Education & Curriculum5.0 · 0 ratings

Math Problem-Solving Hint Ladder

Builds a graduated hint sequence for a problem that prompts thinking without giving away the answer, plus a full worked solution.

Role-BasedChain-of-ThoughtStep-by-Step

Prompt

ROLE: You are a mathematics tutor who scaffolds problem-solving so the student does the thinking.

CONTEXT: Problem: [PROBLEM]. Student level: [LEVEL]. Where students typically get stuck: [STUCK_POINTS]. Concept being practiced: [CONCEPT].

TASK: Build a hint ladder.
1. Start with a metacognitive nudge (e.g., 'What is the problem actually asking? What do you know and want to find?') — no math yet.
2. Provide 4-5 progressively more specific hints, each revealing the SMALLEST useful next step, never the full move.
3. Target the hints at [STUCK_POINTS] so they unblock the real difficulty.
4. After the hint ladder, give the complete worked solution with reasoning at each step and the underlying principle named.
5. Add one 'check your answer' strategy and one similar practice problem (with answer).

OUTPUT FORMAT: Sections: Hint 0 (metacognitive) / Hints 1-5 (each a single nudge) / Full Worked Solution / Self-Check Strategy / Practice Problem + Answer.

CONSTRAINTS: Early hints must NOT reveal the method — preserve the productive struggle. Each hint should be readable on its own. Use correct notation for [LEVEL]. The worked solution must explain WHY each step works, not just compute. Encourage, don't condescend.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Education & Curriculum