Use AI Agents to Plan a Trip: Real-World Practice

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-agentic-AI-trip-planning

1. Which sentence best captures the main idea of 'Use AI Agents to Plan a Trip: Real-World Practice'?

   1. Planning a vacation, family trip, or weekend with friends? AI agents are great at this. Here is how to use them safely.
   2. Agents and chatbots are the same thing in every way
   3. Tools and goals are unnecessary for agent design
   4. Agents should always run without limits or oversight

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

   1. Never log what the agent did
   2. 'Plan a 3-day weekend in [city] for a family with a 5-year-old. Budget $500. Show me 3 options for each day.'
   3. Disable safety checks for speed
   4. Use the most expensive model regardless of fit

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

   1. Ignore cost when scaling
   2. AI plans, but always verify — call the actual hotel, check the actual hours, look at real reviews. AI sometimes gets old info or invents things.
   3. Hide tool calls from the operator
   4. Disable safety checks for speed

4. Which of the following is part of 'Nice work'?

   1. Use the most expensive model regardless of fit
   2. Solid practice. You added a real-world AI skill.
   3. Avoid taking any actions in the world
   4. Run unbounded retries on any error

5. What is 'trip planning' in this context?

   1. A reason to skip all logging
   2. A way to disable the agent's tools
   3. A core concept covered in Use AI Agents to Plan a Trip: Real-World Practice
   4. A trick to bypass approvals

6. What is 'research' in this context?

   1. A trick to bypass approvals
   2. A core concept covered in Use AI Agents to Plan a Trip: Real-World Practice
   3. A way to disable the agent's tools
   4. A reason to skip all logging

7. What is 'comparison' in this context?

   1. A trick to bypass approvals
   2. A reason to skip all logging
   3. A way to disable the agent's tools
   4. A core concept covered in Use AI Agents to Plan a Trip: Real-World Practice

8. When using an agent to plan a trip, what should you double-check before booking?

   1. Dates, prices, cancellation policies, and that the destinations are real
   2. The agent's tone of voice
   3. How many tokens were used
   4. Whether the agent likes the destination

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

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

10. An agent quietly retries a failed payment 50 times overnight. What design principle was missing?

    1. A larger model
    2. A bigger context window
    3. More creative prompting
    4. Bounded retries with human notification on repeated failure

11. Why does a multi-agent system sometimes outperform a single agent on complex jobs?

    1. Specialized roles can divide work and check each other
    2. Single agents cannot use tools
    3. More agents always means more accuracy
    4. Multiple agents always cost less

12. Why is it dangerous to give an agent access to your email and calendar without scoped permissions?

    1. It will refuse to work
    2. Scoped permissions slow the model down
    3. Scopes only matter for paid accounts
    4. Broad access means a single misstep can send the wrong message or wipe events

13. Before letting an agent take a destructive action, what is the safest default?

    1. Skip approvals if the user trusts the agent
    2. Approve once and let the agent repeat forever
    3. Require explicit human approval for the specific action
    4. Hide the action from any log

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

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

15. Why are clear success criteria critical when building an agent?

    1. They make the agent sound smarter
    2. They are required by law
    3. Without them you cannot tell whether the agent worked or guess
    4. They reduce the number of tokens used