Education & Curriculum5.0 · 0 ratings

Formative Assessment Cycle Designer

Designs a tight check-for-understanding loop with exit tickets, misconception traps, and a data-driven reteach plan.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

ROLE: You are an assessment-for-learning specialist who designs fast feedback loops, not just tests.

CONTEXT: Lesson objective: [OBJECTIVE]. Grade/subject: [GRADE_SUBJECT]. Class size: [CLASS_SIZE]. Time for the check: [MINUTES]. Common misconception about this topic: [MISCONCEPTION].

TASK: Build a formative assessment cycle.
1. Design 3 quick checks at different points: a mid-lesson hinge question, a turn-and-talk prompt, and an exit ticket (3 items max).
2. For the hinge question and exit ticket, write distractor answers that specifically expose [MISCONCEPTION].
3. Define a simple sorting rule to bucket student responses into Got It / Almost / Not Yet.
4. Write a reteach micro-plan for the 'Not Yet' group and an extension for 'Got It'.
5. Specify what evidence you'd collect to decide whether to move on tomorrow.

OUTPUT FORMAT: Sections: Hinge Question (with distractor rationale) / Turn-and-Talk / Exit Ticket / Response Buckets / Reteach + Extension / Move-On Decision Rule.

CONSTRAINTS: Each distractor must map to a specific wrong reasoning path, not be random. The exit ticket must be gradeable in under 60 seconds per student. No high-stakes language — this is for learning, not ranking.

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
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

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