# Check a lesson before teaching Published 2026-10-13 · Version 1.0 By the ChatwithGPT editorial project. Prepared with AI assistance. Turn a draft activity into a teachable sequence with a clear learning goal, a matching check, and verified materials. For: Teachers · Instructional coaches Suggested time: 20 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 learning goal in plain language and the prior knowledge the task assumes - A short draft activity or a teacher-created description safe to share - Available lesson time, materials, and general access requirements without student details ## Output to keep A short lesson sequence, a checked example and exit task, and a list of unresolved issues that would prevent use. ## Try the workflow ### 1. Name the learning (3 suggested minutes) Write what learners should be able to explain or do. Write a possible response that would show it. If the goal is unclear, settle that before generating activities. ### 2. Draft the sequence (5 suggested minutes) Use the prompt or sketch a model, guided attempt, independent attempt, and brief exit task. Include transitions and materials in the lesson-time total. Ask for only one alternative if the first plan is impractical. ### 3. Solve and inspect (5 suggested minutes) Complete the example and exit task yourself. Check every fact, calculation, instruction, and key. Compare the work required by the exit task with the goal. Use Verify sources and answer keys when a factual claim needs checking. ### 4. Remove a barrier (5 suggested minutes) Choose one likely obstacle, such as dense directions or a response mode unrelated to the goal. Add a brief model, vocabulary support, or another way to respond while preserving what the task is meant to assess. ### 5. Make the teaching decision (2 suggested minutes) Mark the plan ready, revise, or hold. Keep a note of what you changed and why. An unresolved factual or answer-key error means hold that part. ## Copy-ready prompt ```text Help me revise a lesson draft for adult teacher review. Goal: [one learning goal] Prior knowledge: [general prerequisites] Lesson time and materials: [constraints] Safe-to-share draft: [teacher-created description] General access requirement: [for example, directions must also be available in plain text] Return: (1) a sequence whose minutes fit the lesson time, (2) one modeled example, (3) one independent task and a worked answer, (4) an exit task that directly checks the goal, (5) one optional scaffold that preserves the goal, and (6) assumptions and items I must verify. Explain how each task connects to the goal. Do not invent standards alignment, citations, classroom results, or student characteristics. Label factual claims that need sources. Everything is a draft until I check it. ``` ## Synthetic worked example Context: A teacher is preparing a 15-minute fraction comparison segment. This is an invented planning situation. Input: Goal: compare two fractions referring to the same-size whole and justify the comparison. Prerequisites: equal parts and equivalent fractions. Materials: paper and pencil. Draft: explain cross-multiplication for 10 minutes, then ask learners to name the numerator in 2/3. Example output: - The exit task does not check the stated goal. Replace it with “Which is greater, 3/4 or 4/5? Show or explain why.” - Revised segment: 3 minutes model 2/3 versus 3/4 with same-length strips; 4 minutes guide a comparison of 1/2 and 2/3; 5 minutes independent comparison of 3/5 and 2/3; 3 minutes share a reason and complete a fresh exit comparison of 3/4 and 4/5. - Teacher-checked answers: 2/3 = 8/12 and 3/4 = 9/12, so 3/4 is greater. Also 1/2 < 2/3, 3/5 = 9/15 < 10/15 = 2/3, and 3/4 = 15/20 < 16/20 = 4/5. - Optional support: provide equal-length blank strips and “___ is greater because ___.” Accept a labeled diagram or oral explanation when the goal is fraction reasoning rather than writing. Human decision: Use the revised sequence only after checking strip sizes, task directions, and the time available. No claim is made about how a class would perform. ## Teacher-owned checks - Can the exit task actually reveal the learning in the goal? - Have I independently checked the example, every answer, and any factual source? - Do the materials, transitions, and response options fit this lesson? - Does the scaffold preserve the intended reasoning rather than supply the answer? ## Measure this attempt Record your planning minutes and the number of factual, key, or goal-mismatch problems you corrected before use. These describe the preparation process, not teaching quality or student learning. ## Repeat deliberately Save the checked structure, not an unchecked generated lesson. Next time, replace the goal and examples, recheck the answers, and change one source of friction. After use, privately note one instruction you would clarify. ## Adapt the method - For literacy, check that a response must use the text evidence named in the goal. For science, check that the explanation follows from the information provided. - For arts or practical subjects, replace a written exit task with a demonstration plus a brief explanation when that matches the goal. - Low-prep version: revise only the exit task and one worked example from an existing lesson. ## 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 - [Teacher Feedback to Improve Pupil Learning](https://educationendowmentfoundation.org.uk/education-evidence/guidance-reports/feedback) — Education Endowment Foundation Supports: The guidance focuses on feedback grounded in teaching and an understanding of learning gaps. This informs checking the learning goal and using evidence to consider a next teaching step. Limit: The source concerns teacher feedback. It is not evidence that AI analysis, these prompt sequences, or the suggested timings improve learning. - [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. 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/verify-lesson/ An independent AI field journal. Not affiliated with or endorsed by OpenAI.