Teachers · Instructional coaches · 30 suggested minutes
Build a coherent lesson-material packet
Use one bounded knowledge pack to author a lesson brief, learner handout, teacher key, and exit check that agree with one another.
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 single learning goal, lesson duration, and the small set of artifacts genuinely needed
- A teacher-owned knowledge pack containing checked facts, definitions, source links, allowed assumptions, and unresolved questions
- An artifact list with stable item labels, audiences, and a clear rule keeping teacher answers out of learner copies
The output to keep
Four linked draft artifacts, a cross-artifact consistency check, and a teacher-approved packet version. The knowledge pack is a bounded reference, not model training.
Try the workflow
30 suggested minutes in total. Allow more time whenever checking, access or local policy requires it.
Build the smallest useful knowledge pack 5 suggested min
Write the goal, essential definitions, checked examples, permitted source locations, and what must not be inferred. Distinguish teacher-created facts in a fictional scenario from external factual claims. Keep copyright permission, local policy, and privacy checks explicit. Use short original summaries. Exclude unresolved information from approved content.
Define the artifact contract 6 suggested min
Name the required outputs and their readers: teacher lesson brief, learner handout, teacher answer key, and exit check. Give tasks stable labels so the key can refer to them. Specify what must match across files and what must remain teacher-only. Decide which reference controls changed numbers before generating prose.
Draft in dependency order 7 suggested min
Draft the brief and task list first, then the handout, then solve the handout independently to author the key. Draft the exit check last against the same goal, using fresh values. The prompt may assist, but its own answer key is not independent verification. If the content boundary changes, revise the knowledge pack before regenerating dependent material.
Run a cross-artifact review 8 suggested min
Check matching task labels, quantities, units, definitions, directions, and version labels. Walk through every reference: 'see task H2' must point to an existing task. Open the learner copy and confirm no teacher answer or drafting note leaked into it. Solve the exit check separately. Hold inconsistent content or incomplete directions.
Package a checked release 4 suggested min
Mark each item ready or hold, list the files in a short contents note, and identify the controlling packet version. Stop if a dependent answer is unresolved, the key no longer matches the handout, or a source lacks permission or support. Keep a rollback copy of the previous checked version. This website does not collect classroom files.
Copy-ready prompt
Replace the placeholders with public, teacher-authored or invented material. Keep personal information out of the prompt.
Help author a small lesson-material packet for teacher review. Goal and lesson length: [goal/time] Bounded knowledge pack: [original checked definitions, facts, assumptions, source links, and exclusions] Artifact contract: [required outputs, audience, stable task labels, version] Use only the approved content boundary. List missing information instead of inventing it. Draft in order: teacher lesson brief; learner handout with labeled tasks; teacher-only worked key; fresh exit check and separate key. Explain how each task serves the same goal. Keep teacher answers out of learner copies. End with a cross-artifact checklist covering labels, numbers, units, source support, answer consistency, and version. Treat all outputs as drafts until I independently solve the tasks and approve each artifact. Do not include learner records, claim standards alignment without a supplied standard, or claim this packet was classroom-tested.
Invented example · not an outcome claim
Synthetic worked example
Context: An invented data lesson shares one content boundary. Version labels do not establish validation.
Input: Knowledge pack KP1: goal, calculate an arithmetic mean and explain its equal-share meaning. Definition, mean = sum of values ÷ number of values. Toy data only; no actual learner results. Units, counters. Required assumptions, count all supplied values, including zero when present. Exclusions, no claims about real populations or median. Packet version 1.0. Lesson length 20 minutes.
Example output
- Artifact P1, teacher brief: 3 minutes recall equal sharing; 5 minutes model 2, 4, 6 counters as 12 shared equally among 3 groups; 6 minutes attempt H1 and H2; 4 minutes complete E1; 2 minutes transitions. Explain that equal redistribution preserves the total. Materials: drawn counters or paper; no student AI account.
- Artifact H, learner handout: H1, 'Three groups have 3, 5, and 7 counters. Find the mean. Show the total and number of groups, then explain the equal-share amount.' H2, 'Four groups have 0, 4, 4, and 8 counters. Find the mean and explain whether the empty group counts.' These are complete tasks with enough information to solve.
- Artifact K, teacher-only key: H1, 3+5+7=15; 15÷3=5 counters per group. H2, 0+4+4+8=16; 16÷4=4 counters per group. The zero is one supplied group and belongs in the count. Dividing 16 by 3 would answer a different question. A drawing is acceptable if it preserves totals and group counts.
- Artifact E, learner exit check: E1, 'Four groups have 1, 3, 5, and 7 counters. Find their mean and show an equal-share explanation.' Teacher-only E1 key, stored in K: sum 16, count 4, mean 4 counters per group; redistribute 3 from the 7-group and 1 from the 5-group to fill the groups starting at 1 and 3.
- Consistency review: P1 names H1, H2, and E1, which all exist; H and K use the same values; every quantity uses counters; timing totals 20 minutes; KP1’s zero condition is exercised by H2. Keep K teacher-only, including its E1 answer. Release contents: P1, H, K, E, all packet version 1.0.
- Change rehearsal: if H2 changes to 0, 4, 4, 12, update K to sum 20 and mean 5, then recheck all references before release. Changing the handout alone invalidates the old key; matching version labels cannot repair the mismatch.
The human decision: Approve a packet only after checking every dependency and opening the learner copy. Keep unresolved source material and teacher-only answers outside the learner handout.
Teacher-owned checks
- Is the knowledge pack small, permitted, checked, and free of learner information?
- Does each artifact serve the same goal and use the controlling version?
- Do all cross-references resolve to matching task labels and values?
- Have I independently solved both practice and exit tasks?
- Are teacher answers and drafting notes absent from learner copies?
Measure this attempt
Record artifacts completed, consistency defects found, keys independently checked, and total authoring plus checking time. A packet with four files and two unchecked keys is not a finished packet. These counts do not establish classroom effectiveness.
Repeat deliberately
When revising, change the knowledge pack first if the content boundary changes, then list affected artifacts and rerun their checks. Retain the previous checked version until the replacement passes. Add artifacts only for clear teaching needs.
Adapt the method
- For reading, use a short original passage, permitted source locations, question IDs, and teacher notes describing acceptable evidence.
- For science, include units, conditions, and verified safety constraints; do not invent experimental results.
- Low-prep version: pair one learner task with a separate checked key.
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.
- Guidance for generative AI in education and researchUNESCO
Supports: UNESCO emphasizes human agency, data protection, and educational and ethical review of generative AI use. These principles inform the toolkit’s adult-led use and verification boundaries.
Limit: Policy guidance does not validate these prompts, certify a particular tool, or establish compliance with local rules.
- Organizing Instruction and Study to Improve Student LearningInstitute of Education Sciences, What Works Clearinghouse
Supports: The guide includes worked examples alongside problem solving and links between representations. These inform selected planning choices; the original lesson and packet are authored here.
Limit: This guidance does not evaluate these prompts, examples, timings, or packets. It does not establish that an AI-authored plan improves 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.