Your answers save in this browser on this device. Clearing browser data can remove them. Copy your notes somewhere you keep your work, or print them as a PDF.
Copyable prompts and section summaries are in the resource library . For your first run, open The wording for your first comparison .
Copy all notes Print or save as PDF
1. Run Your First AI Agent Without Writing Code Your practice Lecture 1.2 Your first explanation Describe the agent run you watched in your own words. Keep this first version so you can compare it with your explanation at the end.
Lecture 1.2 Compare the explanations Record Arun’s explanation below your own. Which actions did you include, and which did you leave out?
Lecture 1.5 Your price check Keep the question, tool, source, and whether the answer matched the source. Record anything you could not establish from the activity shown.
Lecture 1.7 Your first comparison Keep your decision, prompt, saved result or link, displayed model, and any unfinished work or question the tool asked.
2. Understand How AI Agents Work (Models, Tools and Memory) Your practice Lecture 2.5 Look, Think, Do and Check Choose a regular job that includes a decision. Describe what you look at, decide, do and check.
3. Tell Agentic AI, Chatbots and Workflows Apart Your practice Lecture 3.4 Two jobs from your week Write one example with fixed steps and one where an agent would need to choose the next action.
4. Check How AI Uses Company Data (RAG, APIs and MCP) Your practice Lecture 4.1 Knowledge base and RAG Keep a plain-language explanation of knowledge base and RAG, and the company passage you would ask the seller to show.
Lecture 4.7 An action and a decision Read your agent explanation aloud. Add one tool action and one decision. Replace an unexplained word such as autonomous with what you mean.
5. Direct AI Agent Decisions (Goals, State and System Prompts) Your practice Lecture 5.5 The purpose of your request Write one sentence explaining what you will decide or produce with the answer.
6. Get Better Agent Results With Prompt Engineering Your practice Lecture 6.2 Choose your practice task Name the task, options, information needed, suitability requirements, and a result you can review in the time you have.
Lecture 6.11 Your request, result and review Keep the prompt and output together. Record deciding facts and sources checked, unresolved points, and the correction you would make.
7. Verify AI Results and Set Limits (Hallucinations and Guardrails) Your practice Lecture 7.5 Actions that need control List actions in your task that need review or a limit. State the condition for each approval or limit.
Lecture 7.9 Extend your explanation Add a short paragraph describing the checks you make when an agent is wrong and the actions that wait for your approval.
9. Measure AI Agent Costs and the Work You Still Do Your practice Lecture 9.1 The work that remains List preparation, checking and exceptions that people still handle around your chosen task.
Lecture 9.2 When the work reaches you Add when and how each remaining job reaches you, and who handles it.
Lecture 9.3 The cost of your run Keep the prompt, result and checking time. Record how often the job occurs, unsuccessful attempts, and the usage or plan cost you can establish.
Lecture 9.4 Your reusable request Save your prompt with a name that describes its job. Keep changing details visible and record your checking questions beside it.
10. Prepare for AI at Work (Jobs, Skills and Employment Evidence) Your practice Lecture 10.5 Make the explanation concrete Read your opening explanation. If it remains abstract, add an example from your own work.
11. Grow Your AI Workflows (Client Work and Local Files) Your practice Lecture 11.1 Your next improvement Choose one improvement or repeatable handoff. Keep the original requirement and state the result you will check.
Lecture 11.4 Your new explanation Write a new explanation beside your first. Use your task to name a goal, a decision the agent chose and an action it performed.
Notes from the earlier worksheet Your previous answers stay available here. They have not been assigned a new meaning or deleted.
The sixty-second test Which did yours do, recite or go and look? And on which question?
Knowing without hands What do you know well enough to explain in five minutes, and still have to sit down and do by hand every single time?
The words, and what you would say Each word people use around you, what it means in ordinary language, and one sentence you could genuinely say out loud. This is the part you open on your phone before a meeting.
The word you have been nodding at Which word have you been nodding at for months without knowing what it meant? Write it down, and write what you would say about it now.
Your crooked shirt What is the thing that arrives slightly wrong, often enough that you have stopped noticing you are the one fixing it every time?
What you batch up What do you deliberately batch up rather than doing one at a time, and what does it cost you when somebody makes you do it one at a time?
Your ask The purpose. The boundary around the options. What you care about, in order. And the shape you want back. Keep this one. It is the most reusable thing you will make here.
The job that was the right shape Which job of yours turned out to be the right shape, and what made it the right shape rather than another one?
Your checking routine The routine, in your own words. This is what decides whether you are still using any of this in six months.
The question worth asking anybody selling to you Keep the question itself here, so you have it in the room. Add what a good answer sounded like, once you have heard one.
Shown rather than told What in your own work did you learn by being shown rather than by being told?
The last annoying ten percent What is the last annoying ten percent in your work that nobody has ever taken off you?
Worth writing the ask down for Which job of yours is worth writing the ask down for, because you know you will be doing it again next month?
Copy all notes Print or save as PDF