Skip to main content
Learning Center

Practical AI

Find your starting point

Try three short checks using only these fictional packets. Your writing stays on this page until you leave or reload; it is not sent for grading or saved to your account. This is a self-check, not a proficiency credential. You may start any course.

A claim and its source

Notice: The workshop includes a workbook. It says nothing about refreshments. Draft: “Refreshments are included.”

An ambiguous request

Message: “Tell Robin that Casey can review their outline.” Robin and Casey both have outlines.

A numeric result

Register: 15 people enrolled and 12 attended. Room capacity: 20. Draft: “80% of enrollees attended.”

For a complete introduction, begin with AI Foundations and Language. All six courses are available from the catalog.

Practical AI glossary — terms and common confusions
Model
A learned component used to produce a result.

A drafting model is one part of a letter app; it is not the whole app.

Application
The software experience around components and services.

A letter app adds accounts, storage, and a Send button.

Prompt
Instructions and input supplied for a task.

“Summarize this notice in two bullets” specifies a task and shape, not a truth guarantee.

Token
A unit a model processes; it need not be a whole word.

A tokenizer can split a name into pieces; count using the actual system.

Context
Information available for the current request.

An earlier attachment may be absent even when its filename is visible.

Training
Adjusting a model using examples.

A training log differs from a conversation correction.

Inference
Using a trained model to produce a result.

Drafting another sentence does not by itself prove retraining.

Retrieval
Selecting material to supply to a task.

A retrieved notice still needs a relevance and date check.

Embedding
A numerical representation used to compare or organize items.

A similar search match is a candidate, not proof of the same meaning.

Tool
A function an application can call.

A calendar lookup can be read-only; finding an event is different from creating one.

Agent
Software that can choose and carry out steps toward a goal.

An agent still needs bounded permissions and checked action receipts.

Hallucination
Plausible generated content that is unsupported or false.

An invented opening time needs evidence or removal, even when phrased confidently.

Evaluation
Checking results against stated criteria.

Twenty checked examples establish a bounded result, not universal reliability.

Multimodal
Working with more than one kind of input or output.

A photo plus text does not prove every small label in the photo was read correctly.

learning.goultergroup.com

The interactive parts of this page have not loaded. Reading and links still work; reload the page to try again.