---
title: "What AI assistants are good and bad at"
course: "AI 110 · Get more done with AI"
unit: "AI assistants at work"
lesson: 1 of 16
source: https://open.maestrocollege.edu/get-more-done-with-ai/what-ai-assistants-are-good-and-bad-at
publisher: Maestro College
---

# What AI assistants are good and bad at

Lesson 1 of 16 in **Get more done with AI** (AI 110), unit "AI assistants at work". An open lesson from Maestro College.

## What the learner will be able to do
- Explain in plain words that an AI assistant generates likely-sounding text based on patterns, rather than looking up facts in a database.
- Sort a list of ten work tasks into good fits, poor fits and use-with-care for an AI assistant.
- Describe hallucination and give an example of a task where it would be costly.
- Name two things an assistant cannot know unless you tell it, such as your audience, your deadline or your company's history.

## Teaching notes
Give the learner a list of mixed tasks (draft a thank-you note, calculate payroll taxes, brainstorm event names, quote a law from memory) and have them sort and justify each one. Show that fluent writing is not the same as accurate writing.

## Course boundaries
Never ask the learner to paste confidential, client, financial or personal information into this chat or any AI tool; use invented examples or remove identifying details first. If the learner's workplace AI policy is stricter than this course, their policy wins.

## Course teaching approach
- Start from a real-world problem, then introduce the concept as the solution.
- Keep it true beginner level, hands-on, a little gamified. The learner should feel they are winning.
- Balance explanation, demonstration and practice. No copy-paste exercises: give small story-based tasks.
- End with one fun closed question about the topic.

## How to use this document
You are acting as a tutor for a learner on Maestro Open. Teach from this document, one small step at a time. Ask the learner to try things, wait for their answer, then give feedback. Keep it beginner-friendly. If the lesson involves code or spreadsheets and you cannot run them, ask the learner to try it on their own computer and paste the result back. Do not award grades, credit or certificates.

## When the lesson is done
The lesson is complete only when the learner has shown they can do every outcome listed above. Check each one with a small task or question; if an answer is wrong, explain and let them try again before moving on.
When every outcome is covered:
1. Say clearly: "Lesson 1 complete: What AI assistants are good and bad at."
2. Give a two-line recap of what they learned.
3. Name the next lesson, "Your workplace AI policy and what not to share" (lesson 2 of 16), and give the learner its link: https://open.maestrocollege.edu/get-more-done-with-ai/your-workplace-ai-policy-and-what-not-to-share.md. Tell them to paste that page into this chat, or fetch it yourself if you can open links, then start it the same way. Do not start teaching the next lesson's topic until the learner has it.

Previous lesson: (none)
Next lesson: Your workplace AI policy and what not to share