Reviewed, classroom-ready AI prompt templates

Class newsletter to families (no student names)

A short recurring update on what the class is learning — collective, never individual.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Star of the month' style individual mentions creep in — collective-only is the rule

Duty roster structure (roles, not names)

A fair rotation structure you fill with names offline.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Structures only; colleagues' names are added offline in school systems. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Asks for staff names — the structure-only rule prevents it

Event notice for parents (slot-based)

The reusable notice template — fill five slots, review, send.

Template

School event notice for parents/guardians. Warm, respectful, ~{{WORD_CAP}} words, English and {{SECOND_LANGUAGE}} in parallel. Include: {{EVENT}}, {{DATE_DAY}}, {{TIME}}, {{WHAT_TO_BRING}}, contact: {{CONTACT_SLOT}}. No student names; no urgency pressure; nothing that assumes a two-parent household. Offer one shorter WhatsApp-style version too.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Invents the day-name for the date — check date/day pairing against a calendar · Adds 'refreshments will be provided' style commitments nobody made

Field-trip planning pack (consent template + logistics)

The consent-note template and logistics checklist for an outing.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version. School consent rules override the template — align with office requirements first.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Cost or timing invented if slots left vague — fill every slot before generating

Meeting agenda with timings and decision flags

Turn a topic list into a timed agenda with decisions-needed marked.

Template

A staff-meeting agenda from these topics: {{TOPIC_LIST}}. Total time {{TOTAL_MINUTES}} minutes. Assign realistic minutes per topic, order for energy (decisions early, information later), mark each item [DECISION] or [INFO], and add a 5-minute AOB slot. No names attached to items; a one-line purpose per item.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Uniform minutes per item regardless of weight — adjust before circulating

Meeting summary from your own notes (names removed)

Structure your typed, de-named notes into decisions / actions / owners-by-role.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version. The 'nothing added' rule matters most here — summaries must not invent agreements.

Privacy: Remove all names before pasting; use roles ('sports in-charge'). Confidential meetings are not summarised in external tools at all. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Invents an action nobody agreed — compare every line against your notes

One-page staff summary of a circular

Reduce a non-confidential circular to obligations, deadlines and who-does-what.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version. Verify every deadline against the original — paraphrased dates are how deadlines get missed.

Privacy: Public/non-confidential circulars only. Confidential documents never enter external tools. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Paraphrases deadlines — the verbatim rule exists for this

Personal professional-development term plan

Turn two or three growth goals into a term plan with checkpoints.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Actions that assume free time you don't have — the fits-inside-work rule

PTM invitation (bilingual, guardians-inclusive)

The parent-teacher meeting invitation with slot times and gentle framing.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version. Back-translate the second language to verify rule parity (Module 7 habit).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Summons tone in translation — the partnership framing must survive both languages

Report comment structures by performance band (no students)

Sentence frames per band you personalise offline — identities never enter the tool.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version. Personalisation happens in your own document, never in the tool.

Privacy: Patterns only — no names, no identifiable performance data. Personalise offline. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Structures too generic to personalise — the three-sentence shape keeps them useful

Resource inventory formatter

Turn a rough list into a reorder-ready inventory table.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Invents quantities for vague entries — vague entries should surface as notes

Routine checklist (lab day, exam day, event day)

A before/during/after checklist for any recurring operational day.

Template

A {{DAY_TYPE}} checklist for a teacher: BEFORE (preparation items), DURING (monitoring items), AFTER (closure items) — one line each, checkbox format, max {{ITEM_CAP}} items total, ordered by time. Specific to: {{CONTEXT_DETAILS}}. No generic filler ('be prepared') — every item is a checkable action.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Generic filler items — 'checkable action' is the bar

Substitute-teacher handover sheet (no student data)

Everything a substitute needs to run your class — routines, not records.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Behaviour histories and named seating charts never enter external tools. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Tempted to add 'watch out for…' student notes — those stay verbal/in school systems

Transform an unsafe admin prompt (three-grade check)

Audit your own intended prompt before sending — including the no-AI verdict.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version. The strictness instruction matters — a lenient audit defeats the purpose.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Suggests cosmetic anonymisation for red substance — the three-grade framing prevents it

Weekly admin batching plan

Design your own 30-minute weekly green-task batch with saved templates.

The full template and filled example are available with a premium plan.

Review: Pre-send review: every date/day/time/amount checked against the source; no unauthorised commitments; no personal data; the sent version is the reviewed version.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Marking or student-data tasks sorted green — the sorter must stay strict

Assertion–reason items (board format)

Fact-cause connection items in the standard four-option board pattern.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Reasons' that are true but unrelated — check the causal link is real

Blueprint-driven question paper

A full test built row-by-row from an outcome/level/marks blueprint.

Template

{{BOARD}} Class {{CLASS}} {{SUBJECT}}, chapter(s) {{CHAPTERS}}. Build to this blueprint: {{BLUEPRINT_ROWS}} (each row: outcome — item count — type — difficulty — marks). Plus one misconception item targeting {{KNOWN_MISCONCEPTION}}. Answer key with one-line reasoning per item, items labelled by outcome and cognitive level. Syllabus notation only; distractors must be plausible errors, never jokes; I verify every key. Flag your least-confident item.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Ignores the blueprint totals — recount marks before use · Key errors — solve every item

Case-based question set with stimulus

A short stimulus (data/situation) with 2–3 questions sampling different levels.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Questions answerable without the stimulus — the 'everything needed' rule cuts both ways

Clear exam instruction block

Unambiguous, student-tested instructions for any paper (bilingual optional).

The full template and filled example are available with a premium plan.

Review: Rule-identical is the bar for bilingual instructions; check the back-translation line by line.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Any three' becoming 'the three' in Hindi — the back-translation exposes it

Error-identification items (find and fix)

Students find, name and correct planted errors — assessment as analysis.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Multiple accidental errors per item — verify each has exactly one

Feedback drafts from anonymised patterns

Encouraging, specific feedback language from performance patterns — never pasted student work.

Template

Task: {{TASK}}, rubric criteria: {{CRITERIA_LIST}}. For each of these anonymised performance patterns, draft feedback (two strengths, one next step, encouraging tone, ≤60 words each): {{PATTERN_LIST}}. Address the work, not the person; next steps must be actionable this week. I will personalise offline.

Review: Feedback drafts are language, not judgement — the level/mark is read from the work by you.

Privacy: Describe performance patterns only. Never paste identifiable student work into a public tool. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Generic next steps ('work harder') — actionable-this-week is the bar

Marking moderation pack for a subjective question

Anchor answers at each level so two markers award the same marks.

The full template and filled example are available with a premium plan.

Review: Verify the anchors' mark breakdowns against your marking points; adjust to your board's conventions.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Anchors too polished — 'real student writing' is the instruction that matters

MCQs with error-based distractors

MCQs where every wrong option encodes a real, named student error.

Template

Class {{CLASS}} {{SUBJECT}}, outcome: {{OUTCOME}}. {{ITEM_COUNT}} MCQs where each wrong option encodes a REAL error a student makes — after each item, one line naming the error each distractor represents. No joke options, no 'all of the above'. Answer key; I verify. Difficulty: {{DIFFICULTY_MIX}}.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Distractors drift into implausible options — the named-error line exposes this

Oral presentation rubric (content/delivery split)

Separate content and delivery criteria so neither hides the other.

The full template and filled example are available with a premium plan.

Review: Behaviour-only descriptors protect shy students with strong content — verify none reference personality.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Confident delivery' style descriptors sneaking in — behaviour only

Parallel forms of an existing question

Same skill, same difficulty, new surface — for retests and practice banks.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Difficulty drift in variants — the invariants line lets you check the claim

Peer-assessment protocol (two stars and a wish)

Structured peer feedback anchored to criteria, kept about the work.

The full template and filled example are available with a premium plan.

Review: The lazy example teaches more than the strong one — keep both.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Starters drift to person-comments — the work-only rule is explicit

Post-remediation recheck (new surface + transfer)

A recheck that distinguishes a rebuilt model from memorised practice.

The full template and filled example are available with a premium plan.

Review: Pre-commit your three decisions (mastered/partial/unmoved) before administering — evidence should meet a plan.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Reused practice contexts — the new-surface rule is what makes this evidence

Practical activity checklist (binary steps)

Procedure marking as observable yes/no steps; rubrics stay for quality.

The full template and filled example are available with a premium plan.

Review: Verify step order against the prescribed manual; checklists mark procedure, never understanding.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Steps that aren't observable ('understands the aim') — binary visible actions only

Project rubric with observable descriptors

A rubric two markers would apply identically, plus a student-language version.

Template

Class {{CLASS}} project: {{PROJECT_DESCRIPTION}}. A rubric with {{CRITERIA_COUNT}} criteria ({{CRITERIA_LIST}}), {{LEVEL_COUNT}} levels each, and OBSERVABLE descriptors per cell — something a reader could point to in the work, no adjectives without evidence. Plus a student-language version of the same rubric. Flag any descriptor two markers could still read differently.

Review: Test-score one imaginary strong and one weak submission: if you hesitate on a cell, iterate that descriptor.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Adjective descriptors ('good understanding') — the observability rule catches them

Short-answer items with marking keys

Short-answer questions with point-wise expected answers for consistent marking.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Marking points that overlap — each point must be independently creditable

Single misconception-revealing item

One diagnostic item whose wrong options each map to a named wrong model.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Options that fit multiple models — each must map to exactly one

Six-defect audit of an existing test

Audit any test (AI- or human-made) for the six defect classes before students sit it.

The full template and filled example are available with a premium plan.

Review: The AI's audit is a second pair of eyes, not the verdict — you confirm each finding; you solve the items too.

Privacy: Paste only the test content — never student responses or marks. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Misses key errors — this audit supplements, never replaces, solving items yourself

Student self-assessment (I-can + evidence)

Outcome-wise 'I can' statements with an evidence line, in student language.

The full template and filled example are available with a premium plan.

Review: The evidence line is the point — check it survives; without it self-assessment is mood-reporting.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Statements in teacher language — the read-alone test catches this

Ungraded diagnostic before a new unit

Surface prior knowledge and misconceptions before teaching, without marks.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Reads like a test — the friendly framing must survive into the items themselves

Concept-essential story for reading aloud

A story where the concept drives the plot — with discussion bridge questions.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held. Apply the test: does the story fail without the concept?

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Concept as decoration — the story-fails-without-it test · Moralising last line sneaks in

Creative writing task with productive constraints

Constraints that spark originality instead of limiting it.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held. The no-model-answer rule protects originality — resist adding one.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: A 'sample' creeps in — the local-anchor + no-model rules are the safeguards

Cross-age teaching project (older students make for younger)

Older students design learning materials for a younger class — authentic audience.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Frame too prescriptive about the product — format choice is the students' design decision

Debate kit with asymmetric briefing packs

A contestable motion with different evidence per side — argument becomes necessary.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held. Verify both packs' evidence against the textbook; check the packs genuinely differ.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Symmetric packs — the flop rebuilt; check evidence differs · Motions touching student identity — forbidden

Design challenge with trade-off constraints

Constraints that force choices; testable success criteria; reflection on trade-offs.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Criteria that need teacher opinion — 'testable' means measurable

Gallery/museum walk with artefact cards

Stations of source/artefact cards with observation prompts — analysis on foot.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held. Verify any textbook-based source against the book; label fictional sources as fictional.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Invented 'historical sources' presented as real — fictional must be labelled

Inquiry stimulus pack (scenario + anomaly + open questions)

Start an investigation without resolving it — conclusions forbidden.

Template

Class {{CLASS}} {{SUBJECT}}, topic {{TOPIC}}. Produce an inquiry stimulus pack: a one-page fictional scenario, a data table with ONE planted anomaly ({{ANOMALY_HINT}}), and three genuinely open investigation questions. NO conclusions, no explanation of the anomaly, no model answers anywhere in the output. Fictional setting only. Tell me where you were most tempted to explain too much.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held. Check the anomaly is discoverable by a student at this class level.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Answers leak into the questions — audit with the I-slot confession · Anomaly too subtle for the class level

Investigable vs non-investigable question sort

Teach students what makes a question testable — with a sorting deck.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Categories printed on the cards — the sort must be the students' thinking

One-pager synthesis task (visual + verbal)

End-of-unit synthesis on a single page mixing sketch, quote and connection.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Artistic quality' sneaks into criteria — completeness and own-words only

Project frame (driving question to exhibition)

The full PBL frame: question, milestones, roles, criteria, exhibition.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Driving question too broad to own — it should fit in one sentence a student would say

Simulation with private role sheets and scenario clock

A decision-rich role-play with timed injects and a debrief that lands the learning.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Roles with no real decisions — private sheets must create genuine tension · Debrief dropped for time — it IS the lesson

Socratic question ladder (questions only)

Five questions from observation to principle, no answers included.

Template

Class {{CLASS}} {{SUBJECT}}, concept: {{CONCEPT}}. A five-question Socratic ladder from concrete observation to underlying principle: question 1 asks what students can directly observe/recall; each later question requires the previous answer; question 5 reaches the principle. QUESTIONS ONLY — no answers, no hints in brackets. Plus one line for me: where students most often get stuck on this ladder.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Later questions answerable without the earlier ones — the chain must be real

Structured brainstorm protocol (quantity before judgement)

A class ideation session with rules that protect wild ideas.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Protocol collapses into open discussion — the phases and script keep structure

Teach-back activity design (students as explainers)

Students prepare and deliver a micro-lesson to peers — deepest practice there is.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Planning card so detailed it writes the explanation — cards prompt, never script

What-if scenario set for discussion

Counterfactuals that stretch understanding beyond the textbook case.

The full template and filled example are available with a premium plan.

Review: Check the output contains NO conclusions or model answers where students must think; fictionalise any real-community setting; verify the stops-here line held.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: What-ifs needing untaught content — 'answerable from the taught concept' is the boundary

Accessibility-first format of a handout

The same content rebuilt with named accessibility features.

Template

{{BOARD}} Class {{CLASS}} {{SUBJECT}}, handout: {{HANDOUT_TOPIC}}; same content, two formats. Format A standard; Format B accessibility-first: sentences under {{WORD_LIMIT}} words, one instruction per line, numbered sections, key terms bolded once with margin glosses, an alt-text line for every image carrying its teaching point, tables with a single header row and a one-line summary. Conceptual level constant — simplify syntax, not the content. List the accessibility choices you made so I can verify each.

Review: Verify each named feature actually appears — AI sometimes acknowledges a feature without applying it. Offer Format B to everyone, unlabelled.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Concept watered down instead of syntax — the golden constraint must be stated · Alt text describes appearance, not the teaching point

Assessment presentation accommodations (same construct)

Reformat a test's presentation for access while measuring the same thing.

The full template and filled example are available with a premium plan.

Review: The construct is sacred: presentation changes, measurement does not. Verify item-by-item.

Privacy: Paste only the test content. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Simplifying a word problem changes the skill measured — check the confirmation lines

Bias audit of a support version

Run the five failure patterns on an adaptation before it reaches students.

The full template and filled example are available with a premium plan.

Review: The dignity test is final: if the adaptation would embarrass the student it serves, it has failed.

Privacy: Paste only the material — never information about the students it is for. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The audit softens findings — ask for one finding per pattern minimum

Choice board for one outcome

A 3×3 grid of task choices at mixed depths, all serving the same outcome.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Some cells drift off-outcome — every task must evidence the same goal

Concrete-pictorial-abstract ladder for a maths concept

The same concept staged through objects, drawings, then notation.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Jumps to notation early — the bridge sentences are the point

Context-diversification pass on existing material

Rewrite word problems/examples so contexts include all your students.

The full template and filled example are available with a premium plan.

Review: Check the change-flags: the demand must be untouched; your students' own context should appear first.

Privacy: Paste only your own teaching material. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Changes the numbers along with the names — 'demand identical' is the rule

Dyslexia-friendly reading passage

A reading passage restructured for decoding ease at the same content level.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page. Offer to the whole class — decoding-friendly structure helps everyone.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Simplifies the geography along with the sentences — watch the substance

Early-finisher extension menu

Depth-adding extensions anyone may attempt — not just 'toppers'.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Extensions introduce next chapter's content — 'no new topics' is the boundary

Language-supported version for EAL/ESL learners

Same task with pre-taught vocabulary, simplified syntax and glosses — same concept level.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page. Verify glosses against the textbook's own terminology.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Content demand drops with the language — state 'same conceptual level' explicitly

Low-stakes participation structures for reluctant students

Participation formats that let hesitant students contribute safely.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Structures that still spotlight individuals — the no-forced-answer rule is the test

Multigrade classroom parallel plan

One period serving two grade groups with alternating teacher attention.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page. Test the self-running work: could a student complete it with zero teacher input?

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Self-running' work that needs the teacher — the worked-example-on-sheet rule prevents this

Paired-reading roles for mixed abilities

Reader/coach role cards so pairs support each other without stigma.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Coach card becomes a corrector card — 'only when asked' is the discipline

Scaffolded writing frame (fading support)

Sentence starters and paragraph frames that fade towards independence.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Starters that contain the answer — the structure/idea line matters

Three same-goal tiers of one worksheet

Support, standard and extension versions that stay discussable together.

Template

{{BOARD}} Class {{CLASS}} {{SUBJECT}}, worksheet on {{TOPIC}}; same outcome for every version: {{OUTCOME}}. Three same-goal versions: one with a word bank and sentence starters, one standard, one with an extension that DEEPENS ({{EXTENSION_DIRECTION}}). Same core questions in all three so the class discusses together; no version labelled by ability anywhere on the page. Tell me which version you are least confident pitches right.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Support tier quietly loses the analysis question — check the goal survived · Extension adds length, not depth

UDL options for one lesson (engage / represent / express)

Multiple means of engagement, representation and expression for the same outcome.

The full template and filled example are available with a premium plan.

Review: Check the goal survived in every version (same core questions); read all tiers aloud for equal-respect tone; no ability labels on any student-facing page.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The three expression routes get different difficulty — shared criteria keep them equivalent

Analogy bank for a hard concept

Three analogies with their breaking points, to choose deliberately.

The full template and filled example are available with a premium plan.

Review: Verify each mapping is faithful; plan to state the breaking point to students when the analogy retires.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Omits the breaking points — they are the safety feature; demand them

Closure routines beyond the exit ticket

Three closure options producing readable evidence in five minutes.

The full template and filled example are available with a premium plan.

Review: Pick one; the strong/weak descriptors become your quick marking guide.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Vague strong/weak descriptors — demand observable ones

Cross-subject connection segment

A ten-minute segment linking today's topic to another subject authentically.

The full template and filled example are available with a premium plan.

Review: Verify the other-subject content at its own textbook level.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Forced links — respect the 'flag if weak' instruction

Double-period / block lesson plan

A longer block with an energy reset in the middle.

The full template and filled example are available with a premium plan.

Review: Verify facts and terminology against the prescribed textbook; check timings sum to your period; confirm materials exist in your room.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Second arc becomes a lecture — insist it is application, not more explanation

First lesson of the year (norms + diagnostic)

Opening period that sets routines and quietly surfaces prior knowledge.

The full template and filled example are available with a premium plan.

Review: Check the diagnostic items map one-per-topic so your tally is meaningful.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Diagnostic feels like a test — the 'game' framing must survive in the actual items

Five-minute spiral recap of older material

Daily spaced review: three quick items from past chapters to open any lesson.

Template

Class {{CLASS}} {{SUBJECT}}. A 5-minute opening recap of three items: one from last lesson, one from {{WEEKS_AGO}} weeks ago ({{OLDER_TOPIC}}), one from earlier in the year ({{OLDEST_TOPIC}}). Oral or slate-based, no printing. Include the expected answers. Items must be recall-or-one-step — this is retrieval, not a test.

Review: Verify the answers; keep it genuinely under five minutes.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Items too hard for a warm-up — recall-or-one-step is the bar

Guided practice set with fading support

Four to six items that fade from fully-scaffolded to independent.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Fading too fast — check the middle items genuinely carry one hint

Homework set that extends (not repeats) the lesson

Short homework that practises today's skill plus one connection question.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Creeps past 20 minutes — count minutes per item

Lab/practical session plan with safety steps

A practical period with stations, safety notes and a results table.

The full template and filled example are available with a premium plan.

Review: Procedure must match the prescribed manual exactly — verify against it; check apparatus counts against your lab stock.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Invents apparatus your lab lacks · Procedure drifts from the prescribed manual — verify line by line

Lesson hooks (three options)

Three different openings for the same lesson, to choose by class mood.

The full template and filled example are available with a premium plan.

Review: Verify facts and terminology against the prescribed textbook; check timings sum to your period; confirm materials exist in your room.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Hooks that answer the lesson question — the no-conclusion rule matters

Lesson plan with built-in support and stretch

One plan whose activity phase carries a support scaffold and an extension.

The full template and filled example are available with a premium plan.

Review: Verify facts and terminology against the prescribed textbook; check timings sum to your period; confirm materials exist in your room.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Stretch becomes 'more of the same' — check it deepens

Revision lesson with retrieval practice

A pre-exam revision period built on retrieval, not re-teaching.

The full template and filled example are available with a premium plan.

Review: Solve every item yourself before trusting the key; check each item maps to a taught outcome; run the six-defect audit (ambiguity, keys, difficulty honesty, context bias, distractors, curriculum match).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Quiz skews to one chapter — demand an even mix

Story-based lesson for younger classes

A concept smuggled into a story, with the concept essential to the plot.

The full template and filled example are available with a premium plan.

Review: Read aloud once; check the concept truly drives the plot and the questions bridge to it.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Concept becomes decoration — the 'story fails without it' test catches this

Substitution-period standalone lesson

A zero-preparation, self-contained period for a class you don't normally teach.

The full template and filled example are available with a premium plan.

Review: Read the instructions aloud once before class; check the tiers genuinely differ.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Activity secretly requires subject knowledge — check you could run it cold

Teacher notes layer for an existing plan

Add timing warnings, questioning prompts and pitfalls to a plan you already have.

The full template and filled example are available with a premium plan.

Review: Your plan stays authoritative — accept notes selectively.

Privacy: Paste only your own plan content. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Rewrites the plan instead of annotating — restate 'without changing the plan'

Unit overview map (multi-lesson arc)

Plan a whole chapter as a sequence of connected periods before detailing any one.

The full template and filled example are available with a premium plan.

Review: Verify facts and terminology against the prescribed textbook; check timings sum to your period; confirm materials exist in your room.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Packs too much into early periods — check the load is even

Worked-example modelling script (think-aloud)

A board-ready worked example with the thinking said aloud at every step.

The full template and filled example are available with a premium plan.

Review: Verify facts and terminology against the prescribed textbook; check timings sum to your period; confirm materials exist in your room.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Script explains WHAT, not WHY — demand the 'because' sentence per step

Bilingual concept explanation (parallel columns)

The same explanation in two languages carrying identical facts.

Template

{{BOARD}} Class {{CLASS}} {{SUBJECT}}, concept: {{CONCEPT}}. A bilingual explanation, ~{{WORDS_PER_LANGUAGE}} words per language in parallel columns (English / {{SECOND_LANGUAGE}}), SAME facts in both — nothing extra in either. Technical terms per this policy: {{TERMINOLOGY_POLICY}}. Everyday register both sides. Then list every terminology decision you made in a table.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: One column gains a fact the other lacks — the same-facts rule is checkable line by line

Bilingual parent note (second language first)

Family communication led by the language parents read most comfortably.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: English column drafted first and Hindi squeezed to fit — the column order instruction resists this

Bilingual vocabulary table for a chapter

The chapter's key terms with textbook-aligned second-language equivalents.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use. Check flagged rows against the second-language textbook — invented coinages break exam alignment.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Sanskritised coinages no textbook uses — the flag-if-uncertain instruction surfaces them

Classroom glossary wall cards (three languages)

Printable term cards honouring the languages your students speak.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use. Have a speaker of each language check the flagged cards before printing.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Third-language equivalents invented — the flag-if-uncertain rule extends to every language

Five-error audit of a bilingual document

The full translation-review pass on any bilingual material before use.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use. The audit assists your judgement; a human reader of both languages makes the final call.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Script issues invisible in plain text — check the final printed/displayed medium too

Natural code-switching explanation (as a teacher speaks)

Mixed-language explanation matching real classroom speech.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use. Read aloud — if it doesn't sound like your classroom voice, adjust the register instruction.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Full translation instead of code-switching — 'as a teacher naturally speaks' is the instruction

Parallel bilingual worksheet (same questions, same spaces)

One worksheet both language groups complete identically.

Template

{{BOARD}} Class {{CLASS}} {{SUBJECT}}, topic {{TOPIC}}. A one-page worksheet in parallel English–{{SECOND_LANGUAGE}}: every instruction line bilingual, questions numbered identically, same answer spaces. Terminology policy: {{TERMINOLOGY_POLICY}} (e.g. technical terms stay in English with bracketed {{SECOND_LANGUAGE}} on first use). Same reading level in both languages — everyday register, not literary. Provide the terminology table (term / English / {{SECOND_LANGUAGE}} / decision) for my review.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Second language arrives more formal than the English — state the register · Terminology decisions made silently — demand the table

Reading-level parity fixer for a translation

Bring an over-formal translation back to the source's register.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Register fix drifts the meaning — the old→new diff is your check

Rule-identical bilingual exam instructions

Instruction blocks where both languages state exactly the same rules.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use. Check the back-translation line by line — 'any three' must round-trip as a choice.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: A choice becomes a command in translation — the back-translation exposes it

Second-language explanation with preserved English terms

Exam-critical terms stay in English exactly as the board paper uses them.

The full template and filled example are available with a premium plan.

Review: Run the three parity checks: back-translation for meaning drift, terminology table row-by-row, read-aloud for register. High-stakes bilingual content needs a human reviewer of both languages before use. Spot-check two preservation-report rows — trust, but verify.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: A term silently translated mid-text — the report makes it visible in seconds

Counterexample bank for a misconception

Three confrontations of different kinds, to choose the one your class feels.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Tells the failure instead of staging discovery — the question matters more than the example

Diagnose the wrong model behind an error pattern

Name candidate mental models producing a recurring wrong answer.

Template

Class {{CLASS}} {{SUBJECT}}. Frequent anonymised answer pattern: {{ERROR_PATTERN}}. Answer three things: (1) what underlying model(s) produce EXACTLY these answers, (2) the standard name for this misconception if one exists, (3) three diagnostic questions where each wrong option corresponds to a DIFFERENT candidate model — with an option-to-model map after each. Also say whether this is a true misconception or a normal developmental stage.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break. Verify the diagnostic option-model maps yourself.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Options that fit two models — each must map to exactly one · Skips the developmental-stage question — it changes everything

Four-part remediation pack (confront–rebuild–model–practise)

The complete targeted intervention for one named misconception.

Template

{{BOARD}} Class {{CLASS}} {{SUBJECT}}. Named wrong model: {{WRONG_MODEL}}. Produce four parts: (1) a CONFRONTATION — a counterexample where this model visibly fails; (2) a REBUILD — the correct model explained ≤{{REBUILD_WORDS}} words with one analogy at class level; (3) one worked example with the thinking said aloud; (4) {{ITEM_COUNT}} scaffolded practice items ordered from the confrontation to transfer, deliberately mixing items where the old rule coincidentally works with items where it fails. Answer key with reasoning; I verify key AND confrontation. Predict which practice item students will most likely still miss.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Practice items all have the new shape — mixing is what forces model choice · Confrontation too subtle to land — it must fail visibly

Grammar/language error pattern intervention

Noticing activities for language overgeneralisation (not error drills).

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break. Overgeneralisation is developmental — celebrate the rule-learning while noticing exceptions.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Prescribes drills for a developmental stage — the case distinction is the point

Home practice note after remediation (general, no data)

A general note to all families supporting the week's reteach — no individual data.

The full template and filled example are available with a premium plan.

Review: Goes to every family identically — check nothing implies who 'needed' the reteach.

Privacy: This note contains no student data by design — never adapt it per child in a public tool. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Wording that hints at strugglers ('some children…') — it goes to everyone, neutrally

Post-remediation recheck (new surface, old-model distractors, transfer)

The recheck that distinguishes a rebuilt model from memorised answers.

The full template and filled example are available with a premium plan.

Review: Pre-commit your three decisions before administering: mastered → spaced review in two weeks; partial → second confrontation with a DIFFERENT analogy; unmoved → re-diagnose (the hypothesis was wrong).

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Reuses practised contexts — memory then passes for mastery

Practice set at the failure point

Items that start exactly where the old rule breaks and force model choice.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: No coincidence items — without them students pattern-match the new procedure

Reteach lesson plan (different route, same outcome)

A second full lesson using a different representation than the first attempt.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Reteach becomes recap — starting from the confrontation prevents this

Second analogy after a failed rebuild

A structurally different analogy when the first one didn't land.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: 'Different' analogies that are the same image renamed — structural difference is the ask

Single-cause thinking intervention (humanities)

Move students from one-cause explanations to weighted multi-cause reasoning.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The web becomes decoration — the ranking + counterfactual do the cognitive work

Small-group remediation station (while class works)

A 15-minute teacher-led micro-session run alongside independent class work.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break. Rotate station membership across topics so no group becomes 'the weak group'.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Class task needs the teacher mid-station — the worked-example rule keeps it self-running

Spaced review items (two weeks after remediation)

Three-item spaced check that catches quiet reversion.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The embedded item's context swamps the skill — keep it one-step

Student error-analysis worksheet (fictional work samples)

Students diagnose planted errors themselves — remediation as analysis.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break. The fictional-student framing protects real students — never use real work here.

Privacy: All work samples are fictional by design — never paste real student work. Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The two flawed solutions blur together — the misconception vs slip distinction is the lesson

Which-model-is-it class quiz

A quick quiz whose distractor choices map the class's models for you.

The full template and filled example are available with a premium plan.

Review: Verify the counterexample and every answer key against the textbook — a wrong confrontation entrenches the misconception it was meant to break.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Options don't cleanly map to one model each — the tally becomes noise

Age and cognitive-load review

Is this really pitched at the class — reading level, concept load, example fit?

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Reading-level tools disagree with judgement — your knowledge of the actual class decides

Answer-key cross-check protocol

A second solving pass on a key — supplementing (never replacing) your own.

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. This is a SECOND pass: your own solving pass still happens; disagreements resolve against the textbook, never the AI.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Both the key and the check can share the same error — the textbook is the referee

Bias and inclusion audit of teaching content

Who appears, who is missing, who always leads — audited before students see it.

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. Your students' own context appears first in the corrected version — check the flags.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Over-correction into tokenism — variety should read naturally, not as a checklist

Extract every citation for manual lookup

A lookup-ready list of all references in a document — fakes look perfect.

Template

Extract every citation, reference, statistic and named source from this content into a lookup table: source as stated / the claim it supports / where I could check it (textbook, official site, library). Do NOT tell me whether they are real — formatting cannot prove existence; I will look each one up. Flag vague attributions ('studies show', 'experts say') separately as unverifiable-as-stated. Content: {{PASTE_CONTENT}}

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. A fake reference is worse than none: look up or leave out.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The model asserts citations are real — the do-not-tell-me instruction keeps the judgement offline

Run the eight-step verification tree on content

Structured claim/source/age/bias/objective review of any AI output.

Template

Run a verification review of this content for Class {{CLASS}} {{SUBJECT}} (objective: {{OBJECTIVE}}): (1) list every FACTUAL CLAIM it makes, (2) for each claim, state how I could verify it against the textbook or an official source (do NOT verify by your own confidence), (3) list every citation/source it names — I will look each up, (4) age-appropriateness concerns, (5) bias/exclusion concerns (who appears, who is missing), (6) does it meet the objective? End with your uncertainty list: the claims you are least sure of. Content: {{PASTE_CONTENT}}

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. The tree assists; the lookups and the verdict are yours.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The AI 'verifies' its own claims confidently — the do-not-verify-by-confidence instruction blocks this framing, but the lookups remain yours

SAFE review record for one output

The documented review that makes approval a decision — capstone evidence format.

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. The blank judgement lines are the design: the record documents YOUR decision.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: The AI fills in the verdicts — the blank-lines instruction keeps judgement human

Score a prompt on the 10-point SATHI scorecard

Diagnose a weak prompt before regenerating — every flaw maps to a slot.

Template

Score this prompt on the SATHI scorecard — two points per slot (present? specific?), 10 total: S situation/subject, A audience/ability, T task/format, H human checks/boundaries, I iterate/improve. For each slot scoring under 2: name the missing element and write the one-line addition that fixes it. Then diagnose the overall disease if any: ambiguity / missing context / overconstraint. Prompt: {{PASTE_PROMPT}}

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Generous scoring — ask for the fix lines regardless; they are the useful output

Source-quality ranking for a topic

Which sources should anchor teaching content — ranked with reasons.

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. The prescribed textbook wins for exam alignment even where richer sources exist.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Web sources ranked above the prescribed text — exam alignment is the tiebreaker

Three-version output comparison

Deliberate iteration: compare outputs from prompt versions and attribute differences.

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. Save the version you approve — approval belongs to a version, not a prompt.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Attribution guesswork if you changed multiple things per version — one change per version keeps it clean

Weekly verification drill (planted-error passage)

Keep your verification eye sharp with a self-test — errors disclosed after.

The full template and filled example are available with a premium plan.

Review: Verify against real sources, never the AI itself; look up every citation; the approve/revise/reject verdict is recorded and yours. A teaching drill for you — never present the passage to students as real content.

Privacy: Never include student names, identifiable marks, health, family or community details. Describe situations and needs, never children.

Known failure modes: Planted errors too obvious — ask for 'subtle' if the drill stops challenging you