Course · v1.0.0

Using Claude at Work

Get useful, checkable work out of Claude on your phone or desktop. Pick the right plan and privacy settings, write prompts that land first time, use Projects, memory, search and artifacts, decide when an agent needs a human watching, and catch the mistakes before anyone else does.

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

What you will be able to do

  • Choose the right Claude plan for work and set the data-privacy controls before pasting any company content.
  • Write prompts that give context, a role, a format and an example so the first answer is usable.
  • Use Projects, uploaded files and memory to keep recurring work consistent without repeating yourself.
  • Use web search with citations and artifacts to produce documents that someone else can check.
  • Decide when an agent such as Claude in Chrome or Cowork may run on its own and when a person must watch and approve each step.
  • Check Claude's output for planted errors, unsupported claims and missing items before it leaves your hands.
  • 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. Plans and data-privacy settings

    Which account you are signed in to decides who can see your chats. Check it before you paste anything from work. · 8 min

  2. Prompting with context and examples

    Claude cannot read your mind. Give it the situation, the audience, the format and one example, and the first answer will usually be usable. · 9 min

  3. Projects, files and memory

    Stop re-explaining your business every morning. Put standing instructions and reference files in a Project and let memory carry the rest. · 9 min

  4. Web search, citations and artifacts

    Search gives Claude fresh facts and a source to point at. Artifacts turn a chat into a document you can hand to someone else. · 8 min

  5. Agents, and when to supervise them

    An agent does not just answer, it acts. The more it can change, the closer you watch. · 8 min

  6. Checking output before it leaves your hands

    Claude's draft is a first draft. A two-minute check catches the one wrong number, date or name that would have cost you an afternoon. · 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

    Claude 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: from messy thread to reply and task list

    Put the whole course to work. Turn a tangled customer thread into a reply and a task list, then find the one error Claude planted. · 6 min

  10. Assessment: From messy thread to clean reply

    Turn a tangled customer email thread into a reply and a task list, then find the one planted error in Claude's draft before it goes out.

Start lesson 1