Choosing and using AI tools at work
Understand what AI assistants do and their risks, write a clear request, then pick the right tool and mode with a reusable grid.
Course designed by Alex Dionisio, Senior Product Manager. Updated September 28, 2026.
- 29 steps
- ~1 hr 40 min
Level: All levels · No prerequisites: accessible to everyone.
Know what a generative AI assistant does well, what it does badly and what happens to your data, get a usable first result with a clear request, then pick the right tool and the right way of working for each task. You leave with a toolkit tested on your own tasks and a grid to reassess your choices when offerings change.
What you will be able to do
- Explain how a generative AI assistant works and what it does well or badly, so you know what to ask of it.
- Identify a tool's limits (fabrications, sources, freshness, data privacy) and the precautions to take before using it.
- Write a clear request (task, context, data, format, criteria) that produces a usable first result.
- Diagnose why a response falls short and fix it with a targeted clarification.
- Select the right tool for a deliverable using a grid of criteria (deliverable, data, sources, cost, language, integration) and justify the choice.
- Choose the right way of working for a task (conversation, project, deep research, agent) and the level of control that goes with it.
- Build your toolkit by comparing at least two tools on a real task with criteria written in advance.
Prerequisites
- A free account on at least one generative AI assistant (Claude, ChatGPT, Gemini, Mistral or similar).
- No technical skills.
- To go further on writing prompts: "Prompting for Product Managers: delegate, describe, verify".
Syllabus
What will I be able to do by the end of this course?
- Course overview3 steps
Objective · By the end of this overview, you will know who the course is for, what you will produce (a tested toolkit and a selection grid) and how the four modules fit together.
What happens when I ask an AI assistant a question, and what becomes of what I paste into it?
Objective · By the end of this lesson, you will be able to explain in a few sentences how a generative AI assistant produces an answer, and deduce which tasks it handles reliably and which ones require you to provide information or check.
Objective · By the end of this lesson, you will be able to spot the three main risks of an AI assistant (fabrications, misread sources, exposed data) and choose the right precaution before using it for a given task.
How do you phrase a request that gives a usable result, and what do you do when the answer disappoints?
Objective · By the end of this lesson, you will be able to write a request that specifies the task, the context, the data, the format and the success criteria, then diagnose a disappointing answer and fix it with a targeted clarification.
Which tool, and which way of using it, for which need?
- General-purpose assistants3 steps
Objective · By the end of this lesson, you will be able to choose a general-purpose assistant based on your needs (writing, sourced research, ecosystem, privacy) and spot the terms that rule it out for certain data.
Objective · By the end of this lesson, you will be able to choose, for a given task, the right way of working (conversation, project, deep research, agent) and the level of control it requires.
- Specialized tools4 steps
Objective · By the end of this lesson, you will be able to identify the specialized tool suited to a deliverable (application, presentation, voice, image, code) and check its terms of use before adopting it (quotas, watermark, commercial use).
- The tool selection grid3 steps
Objective · By the end of this lesson, you will be able to choose a tool for a given deliverable by applying a grid of six criteria, at least one of them a deal-breaker, and justify your choice rather than follow a ranking.
How do you go from a catalog of tools to a few tested tools that really help?
Objective · By the end of this lesson, you will be able to compare two tools on a real task with criteria written in advance, keep one of them and put together a short toolkit that you will reassess regularly.
Glossary terms
Public definitions of the key concepts in this course:
Guide on this topic
- Claude Skills: build and test a skill
SKILL.md anatomy, install, triggering, testing and security, with a template.
Verified sources
The fast-moving facts of this course (tools, models, regulation) are checked against these sources, then reviewed according to how quickly they go stale.
- Anthropic Privacy Center, How long do you store my data? · verified September 28, 2026
- Anthropic, Reduce hallucinations · verified September 28, 2026
- Claude Academy, Claude 101 · verified September 28, 2026
- Claude Help Center, Get started with Claude Cowork · verified September 28, 2026
- Claude, Plans and pricing · verified September 28, 2026
- CNIL, Q&A on using a generative AI system (in French) · verified September 28, 2026
- Cursor (official site) · verified September 28, 2026
- DeepSeek, Privacy Policy · verified September 28, 2026
- ElevenLabs, Text to Speech · verified September 28, 2026
- Gamma Help Center, What's the easiest way to export my Gamma? · verified September 28, 2026
- Google, Get started with Gems in Gemini Apps · verified September 28, 2026
- Lovable Documentation, Quick start · verified September 28, 2026