School Policies on Agents

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-agentic-agent-school-policy

1. Which sentence best captures the main idea of 'School Policies on Agents'?

   1. Tools and goals are unnecessary for agent design
   2. Agents and chatbots are the same thing in every way
   3. Most schools haven't figured out agent policies yet.
   4. Agents should always run without limits or oversight

2. Which of the following is part of 'Questions to ask'?

   1. Disable safety checks for speed
   2. Run unbounded retries on any error
   3. Are agents allowed for research? Do I have to disclose when I used an agent? Can I use agents for note-taking? What is the consequence if I use an unallowed agent?
   4. Use the most expensive model regardless of fit

3. Which of the following is part of 'Three ways to use agents safely at school'?

   1. Run unbounded retries on any error
   2. Always disclose your use
   3. Skip every form of evaluation
   4. Approve all actions automatically

4. Which of the following is part of 'Review date'?

   1. Never log what the agent did
   2. Reviewed in 2026. Treat fast-changing product names, prices, availability, and policy details as examples to verify before use.
   3. Use the most expensive model regardless of fit
   4. Always run with no oversight

5. What is 'AI policy' in this context?

   1. A reason to skip all logging
   2. A core concept covered in School Policies on Agents
   3. A trick to bypass approvals
   4. A way to disable the agent's tools

6. What is 'disclosure' in this context?

   1. A core concept covered in School Policies on Agents
   2. A reason to skip all logging
   3. A trick to bypass approvals
   4. A way to disable the agent's tools

7. What is 'process artifact' in this context?

   1. A reason to skip all logging
   2. A trick to bypass approvals
   3. A core concept covered in School Policies on Agents
   4. A way to disable the agent's tools

8. What is a reasonable school policy stance on student AI agent use?

   1. Set clear rules for which tasks allow AI, require disclosure, and teach safe use
   2. Allow anything with no rules
   3. Punish students who admit to using AI
   4. Ban all use of any AI tool

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

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

10. Which of these is the strongest indicator that an agent workflow is ready to scale?

    1. It used the latest model
    2. It runs without any logging
    3. It passes a repeatable eval, has cost in budget, and a rollback plan
    4. It worked once for one user

11. What is the most reliable way to keep an autonomous agent from going off the rails on a long task?

    1. Trust the model to know when to stop
    2. Run it for as many steps as possible without checking in
    3. Disable its tools so it can only think
    4. Set a clear goal, a step budget, and review checkpoints

12. Which signal best tells you an agent is stuck in a runaway loop?

    1. It keeps repeating the same tool call with no new progress
    2. It asks one clarifying question
    3. It returns a short summary and stops
    4. It finishes the task in one step

13. What is the best response when an agent suggests an action you do not understand?

    1. Ask the agent to explain the action and its expected effect before approving
    2. Run it twice to be sure
    3. Reject everything and stop using the agent
    4. Approve it to keep things moving

14. Which budget control most directly prevents runaway costs from an agent loop?

    1. A hard cap on steps, tokens, or dollars per task
    2. A bigger model
    3. A friendly system prompt
    4. A longer context window

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

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