not grant mailbox access. Check the connection and permissions separately. Example: a reporting package, spreadsheet connection and report-writing skill — lesson 09.

Business
Skill (ChatGPT Work)
Saved instructions for a repeatable task.
+

A skill describes inputs, rules, outputs and checks. It grants no permissions and does not guarantee identical responses. Test it on two known cases and on missing data.

Basics
Chat, Work and Codex
Three modes of the same app.
+

Chat is a conversation. Work carries out a whole task with your files and tools and hands back a finished file to review. Codex is the same kind of agent with a developer view: commands, code changes (a diff) and tests. Work and Codex share account limits. Lessons 02, 06, 07.

Models
Effort (reasoning level)
How long the model thinks before answering.
+

Low = fast and cheap. High/Max = more careful, slower, uses more limit. Lesson 13.

Business
Shared limit pool
One limit shared by Work, Codex and agents.
+

A long Work task reduces what is left for Codex. Check Settings › Usage. Lesson 03.

Basics
Plugin
A package that connects ChatGPT to an app and adds ready skills.
+

E.g. the Gmail plugin lets it read mail and write drafts. Connect once in Settings › Plugins. Lessons 01, 09.

Basics
Skill
A saved instruction you don't have to rewrite.
+

Like a recipe: describe once how to write an offer, then call it with /offer. Lessons 01, 12.

Basics
Computer use
AI clicks and types in programs on your computer.
+

Codex can open Chrome or Excel and do steps like a person. Start with tasks that send and pay nothing. Lesson 11.

Business
Scheduled task
A command AI runs on its own at a fixed time.
+

E.g. a daily 8:00 inbox summary. Lesson 12.

Dev
Repository
A project folder with its change history, usually on GitHub.
+

The analogy has a limit: an ordinary folder holds only the current files, while a repository remembers every saved version. Codex works inside a repository: reads, edits and shows what it changed. Lesson 07.

Dev
Diff
A view of differences: what was removed and what was added.
+

Like “track changes” in a word processor, but for project files. A line with a minus was removed, a line with a plus was added. It is not a quality score - only reading both lines shows whether the change is good. Lesson 07.

Dev
Pull request
A bundle of changes submitted for review.
+

It contains the changes, a description and test results. Merging approves it and adds it to the main version of the project; a person makes that decision. Lesson 07.

Security
Draft
A version to check before anything goes out.
+

AI prepares the draft, a human approves and sends. Lesson 18.

Basics
Sites
A small website built by ChatGPT.
+

E.g. an event page or an internal form. More › Sites. Lesson 10.

Models
Reasoning model
A model that plans before it answers.
+

Better at numbers, analysis and multi-step work. All GPT-6 models reason. Lesson 13.

Security
Approval
The moment AI asks for your permission.
+

Before an agent sends, deletes or buys, it shows the plan and waits for your yes. Lesson 18.

Missing a term? Reach out - we'll add it.

More detailHow a model produces an answerTokens, context and hallucinations explained. Text estimates are illustrative and should not be used for billing.

Bonus - How AI works

How AI actually works

In shortA model builds an answer from successive text units. It can make mistakes, so check important information against sources.

These six concepts explain conversation length, token usage and errors in answers.

The model generates next tokens

A model produces an answer by generating successive text units called tokens. It uses learned patterns and the available context. A coherent answer does not establish that its facts are true.

Tokens - the currency of AI

A token is a text unit, such as part of a word or a character. Estimates such as ~4 characters in Polish or ~0.75 words in English depend on the text and tokenizer. Use actual usage reports for API billing.

Context window

The context window limits the material available to the model while generating an answer. The example of 128k tokens (~250 A4 pages) is illustrative, not every model’s limit. For long material, check which parts were used; context is different from account memory.

Data cutoff

A knowledge cutoff describes the training knowledge range. Later information can come from supplied files or tools such as search. Check the source and date for current information.

Temperature and creativity

Temperature affects generation randomness if the model supports the parameter. Values of 0 and 1 may produce different variation, but they do not measure truth or act as a simple creativity switch. A style instruction does not change this parameter.

Hallucinations

A hallucination is an answer that presents invented or incorrect information as fact. It can sound convincing. Ask for a source, open it and check whether it supports the particular claim.

In practice

How much is a "token" in practice

In these examples, 1 token is roughly 4 characters in English. A word may take 1, 2–3 or more tokens, depending on the tokenizer. Usage includes the request, answer and file content used by the model.

← Swipe the table →

Illustrative examples, not tokenizer measurements. Do not use these numbers for billing or account limits.
TextTokensNote
Hello there3~4 chars = 1 token in English
Artificial intelligence is changing the company.8short office sentence
1 page of A4 text500≈ 500 tokens
Entire book (~300 pages)150,000illustrative example; check the particular model’s tokenizer and limit
Remembers
only text within the context window
You pay for
input + output (together)
Tip
shorter prompt = cheaper and faster

Check your understanding

What is a token?

This is a self-assessment. Mark the lesson complete after doing the exercise and reviewing the result.

Do this now

Pick 5 terms from the glossary and explain them in your own words to a colleague - the fastest way to make them stick.

How to know you can do it

Keep as evidence: Three terms explained with your own example.

  • You distinguish a model from an application.
  • A skill is not a permission.
  • Context does not guarantee perfect recall.

Mark the lesson complete after the exercise and review. Reading progress and quiz answers alone do not confirm practical skill.

Lesson status
In progress — 0% of the page scrolled
Next