Learning guide · prototype · Suggested 15–25 minutes

An AI Debate Coach for Evidence, Reasoning, and Voice

About this resource · How to use it · Learning engineering connections

What is this resource?

A guided activity for An AI Debate Coach for Evidence, Reasoning, and Voice. Explain how a design could help people construct, defend, and revise an evidence-based argument in real time, and what evidence would justify another iteration. Begin with the use case below. Keep the proposed design separate from what the current exercise actually implements.

How should I use it?

  1. Read Before you begin, then use Open the project to try the listed steps alongside this guide.
  2. Record an observation, explanation, transfer question and next test in the reflection panel. Saving is optional; Print one-page guide produces a paper copy.

How does this connect to LENS and learning engineering?

This activity connects a capability question to observable work and a possible next decision. Does repeated AI rehearsal improve live performance with a human audience? Working teaching exercise; the broader design and its learning effects remain hypotheses. Use the reflection to distinguish what you observed from what still needs evidence.

Explain how a design could help people construct, defend, and revise an evidence-based argument in real time, and what evidence would justify another iteration.

Students often need far more low-stakes rehearsal in argumentation and public speaking than a teacher or coach can provide. Generic generative AI can produce polished arguments for learners, however, which risks replacing the very reasoning and voice the practice is meant to develop.

Before you begin

Begin with the use case below. Keep the proposed design separate from what the current exercise actually implements.

A use case to work with

A learner preparing a school debate gives a two-minute opening statement. The coach asks one skeptical follow-up, highlights an unsupported inference, and invites a revised response before showing any model language.

Try this

  1. Read the representative use case. Identify who must do what and under which conditions.
  2. Try the available exercise with a fictional example. Record your first decision and one revision.
  3. Choose one assumption to test. Use the evidence prompts in the brief to define an outcome that could change your mind.
Open the project (opens in a new tab)

Keep this guide open while you explore.

Pause & make sense

What are you taking away?

How should the system handle controversial topics or biased source material?

Optional. Notes are not sent to a server or scored. Browser storage is specific to this device and can be cleared; download a copy to keep it. Avoid sensitive information on shared devices.

Open my notebook

Notes stay on this page unless you choose to save or download them.

Help me make sense of this
  1. Separate what happened from why. Your observation is the result; your explanation is a claim that may need testing.
  2. Check another explanation. What else could account for the result? What comparison would distinguish them?
  3. Try without the support. Could you explain or perform the task in a new situation? Identify what evidence you would need.
  4. Choose one next move. Return to the concept, compare another example, or test one changed assumption.

Choose your next move

Return to the process, or examine how evidence could change a design.

The Capability Pipeline →Evidence-to-Impact Mapper →
Choose another question on the map