Course · v1.0.0

Using ChatGPT at Work

Make ChatGPT a reliable coworker instead of a confident guesser. Understand free, paid and workspace plans and the data controls behind them, prompt with context and examples, use files, projects, memory, voice and agent features sensibly, make images and slides you can actually use, and verify every answer against its source.

9 lessons · about 72 minutes · pass at 80% · certificate does not expire

What you will be able to do

  • Tell free, paid and workspace plans apart and set the data controls before using work content.
  • Write prompts with context, a role, a format and an example so the first answer is usable.
  • Use uploaded files, projects and memory to keep recurring work consistent and current.
  • Use voice, browsing and agent features appropriately and decide when a person must watch and approve.
  • Create images and slides for internal use and know their limits on brand, text accuracy and rights.
  • Verify answers against the source document and catch unsupported claims, invented details and wrong numbers.
  • Apply the company AI policy, including what never to paste, how to handle hallucinations and bias, copyright, and when to disclose AI use.

Lessons

  1. Free, paid and workspace plans, and the data controls behind them

    The plan you are on decides who can see your chats and whether they train the model. Know which one you are in before you paste anything from work. · 9 min

  2. Prompting that works

    The answer is only as good as the brief. Four parts to every prompt, and one follow-up at a time. · 9 min

  3. Files, projects and memory

    Upload the real document instead of describing it, keep repeat work in a project, and manage what ChatGPT remembers about you. · 9 min

  4. Voice, browsing and agent features

    Voice is for thinking out loud, browsing is for fresh facts with links, and agents act for you. The more a feature can change, the closer you watch it. · 8 min

  5. Images and slides

    ChatGPT can make pictures and slide decks fast. Know what they are good for, where the text goes wrong, and whose rights you might be stepping on. · 7 min

  6. Verifying answers

    A confident answer and a correct answer look identical. A two-minute check against the source finds the difference. · 8 min

  7. AI safety and judgment, part 1: what never to paste

    Some information must never go into an AI chat, some needs the names removed first, and most is fine. Learn the three buckets. · 8 min

  8. AI safety and judgment, part 2: hallucinations, bias, copyright and policy

    ChatGPT can be confidently wrong, quietly unfair, or borrow someone else's work. Know the four risks and the one-line disclosure habit. · 8 min

  9. Lab: a meeting brief from a PDF

    Put the course to work. Build a one-page meeting brief from a PDF, then find the claim in ChatGPT's brief that the document does not support. · 6 min

  10. Assessment: Meeting brief from a PDF

    Build a one-page meeting brief from a provided PDF, then spot the claim in ChatGPT's brief that the PDF does not support.

Start lesson 1