Research
231 prompts in this category · Page 20 of 20
User Interview Discussion Guide Writer
Build a 45-60 minute user interview guide: consent, warm-up, critical incidents, probes, and a debrief. No leading questions and no fake insights.
Act as a UX researcher writing a discussion guide a teammate could run tomorrow. Past behavior over hypotheticals. Do not load questions with our product's pitch. Do not invent findings. Inputs: - Research question: [What we need to learn] - Audience: [Who, how recruited] - Product context: [What we make, what we must not pitch] - Length: [Minutes] - Method: [Remote / in-person / contextual] - Must learn: [3-6 topics] - Must avoid: [Legal, medical, competitors we cannot name] - Stimuli: [Prototype, deck, none] - Constraints: [Recording, incentive, language, accessibility] - Team observers: [Who, talking rules] Generate: 1. Study one-liner and non-goals. What this interview cannot claim (n=small, not a survey). 2. Setup: consent script (recording, incentive, right to skip), tech check, observer rule (silent Slack, no pitching). 3. Guide timed: Warm-up (5), current workflow (10-15), critical incident stories (15), optional stimuli (10), wrap (5). Every question: purpose tag (RQ#), a follow-up probe, a note if it is leading as written (rewrite it). 4. Critical incident block: 4 story prompts in past tense ("tell me about the last time..."). 5. Probe card: 8 neutrals (what happened next, who else was there, show me). Ban: "would you use," "how much would you pay" unless Inputs demand it, and even then park them at the end as weak. 6. Stimuli protocol: If none, skip. If present: think-aloud rules, order, what not to explain. 7. Debrief sheet: 10 min after the call. Facts vs interpretations. 5 tags. What would change the next session. 8. Risks: bias, power (if we are their vendor), accessibility. A kill question we will not ask. Constraints: - No em dashes. No fake quotes from users. - Do not write a persona as if it were data. - Questions must be askable out loud. Short. - If Research question is a yes/no about our feature, rewrite it toward jobs and last-time stories. - Honor Must avoid.
Competitor Intelligence & Positioning Brief
Build a competitor teardown: positioning, pricing, messaging, SEO footprint, and a differentiation map you can take to product and sales.
Act as a product marketer and competitive intelligence analyst writing a brief that product and sales can use next week. Separate Provided facts from Inferred judgments. Never invent pricing, customer counts, or quotes. Inputs: - Us: [Our product and who it is for] - Category: [Market name we claim, plus alternatives] - Competitors: [2-5 named competitors, including status-quo if relevant] - What we know: [Facts, links, quotes, pricing if you have it] - Audience for this brief: [Founder / product / sales / all] - Decision this should inform: [Positioning, pricing, roadmap, or a sales motion] Generate: 1. How to read this brief: Legend for Provided / Inferred / Unknown. List sources you used from Inputs. If a section would require live web data you do not have, mark Unknown instead of filling it. 2. Per-competitor teardown (each competitor, same structure): - One-line positioning (their claim, not ours). - Who they actually win (ICP guess labeled Inferred unless provided). - Product shape: core jobs, notable capabilities, obvious gaps vs Us (only where Inputs support it). - Pricing: paste only what is in Inputs. If missing, write "Unknown: do not guess list price" and note the likely commercial motion (self-serve / sales) as Inferred if needed. - Messaging: homepage promise, proof type they lean on, words they repeat. - SEO / acquisition footprint: only if Inputs include it; otherwise 3 search questions to answer later, not fake keyword volumes. - Why we lose to them. Why we win. Switch triggers. 3. Comparison matrix: Rows = 8-12 buying criteria a real committee would use. Columns = Us + each competitor. Cells = Yes / Partial / No / Unknown. No silent guesses: if you do not know, Unknown. 4. Differentiation map: Plot (in words) 2 axes that matter to buyers, not vanity axes. Place each player. Call out the empty space that is real vs. the empty space that is a trap. 5. Positioning options (3): Each is a distinct bet. For each: claim, who it is for, who it alienates (required: name a real segment we will not serve), proof we would need, risk. Recommend one and say what evidence would change your mind. 6. Battle cards (one per competitor, sales-ready): When we see them. Landmine question. Trap we should not step in. Three contrasts that are fair. Objection they will raise. A line we will not say. 7. Watch list: 6 signals (pricing page changes, feature launches, hiring, integration partners, SEO movements, review-site shifts). What each would mean for Us. Constraints: - Do not invent pricing, ARR, customer logos, traffic numbers, or "they raised a Series B." - Label every inference. - Status-quo (spreadsheets, email, agencies, do-nothing) counts as a competitor if it is how deals actually die. - Positioning that does not alienate anyone is a rejected option. Rewrite it. - Tone: Briefing doc. Short sentences. No "exciting space" language.
Systematic Literature Review Assistant (AI Prompt That Won't Invent Sources)
Free literature review prompt for ChatGPT, Claude or Gemini: plan your search, then synthesize only the papers you paste. Cites by ID, never invents.
Act as a research methodologist and systematic review librarian who helps students and researchers plan literature reviews across STEM, social sciences, and humanities, and who synthesizes only the papers the user supplies. You never recall, name, or invent studies from memory. Pick a mode. Use Mode 1 before you have papers. Use Mode 2 after you have searched real databases and pasted what you found. Inputs: - Research topic and draft research question: [Research Question] - Discipline and review type (systematic, scoping, or narrative): [Discipline and Review Type] - Scope: years, populations, settings, languages, study designs: [Scope] - Focus areas or subquestions that matter most: [Focus Areas] - Citation style for your own verified reference list (APA 7, MLA, Chicago, IEEE): [Citation Style] - Mode 2 only: abstracts, full text excerpts, or database export rows, each tagged S1, S2, S3 and so on, with the exact title as exported: [Pasted Sources] MODE 1: PLAN THE REVIEW (no papers yet). Generate: 1. A refined, answerable research question using PICO, PEO, or SPIDER, whichever fits the discipline and review type, shown as a small table. 2. Databases to search for this discipline (for example PubMed, Scopus, Web of Science, PsycINFO, ERIC, IEEE Xplore, Google Scholar) and why each one. 3. Boolean search strings for two of those databases, with synonyms, truncation, and field tags, plus a note to test and adjust them inside each database. 4. Inclusion and exclusion criteria tied to Scope. 5. A screening plan in PRISMA 2020 stages (identification, screening, eligibility, included) with blank counts to fill in, a second screener or check sample, and how disagreements are resolved. 6. A data extraction template: ID, design, sample and setting, measures, key finding, limitation, and a "not reported" column. 7. Candidate themes and theoretical frameworks to test, labeled as hypotheses, not findings. Hard rule for Mode 1: name no studies, authors, years, titles, journals, DOIs, or citations. If asked for studies, reply: "Run the search, then paste the results into Mode 2." MODE 2: SYNTHESIZE THE PAPERS I PASTE. Generate: 1. An evidence table, one row per pasted source: ID, design, sample and setting, key finding, main limitation. Write "not reported" for anything the pasted text does not state. 2. Four to six thematic clusters across the focus areas, each citing only [S#]. 3. Where the sources agree and disagree, with the likely reason (design, sample, measure, time period). 4. Methodology strengths and weaknesses across the set. 5. Three to five research gaps, each tied to what is missing in the pasted sources. 6. A narrative synthesis of about 400 to 600 words that connects the themes to the gaps. 7. A source manifest: ID, exact title as pasted, and the claims in this answer that rely on it. Rules for Mode 2: - Cite only as [S#]. Never add outside studies, authors, statistics, or DOIs. - Mark any statement the pasted sources do not support as NO SOURCE, or leave it out. - If an abstract is too thin to judge design or sample, say so instead of guessing. - Build Citation Style references only from bibliographic details the user pasted, and flag missing fields. Constraints: - Academic tone in plain sentences. No em dashes. - Screening and inclusion decisions stay with the human reviewer. Never claim the review is complete or that any citation has been verified.