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 Policy
All tips
AI PROMPTS

Ask for a hint ladder, not an answer key

Tutoring systems work because help arrives one step at a time. You can generate that structure for any problem in a minute.

Aug 13, 2026 · 1 min read

Decades of intelligent tutoring research point at the same design: step-level help, escalating gradually, keeps the learner doing the work; systems built this way approach human tutoring in effectiveness (VanLehn, 2011). AI makes the expensive part cheap: for any problem you can generate a ladder of hints, from a nudge to a near-solution, and hand out only as much as each student needs. (This mirrors the progressive-hint-ladder skill in Gareth Manning's education-agent-skills library.)

In practice

prompt.txt
For this problem, write a 4-rung hint ladder:
1. A question that redirects attention, giving nothing away.
2. A reminder of the relevant concept, no method.
3. The first step of the method, not the rest.
4. A worked step with the final answer still missing.
Each rung one or two sentences.
  • Print ladders on card, folded so students reveal one rung at a time, and note which rung they needed. That's assessment data.
  • Use them yourself while circulating: rung 1 aloud before rung 2, instead of the full rescue we all default to.

Quick takeaway: generate the help in steps so students can stop climbing early.

More on ai prompts

AI PROMPTS

Ask for a task they can start, not finish

Productive failure needs a precisely calibrated task: solvable in part with what they know, unsolvable without what you are about to teach. Let AI calibrate it.


1 min read
AI PROMPTS

Make every wrong option confess a misconception

A multiple-choice question earns its keep when every wrong answer tells you exactly which misconception produced it, and which repair comes next.


1 min read
AI PROMPTS

Have AI plant why-questions inside the worked example

Students read worked examples passively. Ask the AI to plant a why-question at each tricky step and reading turns into explaining.


1 min read