Agents Doing Your Personal Tasks

End-of-lesson check

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

1. Which sentence best captures the main idea of 'Agents Doing Your Personal Tasks'?

   1. Agents are increasingly doing personal tasks — booking flights, ordering groceries, comparing insurance..
   2. Tools and goals are unnecessary for agent design
   3. Agents should always run without limits or oversight
   4. Agents and chatbots are the same thing in every way

2. Which of the following is part of 'A typical personal-task agent'?

   1. Ignore cost when scaling
   2. 'Find me 3 birthday gift ideas for my dad under 50 dollars, order the best one to arrive by Friday, and add it to my calendar.'
   3. Use the most expensive model regardless of fit
   4. Always run with no oversight

3. Which of the following is part of 'Three good personal-task agents'?

   1. Hide tool calls from the operator
   2. Comparison shopping (best price across stores)
   3. Run unbounded retries on any error
   4. Use the most expensive model regardless of fit

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

   1. Use the most expensive model regardless of fit
   2. Hide tool calls from the operator
   3. Never log what the agent did
   4. Reviewed in 2026. Treat fast-changing product names, prices, availability, and policy details as examples to verify before use.

5. What is 'errand agent' in this context?

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

6. What is 'automation' 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 Doing Your Personal Tasks

7. What is 'time savings' in this context?

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

8. Which is a sensible first task for a personal AI agent?

   1. Filing your taxes without review
   2. Sending money to strangers
   3. Drafting routine messages and organizing files for you to approve
   4. Posting on your social accounts unattended

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

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

10. Which is the best way to think about an agent's 'autonomy level'?

    1. It is a slider from suggestion only, to ask-then-act, to act-then-report, to fully autonomous
    2. Autonomy does not affect risk
    3. It depends only on the model size
    4. It is binary — fully autonomous or not

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

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

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

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

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

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

14. What is the safest first place to deploy a brand new agent?

    1. A sandbox or low-stakes task with reversible actions
    2. On a public server with no auth
    3. Inside a critical billing system
    4. Production, against real customers

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

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