Presidents Day Debate: Which President Had the Hardest Job? A Post-Holiday AI Literacy Activity for Ages 8 to 16

What You'll Learn

• Why Presidents Day creates an unusually effective window for teaching children to evaluate AI arguments
• The age-appropriate activity path for children ages 8 - 10, 11 - 13, and 14 - 16
• Verbatim prompts for each age group that the child runs directly
• The core AI literacy skill this activity teaches - evaluating which argument is better supported by evidence
• A parent and educator sidebar with debrief questions and a framework for discussing AI persuasion

Presidents Day was Monday. Children who spent any part of the day learning about American presidents have something that makes AI literacy instruction unusually effective right now: prior knowledge they can use to evaluate AI's claims. The debate is still live. The activity works this week.

The skill this activity teaches is not "find information about presidents using AI." It is "evaluate whether AI's argument about presidents is well-supported." AI generates persuasive arguments for any position. Learning to distinguish a persuasive argument from a well-supported one is the competency that makes every other AI skill more valuable - and it is significantly easier to teach when the child already has independent knowledge to check against.

This is a PromptHacker Premium article.

The full age-by-age activity guide, verbatim prompts, and parent/educator debrief framework are available to Premium subscribers.

Ages 8 - 10: Learn About Two Presidents' Hardest Challenges

Have the child open ChatGPT or Claude and run:

Tell me about two presidents who had really hard jobs. What was the hardest thing each president had to do? Make it easy enough for a 9-year-old to understand.

After reading the output, ask: "Which president do you think had the harder job - and why?" The child's reasoning is the activity. If the child simply repeats what the AI said, push back: "But what do YOU think? Is 'harder' about the situation, or about what the president did about it?" Getting the child to distinguish between historical difficulty and personal judgment is the learning artifact.

Ages 11 - 13: AI Argues for Three Presidents - Child Picks the Winner

You are going to argue that THREE different presidents had the hardest job in American history. Pick the 3 you think have the strongest cases. For each one, give me the 3 biggest reasons their job was hardest. Then I will pick the winner.

After reading the output, the child identifies which president they pick as the winner - and writes one paragraph explaining the choice. The paragraph must include at least one reason that was NOT in the AI's output. This is the core skill: AI can build an argument for any position. Choosing which argument is best-supported requires independent reasoning, not AI agreement.

Ages 14 - 16: Build a Full Historical Case and Test the Counterargument

The child chooses one president they think had the hardest job, then runs:

I want to argue that [president name] had the hardest job of any American president. Using historical evidence, help me build the strongest possible case. Cover: 1. The crises they faced and what made each genuinely hard 2. The resources and support they had - or didn't 3. What would have happened if they had failed Then give me the strongest counterargument. Which president would most historians say had a stronger claim, and why?

After reading the output, the child writes a two-paragraph verdict that takes the counterargument seriously before defending the original choice. The verdict must acknowledge the strongest point in the counterargument. This is the analytical skill at the center of the activity - engaging with the best version of an opposing argument rather than dismissing it.

Parent and Educator Sidebar

Conversation starters after the activity:

• "Did the AI's argument surprise you? Was there a president it mentioned that you didn't know much about? Does that make you trust the argument more or less?"
• "The AI made a case for multiple presidents - sometimes for opposite positions. Does that mean there's no right answer, or does it mean some answers are more supported by evidence than others?"
• "If you were making this argument in front of your class, what is the one piece of evidence you would rely on most? Is that evidence in what the AI said, or something you knew before?"

Core AI literacy concept the child is learning:

Persuasive-sounding output is not accurate output. AI will build a compelling case for Lincoln, FDR, and Washington with equal confidence. The quality of each argument depends entirely on the historical evidence behind it - and AI does not always have that evidence right. The child who asks "is this argument actually supported by the history?" before accepting it is demonstrating the competency that makes every other AI use more effective. That habit, once established, transfers to every other context where AI output sounds confident but may be wrong.

Action Steps Summary

• Ask the child to name one president they already know something about before starting. Prior knowledge is the tool they will use to evaluate the AI's argument.
• Choose the age-appropriate activity path (8 - 10, 11 - 13, or 14 - 16) and have the child run the corresponding prompt in ChatGPT or Claude. Do not pre-read the output before the child does.
• Do not skip the evaluation step. The AI output is not the activity. The child's assessment of the output - what it got right, what it left out, whether it was persuasive for good reasons - is the activity.
• If the child agrees with everything the AI said, ask one question: "Is there anything the AI left out that you think matters?" The goal is independent reasoning, not AI agreement.
• Use the three conversation starters in the sidebar after the activity. The debrief is where the child articulates the lesson - which is how it becomes a durable skill rather than a one-time exercise.