Agents and the Future of Work

End-of-lesson check

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

1. Which sentence best captures the main idea of 'Agents and the Future of Work'?

   1. Agents and chatbots are the same thing in every way
   2. Agents should always run without limits or oversight
   3. Tools and goals are unnecessary for agent design
   4. By 2030, agents will probably handle most routine knowledge work.

2. Which of the following is part of 'A 2030 prediction'?

   1. Never log what the agent did
   2. Always run with no oversight
   3. Hide tool calls from the operator
   4. Knowledge workers spend more time on judgment, relationships, and creative direction. Agents handle the execution.

3. Which of the following is part of 'Three skills that will matter most'?

   1. Disable safety checks for speed
   2. Knowing what to ask agents to do
   3. Ignore cost when scaling
   4. Never log what the agent did

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

   1. Use the most expensive model regardless of fit
   2. Reviewed in 2026. Treat fast-changing product names, prices, availability, and policy details as examples to verify before use.
   3. Always run with no oversight
   4. Avoid taking any actions in the world

5. What is 'knowledge work' in this context?

   1. A core concept covered in Agents and the Future of Work
   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 'execution' in this context?

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

7. What is 'judgment' in this context?

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

8. What is the most useful framing for jobs in an agent-rich future?

   1. Nothing will change at work
   2. All jobs will vanish
   3. Tasks within jobs change first; new roles appear around designing, supervising, and auditing agents
   4. Only managers will have jobs

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. Replace the need for any tests
   4. Make the agent run faster next time automatically

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

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

11. 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. Broad access means a single misstep can send the wrong message or wipe events
    4. Scopes only matter for paid accounts

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

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

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

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

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

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

15. 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 are only for legal teams
    3. Logs make the model run faster
    4. Logs replace the need for testing