better-ed
HomeUse CasesPricingPrivacy & TrustFAQContactAbout
LoginSign up for free
better-ed

Empowering educators with AI-powered voice assessment tools. Hear every student think—without doing more work.

LinkedInFacebookYouTube
CompanyAboutTeaching TipsBlogUse CasesPrivacy & TrustPricingFAQChangelog
Finland

Lapinlahdenkatu 16, 00180 Helsinki

Philippines

Unit 3006, One Corporate Centre, Julia Vargas Ave., Ortigas Center, Pasig City

© 2026 better-ed. All rights reserved.

Privacy PolicyTerms of ServiceCookie PolicyDelete account
All tips
AI INTEGRITY

Make the AI argue against itself

Ask for the answer, then ask for the strongest case that the answer is wrong. The gap between the two is where the judgement lives.

Sep 15, 2026 · 1 min read

Models agree too easily, with you and with themselves. A useful classroom counter-move: after any substantive AI answer, require the follow-up "now make the strongest case that what you just said is wrong or incomplete." Where the self-critique is weak, the original was probably solid; where it lands a real punch, the student has found the claim that needed checking, and practised the adversarial reading that transfers to every source. (Manning's ai-expertise-interrogation-designer skill builds full routines on this.)

In practice

  • Make it a standing pair of prompts for research tasks: answer, then counter-case, then the student writes two sentences adjudicating.
  • The adjudication is the assessable part: which points of the counter-case stick, and how would you check?
  • Anything the counter-case flags as factual and checkable goes through lateral reading (see "Teach lateral reading on AI citations").

Quick takeaway: one answer is information. The answer plus its strongest rebuttal is an exercise in judgement.

More on ai integrity

AI INTEGRITY

Chase the claim outside the chat window

Asking the model to verify itself is not verification. Teach students to leave the chat and find independent coverage of the claim.


1 min read
AI INTEGRITY

Pilot the AI tool on your best-known topic

Before any tool reaches students, run it on the topic you know best. That is the one place you can see exactly what it gets wrong.


1 min read
AI INTEGRITY

Bookend every AI session with a plan and debrief

A goal before the chat opens and a debrief after it closes keep the student, not the model, in charge of the learning.


1 min read