Build Your Personal Website With an AI Coding Agent

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-agentic-AI-and-personal-website-teen

1. Which sentence best captures the main idea of 'Build Your Personal Website With an AI Coding Agent'?

   1. Agents and chatbots are the same thing in every way
   2. Agents should always run without limits or oversight
   3. AI coding agents (Claude Code, Cursor) can build a personal website for you with little coding from you. Real teen tool.
   4. Tools and goals are unnecessary for agent design

2. Which of the following is part of 'Some examples'?

   1. Avoid taking any actions in the world
   2. Describe your vision: 'A clean personal website showing my art portfolio with about page and contact form.'
   3. Approve all actions automatically
   4. Disable safety checks for speed

3. Which of the following is part of 'The rule'?

   1. Skip every form of evaluation
   2. Hide tool calls from the operator
   3. Personal websites are real-world experience. AI agents make them accessible. Have one by 16.
   4. Always run with no oversight

4. Which of the following is part of 'You did it!'?

   1. Use the most expensive model regardless of fit
   2. Ignore cost when scaling
   3. Great work — you just leveled up.
   4. Never log what the agent did

5. What is 'personal website' in this context?

   1. A core concept covered in Build Your Personal Website With an AI Coding Agent
   2. A trick to bypass approvals
   3. A reason to skip all logging
   4. A way to disable the agent's tools

6. What is 'AI agents' in this context?

   1. A core concept covered in Build Your Personal Website With an AI Coding Agent
   2. A trick to bypass approvals
   3. A reason to skip all logging
   4. A way to disable the agent's tools

7. What is 'no-code potential' in this context?

   1. A trick to bypass approvals
   2. A reason to skip all logging
   3. A core concept covered in Build Your Personal Website With an AI Coding Agent
   4. A way to disable the agent's tools

8. What is the most useful first goal when AI helps you build a personal website?

   1. Maximize file size
   2. Add as many animations as possible
   3. Ship a simple page that says who you are and what you do
   4. Avoid using any tools

9. What does an 'eval' for an agent measure?

   1. How polite the model sounds
   2. Whether the agent reliably completes a defined task end to end
   3. The temperature setting
   4. The exact wording of every prompt

10. Which is the clearest sign an 'agent' is really just a chatbot in disguise?

    1. It uses a system prompt
    2. It can remember last week's conversation
    3. It can call a search tool
    4. It only produces text and never takes actions

11. Why is logging every tool call an agent makes a baseline requirement?

    1. Logs are needed to debug, audit, and explain agent behavior to users
    2. Logs make the model run faster
    3. Logs replace the need for testing
    4. Logs are only for legal teams

12. Why does an AI agent need 'tools' such as a browser, calendar, or code runner?

    1. Tools shrink the context window
    2. Tools make the model speak more naturally
    3. Tools let the agent take actions in the world instead of only producing text
    4. Tools replace the need for any prompts

13. What is the difference between an agent's memory and its context window?

    1. Memory is faster but less accurate than context
    2. Context lasts forever; memory is cleared every minute
    3. Nothing — they are the same thing
    4. Context is what the model sees right now; memory persists across runs

14. An agent that costs $0.04 per task on average will run 10,000 times this month. Roughly what should you budget?

    1. About $4,000
    2. About $40
    3. About $400
    4. About $4

15. What should an agent's trace let you do after a run?

    1. Hide what the agent did from the user
    2. Make the agent run faster next time automatically
    3. Replace the need for any tests
    4. Reconstruct each step, decision, and tool call so you can debug or audit