Back to guide/Education & Learning

Differentiated Instruction Adapter

Asking for the rationale behind each modification helps teachers understand the differentiation strategy, not just get a worksheet. Specifying ELL proficiency level avoids one-size-fits-all language support.

chatgpt-prompts-for-teachersgrade_levelsubjecttopic
Edit View
Prompt
I have a {{grade_level}} {{subject}} lesson on {{topic}} with this core activity:
{{core_activity}}

Create 3 differentiated versions:

1. **Advanced learners**: Extend the activity with higher-order thinking (analysis, evaluation, creation). Add complexity without just adding more work.

2. **On-level with support**: Keep the core activity but add scaffolding — sentence starters, graphic organizers, word banks, or step-by-step breakdowns.

3. **English Language Learners ({{ell_proficiency_level}})**: Modify for language accessibility — visual supports, simplified instructions, native language cognates where helpful, and reduced linguistic demand while maintaining content rigor.

For each version, explain what you changed and why.

Variables to customize

{{grade_level}}{{subject}}{{topic}}{{core_activity}}{{ell_proficiency_level}}

Why this prompt works

Asking for the rationale behind each modification helps teachers understand the differentiation strategy, not just get a worksheet. Specifying ELL proficiency level avoids one-size-fits-all language support.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Sentiment Analysis

Requesting confidence and key phrases forces the model to justify its classification rather than guessing. The structured output format works zero-shot because sentiment analysis is well-understood by LLMs.

Key Information Extraction

Listing the exact fields to extract removes guesswork. The 'Not specified' instruction prevents hallucination when information is missing -- a common failure mode without this guardrail.

Question Answering with Source

Grounding the answer in source material and instructing the model to refuse when information is missing dramatically reduces hallucination -- the biggest risk in zero-shot Q&A.

Math Word Problem Reasoning

Explicit numbered steps force the model to decompose the problem rather than guessing. The verification step catches arithmetic errors before the final answer.