# Design questions that invite reasoning Published 2026-10-13 · Version 1.0 By the ChatwithGPT editorial project. Prepared with AI assistance. Build a short question sequence around evidence, interpretation, and revision of an idea. For: Teachers · Instructional coaches Suggested time: 15 minutes. Planning estimates, not measured completion times. Published October 13, 2026. Times are suggested planning estimates, not measured completion times. These workflows have not been classroom-tested, and no learning gains or time savings are claimed. Public primary-source guidance informs selected design choices; it does not establish this toolkit’s effectiveness. Process measures help an educator decide whether to keep or revise a workflow. They are not student-outcome measures or teacher-performance scores. ## Before you begin - Use school-approved tools and follow local policy. Keep student work, names, identifiers, photographs, voices, disability information, behavior records, and staff or personnel records out of prompts. Removing a name does not necessarily make a record anonymous. - Use the supplied synthetic inputs when trying a prompt. If you consider a real aggregate later, have an authorized person check that it cannot identify anyone and that the intended tool and use are permitted. Small groups and unusual details can identify people. When unsure, keep the evidence offline and use a fictional pattern. - Teachers decide what to teach and how to respond. Do not use these workflows for automated grading, placement, discipline, eligibility, teacher evaluation, or other consequential decisions. - Do not record lessons or coaching conversations for these workflows. Keep planning notes brief, teacher-owned, and separate from personnel evaluation. Do not score teachers or monitor individual participation. - Treat every AI answer, answer key, citation, and standards claim as an unchecked draft. Verify facts and calculations using sources you can inspect. Standards alignment requires the exact official standard and a teacher review; it is not claimed here. - Use only materials you have permission to share with the tool. A public web page is not permission to upload or reproduce its entire contents. ## Inputs - One short, permitted text, problem, image description, or data display - A learning goal and the evidence learners can actually use - A discussion length and general language or access requirements ## Output to keep Three linked questions, plausible responses, follow-up prompts, and a brief individual check. ## Try the workflow ### 1. Choose the evidence (3 suggested minutes) Read or solve the shared material yourself. Identify what is stated, what can reasonably be inferred, and what remains uncertain. ### 2. Draft the questions (4 suggested minutes) Write one entry question, one question requiring a reason supported by the material, and one inviting an alternative or a revision. Use the prompt if helpful. Describe the reasoning required instead of assigning a complexity level from an action verb. ### 3. Test possible responses (3 suggested minutes) Write one well-supported response and one plausible but weak response. Check that the questions permit a real distinction between them without forcing a single interpretation when several are defensible. ### 4. Plan participation options (3 suggested minutes) Build in quiet thinking time, an optional partner rehearsal, and a written or drawn response route. Prepare one neutral invitation to expand a reason. Avoid using volume, speed, or speaking frequency as a measure of understanding. ### 5. Check and trim (2 suggested minutes) Remove any question answerable without the intended evidence. Choose a short individual response that lets you see the reasoning after the discussion. ## Copy-ready prompt ```text Create a short discussion sequence for teacher review. Learning goal: [goal] Safe-to-share material: [brief original or permitted material] Discussion time and access requirements: [constraints] Give three linked questions: entry, evidence-based reasoning, and reconsideration. For each, identify the evidence needed, the reasoning required, a plausible supported response, a plausible weak response, and one neutral follow-up. Include quiet thinking time, an optional partner rehearsal, an alternative to public speaking, and a brief individual check. Do not assign DOK or other complexity levels from verbs. Do not invent source details, force personal disclosure, or treat participation frequency as learning. Label interpretations as interpretations. ``` ## Synthetic worked example Context: This original fictional microtext is written for the toolkit. It can be read aloud or displayed as plain text. Input: Microtext: “The group’s tower fell. Amara put the blocks back in the box. When Jules reached for the box, Amara slid it closer and cleared a space on the table.” Goal: support an inference with a text detail while distinguishing inference from certainty. Example output: - Entry: “What does Amara do after Jules reaches for the box?” A supported response names sliding the box closer and clearing space; it does not yet need a claim about feelings. - Reasoning: “What might those actions suggest about Amara’s willingness to try again? Which detail supports your view?” One reasonable inference is that Amara may be open to rebuilding, supported by making the blocks and workspace available. “Amara is definitely excited” overstates what the text establishes. - Reconsideration: “Could another explanation also fit? What extra information would help you decide?” Amara could be making room for Jules without intending to build. Both interpretations need to remain compatible with the actions in the text. - Follow-up: “Which words support that, and what are you adding as an inference?” Suggested classroom sequence: 1 minute think, 2 minutes optional pair rehearsal, 4 minutes discussion, 2 minutes individual response. - Individual check: “Write or draw one possible inference, connect it to one action, and name something the text does not tell us.” Optional stem: “The action ___ could suggest ___, but we do not know ___.” Human decision: Keep more than one defensible interpretation. Check the link between the interpretation and the text, rather than requiring a particular emotion label. ## Teacher-owned checks - Do the questions require the material rather than a guess about what I want? - Have I described the actual reasoning and evidence instead of relying on a verb chart? - Is the key open to more than one response where the material supports that? - Can someone show their reasoning without speaking publicly or disclosing personal experiences? ## Measure this attempt Before use, count how many questions genuinely require evidence from the material. Note your preparation time and one follow-up you revised. These are design checks, not participation or learning scores. ## Repeat deliberately Keep the useful question pattern, then replace and re-read the source material. After discussion, write one anonymous note about a question that was unclear or too broad. Revise that question before reusing the sequence. ## Adapt the method - For mathematics, replace the text with two solution methods and ask which steps are justified. For science, distinguish observations from explanations using a small teacher-checked data display. - For older learners, use a more substantial source and ask what evidence would change a claim. For younger learners, shorten the text and allow drawing or pointing with an explanation. - The literacy guidance cited below supports discussion in its stated context. Cross-subject adaptations here are suggestions for teacher review, not proven transfers. ## Check-and-repeat log Keep this optional log privately, on paper or in an approved teacher-owned file. Record process details only. Do not add names, student work, response-level data, coaching transcripts, recordings, or personnel judgments. A few lines are enough; no submission or score is required. - Date and workflow used: ____________________ - Small planning task and intended output: ____________________ - Actual minutes spent, including checking: ____________________ - What I independently checked and where: ____________________ - One correction or unresolved issue: ____________________ - Decision: keep / revise / drop / hold - One change to try next time: ____________________ - Optional next reflection point: ____________________ ## Public sources and their limits - [Action and Expression](https://udlguidelines.cast.org/action-expression/) — CAST Supports: CAST describes options for how learners respond and communicate. This informs the optional response modes and scaffolds offered here. Limit: The toolkit does not reproduce CAST’s framework or claim certification. Teachers must check that an alternative mode still measures the intended learning. - [Improving Adolescent Literacy: Effective Classroom and Intervention Practices](https://ies.ed.gov/ncee/wwc/PracticeGuide/8) — Institute of Education Sciences, What Works Clearinghouse Supports: The guide recommends extended discussion of meaning and interpretation in adolescent literacy. This informs the discussion workflow’s attention to reasons and text evidence. Limit: The recommendation has a specific literacy context. It does not establish effectiveness for this microtext, all ages, other subjects, or an AI-generated question sequence. Published October 13, 2026. Times are suggested planning estimates, not measured completion times. These workflows have not been classroom-tested, and no learning gains or time savings are claimed. Public primary-source guidance informs selected design choices; it does not establish this toolkit’s effectiveness. Process measures help an educator decide whether to keep or revise a workflow. They are not student-outcome measures or teacher-performance scores. Read online: https://chatwithgpt.net/educators/design-discussion/ An independent AI field journal. Not affiliated with or endorsed by OpenAI.