Debate rewards preparation more than improvisation. These 15 prompts let you construct full case briefs, run cross-examination drills, and pressure-test your strongest arguments before the round — in policy, LD, parliamentary, or moot-court formats. One rule shapes everything below: under current NSDA rules (2025-26 season), you may use AI to find articles, ideas, and sources, but you may not quote or paraphrase AI text in a round, and AI cannot be cited as a source. Treat every prompt here as prep, never as evidence.
TL;DR
- Use AI to build structure (cases, blocks, cross-ex banks) and to find leads, then read the real source. Never read an AI-written card.
- For long case files and nuanced impact framing, Claude Opus 4.7 (1M-token context) handles full briefs in one window. Gemini 3.1 Pro is strongest on pure reasoning and topic research; GPT-5.5 is the balanced all-rounder.
- Start with templates 1-4 (cases + cross-ex), then layer in topicality (7), counter-plans (8), and kritiks (9) once the basics hold.
- The NSDA rule (verified June 2026): AI may guide you to sources; the original source of any quoted or paraphrased evidence must be available on request.
Who this is for
High school and college debaters, debate coaches building case files, MUN delegates, moot court teams, and law students prepping oral arguments.
When not to use these prompts
Skip for casual classroom debate where deep prep is wasted. Skip if your tournament or league forbids AI prep — check the invitation and your circuit’s rules first. And never paste an AI-drafted contention into a round as if it were carded evidence; that violates NSDA evidence rules and most local circuit norms.
Which model for which job
As of June 2026, the three frontier models split cleanly by debate task. Pricing is the standard consumer tier.
| Task | Best pick | Why | Cost |
|---|---|---|---|
| Whole case file in one window (1M tokens) | Claude Opus 4.7 | Holds an entire affirmative + neg block file; strong on nuanced impact framing | Claude Pro $20/mo |
| Topic research & deep reasoning | Gemini 3.1 Pro | Leads pure-reasoning benchmarks; 1M context for source dumps | Google AI Pro $19.99/mo |
| Fast all-round drilling | GPT-5.5 | Balanced; quick cross-ex and round simulations | ChatGPT Plus $20/mo |
A free Claude or ChatGPT account runs every prompt below — paid tiers mainly buy higher limits and the larger in-app context for pasting long briefs.
How to write a debate prompt
A debate prompt works best when it carries five things, in this order:
- Format and side: policy / LD / PF / parliamentary / moot court, and whether you are aff or neg.
- Resolution and your position: paste the full resolution text and your one-line thesis.
- Deliverable: one concrete output — a 4-contention case, 12 cross-ex questions, a 200-word refutation block.
- Constraints: word or time limit (a speech is seconds, not words), what to include (tag / warrant / impact), what to skip.
- Evidence handling: tell it to mark every claim that needs a real source with the source type you should chase, not a fake citation.
Best for
- Affirmative or negative case construction
- Cross-examination prep (both attack and defense)
- Refutation block writing
- Impact calculus rehearsal
- Moot court / mock trial argument drafting
15 copy-ready prompt templates
In every template, replace the bracketed placeholders such as [resolution] with your own text before sending.
1. Affirmative case in 4 contentions
Default policy-style case skeleton.
You are a debate coach. Build an affirmative case for the resolution "[resolution]". Output: 1 framework, 4 contentions. For each contention: 1-sentence tag, 1-sentence warrant, 1-sentence impact, 1 evidence source I should locate. Total under 600 words.Variable to swap: resolution
Optimization: If impacts are weak, add: “Each impact must terminalize to a value (lives saved, dollars, rights protected, time horizon). No floating claims.”
2. Negative case in 3 layers
Build a negative case against "[resolution]": (a) framework challenge, (b) 2 substantive contentions undermining the aff, (c) 1 disadvantage or counter-plan. Include tag / warrant / impact for each.3. Cross-examination question bank
Generate 12 cross-examination questions to ask an affirmative team running "[aff thesis]". Mix: 3 clarifications, 4 narrowing questions, 3 trap questions setting up your refutation, 2 framework challenges. For each: the question and the answer that would set up your response.4. Cross-examination defense drills
I am affirmative running "[thesis]". Generate 10 hostile cross-ex questions a sharp opponent would ask. For each: my best honest answer in 1 sentence, the trap to avoid, and how I would pivot if asked.5. Refutation block on key argument
My opponent will likely argue "[opponent argument]". Write a 200-word refutation block: 1 framing line, 3 specific counter-arguments with evidence types, 1 turn (where their argument actually helps me), 1 impact comparison.6. Impact calculus rehearsal
For my impact "[my impact]" and the opponent's impact "[opp impact]", write 150 words of impact calculus covering: magnitude, probability, time-frame, reversibility, and why mine outweighs theirs. End with the one-line judge takeaway.7. Topicality / definitional argument
For the resolution "[resolution]" and the aff "[aff plan]", build a topicality argument: definition, violation, standards, voters. Include 1 author / source per definition. Keep under 250 words.8. Counter-plan construction
Against the aff "[aff plan]", construct a counter-plan: the action, why it solves the affirmative impacts, the net benefit (something the aff cannot capture). Include a perm-block on "do both".9. Kritik (theory-level) sketch
Sketch a kritik against the aff "[aff plan]": link (what assumption the aff makes), impact (what is wrong with that assumption), alternative (what to do instead). Use a recognizable theoretical framework: capitalism, biopolitics, settler colonialism, or security K. Keep terms accessible.10. Evidence-card request list
For my aff on "[resolution]", list 10 evidence cards I need: claim I would use them to support, ideal source type (peer-reviewed / think tank / news / government), 1-line of what the card should say. Mark which 3 are highest priority.11. Round flow simulation
Simulate a round on "[resolution]" through the first 4 speeches: AC (aff constructive), NC (neg constructive), 1AR, NR. For each speech, give the speech's 3 main moves and the 1 line a judge would write on the flow.12. Judge adaptation brief
For a judge with a [paradigm: flow / lay / tabula rasa / policy-maker] paradigm, how should I adapt my aff case on "[resolution]"? List 5 specific moves I should add or drop, with rationale.13. Final-rebuttal “voter” outline
For my final speech on "[resolution]", outline 3 voters (key reasons the judge should vote for me). Each: a 1-sentence claim, the relevant flow location, the impact comparison line. End with a 30-second "ballot story".14. Moot court oral-argument opener
For a moot court argument in [case name], draft a 90-second oral-argument opener: facts in 1 sentence, issue, my position, 3 reasons, and my one-line concession to anticipate. Voice: formal, court-appropriate.15. Post-round self-debrief
I lost a round on "[resolution]" arguing aff. Below is the judge's RFD (reasons for decision): [paste]. Identify: (a) the 1 argument that lost the round, (b) the speech where I should have responded better, (c) 1 prep change for next round, (d) 1 rhetorical change.Common mistakes
- Building cases without evidence — debate rewards warranted claims, not assertions.
- Skipping topicality or framework — judges who flow these will tank you.
- Memorizing whole speeches instead of structured cases; rigid scripts crumble in cross-ex.
- Ignoring impact calculus — winning arguments without weighing them loses ballots.
- Practicing only with friendly partners; AI gives you a tireless hostile sparring partner.
- Running a kritik you cannot defend in cross-ex — only run K positions you actually understand.
- Forgetting judge adaptation; the same speech wins or loses depending on paradigm.
- Reading AI text as evidence — an NSDA-illegal move that a sharp opponent can challenge for the source.
How to push results further
- Maintain an evidence file organized by topic; AI generates request lists, not citations.
- End every contention with a terminal impact: lives, dollars, or rights, with a time horizon.
- Make your first cross-ex questions clarifications; save trap questions for late.
- Run one full round per week with AI as opponent before live drills.
- Re-prompt the same case from the opposite side; you find weaknesses faster.
- Treat AI-generated evidence claims as leads, not citations — always find and read the real source.
- Time every speech you draft; AI pads without realizing a speech is measured in seconds.
FAQ
- Can I use AI evidence in a round?: No. Under NSDA rules you cannot quote or paraphrase AI text, and AI cannot be cited as a source. Use AI to identify what to look for, then read the real source from a database. The one exception: a speech about AI may quote AI to illustrate a point, within normal quoted-word limits.
- Are AI-written counter-plans tournament-legal?: A counter-plan you author with AI prep help is fine, as long as the evidence you read is from real sources you can produce on request, and your league does not ban AI prep. Check your circuit rules.
- Which model should a beginner pick?: Any free tier works. For structure (templates 1-4), Claude or ChatGPT free are plenty. Avoid theory-heavy templates like the kritik (9) until the basics hold.
- How realistic is AI as a sparring opponent?: Strong on argument generation, weaker at strategic mid-round pivots. As of June 2026, Claude Opus 4.7 and Gemini 3.1 Pro give the most coherent long arguments; none replaces human practice.
- Can AI judge my speeches?: It can flow and critique if you paste the speech and a paradigm. Treat it as one judge, not an oracle, and remember its feedback is prep, not a ballot.
Related
- Argument strengthening prompts
- Essay thesis prompts
- Thesis topic prompts
- Research summary prompts
- How to Use AI for Step-by-Step Math Explanation: Understand, Not Cheat
- AI Writing Feedback: Get Senior-Editor Critique on Any Draft in Minutes
- Historical Timeline Prompts for Causal Narratives
- Learning & Research Prompts hub
- Data Interpretation Prompts for Tables, Charts and Stats
- NSDA generative AI policy: speechanddebate.org/rules-forms-manuals