Agents in Medicine

End-of-lesson check

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

1. Which sentence best captures the main idea of 'Agents in Medicine'?

   1. Agents and chatbots are the same thing in every way
   2. Medical agents help with documentation (ambient scribes), imaging (X-ray review), and even clinical decision support..
   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 'Where medical agents are used'?

   1. Approve all actions automatically
   2. Run unbounded retries on any error
   3. Disable safety checks for speed
   4. Ambient scribing (Abridge, Nuance DAX). Imaging review (Aidoc for radiology). Decision support (UpToDate AI).

3. Which of the following is part of 'Three rules for medical agents'?

   1. Avoid taking any actions in the world
   2. Never log what the agent did
   3. Run unbounded retries on any error
   4. Doctor still makes the diagnosis

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

   1. Reviewed in 2026. Treat fast-changing product names, prices, availability, and policy details as examples to verify before use.
   2. Never log what the agent did
   3. Disable safety checks for speed
   4. Use the most expensive model regardless of fit

5. What is 'ambient scribe' in this context?

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

6. What is 'clinical decision support' in this context?

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

7. What is 'radiology AI' in this context?

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

8. Which agent role is most appropriate in a medical setting?

   1. Replacing the patient relationship
   2. Diagnosing patients without clinician review
   3. Auto-prescribing medications
   4. Drafting notes, summarizing records, and surfacing options for a clinician to evaluate

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

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

10. 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. The temperature setting
    4. How polite the model sounds

11. 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

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

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

13. 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

14. Why is keeping a human in the loop valuable for high-stakes agent actions?

    1. It replaces the model entirely
    2. It speeds the agent up
    3. It removes the need for any logging
    4. It catches mistakes before they cause real-world harm

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 $4,000
    3. About $400
    4. About $4