Teachers · Instructional coaches · 20 suggested minutes
Write feedback that leads to a revision
Use a fully invented response to practice drafting a specific next step, a revision opportunity, and a check the teacher can actually use.
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.
Bring these inputs
- A teacher-written task, learning goal, and clear success criteria
- A fully invented response plus the teacher’s own evidence-based observation
- Time for a manageable revision and an independent check on the same idea
The output to keep
A brief teacher-edited feedback comment, a bounded revision task, a worked synthetic revision, and a plan to inspect the new evidence locally.
Try the workflow
20 suggested minutes in total. Allow more time whenever checking, access or local policy requires it.
Find the smallest useful gap 3 suggested min
Read the task and criteria before writing a comment. Distinguish absent reasoning from an incorrect idea. For an AI rehearsal, invent a response from scratch rather than transforming real student writing. Keep actual work in its approved school location. Choose one important improvement.
Draft feedback that points to an action 4 suggested min
Use the prompt to identify something already present, name the specific gap, and ask for one doable next move. Avoid generic praise, personality labels, inferred effort, or claims about the writer’s emotions. Do not let the model complete the learner’s thinking inside the feedback. For an ambiguous task, revise instruction first.
Plan the revision opportunity 4 suggested min
Decide when and how the learner could act on the feedback using materials already available. Provide a bounded action such as adding a labeled comparison or connecting a claim to one item of evidence. If that action requires missing knowledge, plan a short explanation first. Plan an opportunity to use the comment.
Test the comment against a synthetic revision 5 suggested min
Write a plausible revision yourself and inspect whether the comment actually leads toward the criterion. A corrected answer does not prove independent understanding. Create one small new task that checks the same idea with different surface details. Solve that check independently; otherwise hold it.
Choose the human follow-through 4 suggested min
Edit the comment into your own voice and decide whether to use it. Stop for personal information, unsupported claims about the writer, incorrect subject feedback, or a revision task that supplies the whole answer. Teachers inspect actual work locally; the prompt does not diagnose, grade, or maintain learner profiles.
Copy-ready prompt
Replace the placeholders with public, teacher-authored or invented material. Keep personal information out of the prompt.
Help an adult teacher rehearse actionable feedback using only this invented work. Task, goal, and criteria: [task/goal/criteria] Fully synthetic response: [newly invented response] Teacher observation: [evidence visible in the response] Revision time and materials: [constraints] Return a brief feedback comment that names evidence already present, identifies one task-specific gap, and asks for one achievable revision without supplying the answer. Give a short revision instruction and a fresh independent check with a separate worked answer. Separate observations from uncertain explanations. Flag unclear task directions. Do not infer ability, effort, emotions, identity, disability, or intent; do not grade or rank. Keep feedback focused on the work, not the person. I will check subject accuracy, edit the wording, and make the teaching decision.
Invented example · not an outcome claim
Synthetic worked example
Context: All text is newly invented to illustrate the process; no classroom result is claimed.
Input: Task: 'Is 0.7 greater than 0.65? Explain using place value.' Success criterion: compare equal units and connect them to the conclusion. Synthetic response: '0.7 is bigger because 7 is bigger than 6.' Teacher observation: the comparison is correct, but the response does not identify what the digits represent. Six-minute revision window; paper and pencil.
Example output
- Weak draft feedback: 'Great job! Be more detailed.' It does not identify the missing mathematical evidence or say what to do next. Avoid changing it to a character judgment such as 'You are good at decimals.'
- Teacher-edited comment: 'Your comparison is correct. Make the place-value reasoning visible: write both numbers in hundredths, then explain how those amounts support your conclusion.' The converted numbers remain for the learner to find.
- Revision instruction: 'Use the first 2 minutes to rewrite the numbers in hundredths, the next 2 minutes to add your explanation, and the last 2 minutes to check that your comparison symbol matches it.' If the equal-unit idea is unfamiliar, replace the revision with a short teacher model using different numbers before returning to the task.
- Synthetic revised response: '0.7 is 70 hundredths and 0.65 is 65 hundredths. Because 70 hundredths is greater than 65 hundredths, 0.7 > 0.65.' Independent check: multiplying both positive decimals by 100 gives 70 > 65, consistent with the place-value explanation. The explanation meets the criterion.
- Fresh check: 'Compare 0.6 and 0.58 using hundredths. Explain the comparison.' Separate teacher key: 0.6 = 0.60, or 60 hundredths; 0.58 is 58 hundredths; therefore 0.6 > 0.58. A correct symbol without units still leaves the target reasoning unseen.
- Follow-through plan: inspect the revision and fresh check locally. If units are explicit in both, consider moving on while acknowledging that this is limited evidence. If only the coached revision includes units, ask for a further explanation rather than assuming the underlying idea is secure. The teacher makes that judgment.
The human decision: Keep the comment and revision opportunity. The example demonstrates neither actual learning nor why an explanation was brief.
Teacher-owned checks
- Is the observation supported by words or work actually present?
- Is the next action clear, manageable, and connected to the criterion?
- Does the comment leave meaningful reasoning for the learner?
- Is time and material available to act on it?
- Are the revision and fresh-check keys correct, with uncertainty kept visible?
- Have all statements about personal traits, effort, or emotion been removed?
Measure this attempt
Record drafting plus checking minutes, comments materially rewritten, and whether each feedback plan includes an action, a revision opportunity, and a checked fresh task. These process measures do not establish AI-driven learning gains.
Repeat deliberately
Keep a small bank of task-specific feedback patterns without real learner responses. Recheck each pattern against the new task and criteria before reuse. Revise unclear directions without building learner profiles.
Adapt the method
- For argument writing, ask for a missing connection between a claim and a supplied source rather than rewriting the entire paragraph.
- For science, ask the response to distinguish an observation from an explanation using the evidence actually provided.
- For oral or practical work, use a brief teacher-delivered next-step instruction and a new demonstration opportunity without recording learners.
Your 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
- Space for your own offline notes
- Small planning task and intended output
- Space for your own offline notes
- Actual minutes spent, including checking
- Space for your own offline notes
- What I independently checked and where
- Space for your own offline notes
- One correction or unresolved issue
- Space for your own offline notes
- Decision: keep / revise / drop / hold
- Space for your own offline notes
- One change to try next time
- Space for your own offline notes
- Optional next reflection point
- Space for your own offline notes
These are blank spaces for your offline copy. This site does not collect or store entries.
Public sources & their limits
Sources reviewed . Review dates describe this editorial check, not the source publication date.
- Teacher Feedback to Improve Pupil LearningEducation 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 ExpressionCAST
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.
- Teacher Feedback to Improve Pupil Learning: Summary of recommendationsEducation Endowment Foundation
Supports: The summary emphasizes task-focused feedback and planning an opportunity for learners to use it. This informs the feedback-and-revision sequence.
Limit: The source concerns teacher-delivered feedback, not the validity of AI-generated comments. No learning or workload effect is established for the synthetic example.
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.