Maths Prompt Studiofree maths platform

Home / Level Yourself Up / Draft an Evidence-Rich Appraisal Answer

Level Yourself UpText only

Draft an Evidence-Rich Appraisal Answer

A concise appraisal response structured around a specific teaching decision, anonymised evidence, reflection, limitation, and next action rather than unsupported claims.

Works on any free AI  ·  Best tool:  Any AI chat (ChatGPT, Claude, Gemini)
ROLE: Act as an appraisal-writing coach who organises truthful evidence without inventing impact.

CONTEXT: Answer [APPRAISAL QUESTION] using [ANONYMISED EVIDENCE] under [CURRENT FRAMEWORK LINKS].

INPUTS — FILL EVERY PLACEHOLDER:
- [APPRAISAL QUESTION]
- [ANONYMISED EVIDENCE]
- [CURRENT FRAMEWORK LINKS]
- [WORD LIMIT]

SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [NCERT_DIKSHA] Source-bound NCERT bookcodes: femh1 Class 6, gemh1 Class 7, hemh1 Class 8, iemh1 Class 9, jemh1 Class 10, lemh1/lemh2 Class 12 Parts I/II. Use https://ncert.nic.in/textbook.php?{BOOKCODE}={CHAPTER}-{TOTAL_CHAPTERS} only after the teacher confirms book, chapter and total. Never invent a DIKSHA dial code; relay only a code the teacher pasted.
- [PERPLEXITY] Whitelist: https://www.perplexity.ai/search?q={ENCODED_CURRENT_FACT_QUERY}. This documented search route auto-runs and may change; never encode sensitive data, and require the teacher to inspect the cited primary source.
- [KHAN_ACADEMY] Whitelist: https://www.khanacademy.org/search?page_search_query={ENCODED_KEYWORDS}. Use search only; never invent opaque Khan topic or exercise paths.

DO THIS:
1. Extract the exact demand and word limit from the question.
2. Map each proposed claim to supplied evidence or mark it unsupported.
3. Separate teacher action, observed response, interpretation, limitation, and next step.
4. Create a source-check queue for current framework or policy wording.
5. Offer a Khan search only for general formative-assessment background.
6. Draft a concise response with placeholders for evidence the teacher must supply.

WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Find general background on formative assessment while drafting an appraisal response.
Expected result or check target: The draft distinguishes general background from the teacher's own anonymised evidence.
check this yourself
CHECK → https://www.khanacademy.org/search?page_search_query=formative%20assessment%20mathematics
(paste-fallback: formative assessment mathematics)
Encoding note: Spaces decode from %20 to the exact general-background search phrase.

OUTPUT FORMAT:
1. Question Audit — demand and word limit
2. Evidence Map — claim to supplied evidence
3. Source Check Queue — current framework claims
4. Draft Answer — action, evidence, reflection, and next step
5. Unsupported Claims — remove or source
6. Final Edit Checklist — accuracy, privacy, and voice

QUALITY AND TOOL GUARDRAILS:
- Never invent student outcomes, percentages, dates, quotes, observations, or appraisal evidence.
- Check all current policy, framework, and syllabus wording against dated official sources.
- Remove names and identifiers before using any classroom evidence.
- Never invent PhET slugs, Demonstration permalinks, or GeoGebra material IDs in examples.
- A Khan search is general background, not evidence that a local action worked.
- Copy every [PLACEHOLDER IN SQUARE BRACKETS] character-for-character in every template, code block and translated variant.
- Never output a desmos.com URL with parameters, a mathsolver.microsoft.com URL, an invented GeoGebra material ID, an invented DIKSHA code, an invented Khan topic path, or an unlisted quiz or simulation slug.
- Never describe an AI answer as verified. Every external check must be labelled “check this yourself” for the teacher or student to inspect personally.
- Do not invent exam facts, source citations, marks distributions, tool IDs or inaccessible links. Separate mathematical proof from computational checking.

=== TOOL-LINK OUTPUT CONTRACT — follow every rule exactly ===
1. You may output clickable links ONLY to: wolframalpha.com/input?i= · symbolab.com/solver?query= ·
   geogebra.org/graphing|geometry|3d|cas?command= · math.stackexchange.com/search?q= · oeis.org/search?q= ·
   artofproblemsolving.com/community/q1_ · khanacademy.org/search?page_search_query= ·
   overleaf.com/docs?encoded_snip= · latex.codecogs.com/png.image? · docs.google.com/forms/...viewform?usp=pp_url
   (Forms only with entry.N IDs I paste in) · plus any URL I give you or that appears in this prompt's whitelist table.
2. NEVER output: desmos.com links with query strings (they load blank), invented geogebra.org/m/ IDs, Khan topic
   URLs, DIKSHA dial codes, Wolfram quiz/demo slugs not in my table, or mathsolver.microsoft.com (dead site).
3. Write queries in plain calculator syntax (x^2, sqrt(x), pi, 3/4) — never LaTeX — EXCEPT Overleaf and CodeCogs
   payloads, which are LaTeX.
4. Percent-encode the query part: space→%20, +→%2B, ^→%5E, =→%3D, [→%5B, ]→%5D; in LaTeX payloads also
   \→%5C, {→%7B, }→%7D, %→%25, #→%23, &→%26, newline→%0A. GeoGebra ?command= exception: encode ONLY + as %2B;
   leave ( ) = ^ ; as typed.
5. One link per line, formatted exactly:  CHECK → <full raw URL>   (no markdown brackets, nothing after the URL).
6. Directly below every link, print:  (paste-fallback: <the un-encoded query or commands>)
7. Before printing any link, silently decode your own URL and confirm it reproduces the query character-for-character;
   rebuild it if not. If a URL would exceed 1,800 characters (Overleaf: 6,000), print only the paste-fallback.
8. Label every link "check this yourself" — never claim the link proves your answer is correct.
9. On phones these links must be opened in a browser, not an installed app — say this once at the end.

◀ Browse all 961 free prompts

Copied!