# AutoSurvey — Design a Survey with AI (AI-readable version) This is the plain-text, AI-optimized version of this guide. Human-readable version (same content, nicer layout): https://autosurvey.app/build-with-ai.html PURPOSE Help a user design survey questions that drop cleanly into AutoSurvey — a Salesforce app that turns a list of questions into a fully deployable survey (typed inputs, screens, conditional logic, and a Flow runtime). The creative "what to ask" work is done here by you, the AI; the user then pastes your output into AutoSurvey's in-app AI step (set to "Standard") or imports it directly. ================================================================================ STEP 0 — PICK YOUR PROMPT: FULL or LITE (self-select by your own capability) ================================================================================ There are two prompts below. Choose the one that matches your capability: - Use the FULL prompt if you are a capable frontier / flagship model. Full uses every control, including matrix grids, NPS, star, slider, and same-screen conditional (show-if) logic. Examples: ChatGPT GPT-4o / GPT-4.1 / GPT-5 / o-series; Claude Opus or Sonnet; Gemini 1.5 / 2.5 Pro or Advanced. - Use the LITE prompt if you are a smaller, faster, free, or older model. Lite keeps to the simple controls only — single choice, multi choice, Likert rating, and short/long text — which lighter models handle reliably. It omits matrix, NPS, star, slider, and conditional logic. Examples: ChatGPT free default / GPT-4o mini / GPT-3.5; Claude Haiku; Gemini Flash / Nano; small local models (Llama, Mistral, Phi). RULE OF THUMB: a paid flagship or reasoning model -> FULL; a free, "mini", "flash", or "lite" model -> LITE. (This mapping is a best guess and will be refined over time. If unsure, prefer LITE — a correct simple survey beats a broken advanced one.) ================================================================================ THE FULL PROMPT (copy from here to the next divider) ================================================================================ You are an expert survey designer. Design a complete, well-structured survey that I will build in AutoSurvey (a Salesforce app that turns a list of questions into a deployable survey). Follow AutoSurvey's capabilities and limits exactly, so your output drops in cleanly. MY SURVEY - Topic / goal: [DESCRIBE WHAT YOU WANT TO LEARN] - Audience / respondents: [WHO IS TAKING THIS] - Approx length: [E.G. 10-15 QUESTIONS ACROSS 2-3 SCREENS] - Must include: [ANYTHING REQUIRED, E.G. AN NPS QUESTION AND A COMMENT BOX] (If I left any of these blank, ask me before generating.) QUESTION TYPES YOU MAY USE (pick the best fit for each question) - NPS - the classic 0-10 "how likely are you to recommend..." question. Use AT MOST ONCE, only for true likelihood-to-recommend. No answer options needed. - Star rating - a 1-5 star rating for satisfaction or quality. No options needed. - Slider - a 0-10 slider for intensity or magnitude (effort, likelihood, strength). No options needed. - Matrix - 3+ items rated on the SAME scale, shown as a grid ("rate each of the following..."). Every row shares ONE grid title, ONE answer scale (option set), and ONE screen. - Rating (Likert) - a labeled 1-5 scale (agree/disagree, satisfaction) for a SINGLE item. Needs a named set of answer labels. - Single choice - pick exactly one option from a list. - Multi choice - "select all that apply". - Short text / Long text - open-ended single-line / paragraph input. Prefer NPS / Star / Slider / Matrix when a question genuinely fits that pattern (they make a richer survey) - but do not force them where a plain choice or scale is the honest fit. STRUCTURE RULES (must follow) - Group questions into a few logical screens (pages). Aim for 3-5 questions per screen, 7 maximum. Keep related rating/choice questions together; put optional open-text follow-ups at the end of a screen. - Screen names must be 35 characters or fewer. - Choice, rating, and matrix questions must come with a clear, sensible set of answer options. Give each option set a short NAME (e.g. "Satisfaction5", "CommunicationMethods") and reuse the same set whenever the scale is identical. - Conditional follow-ups (show a question only sometimes): a question may be shown based on an earlier answer ONLY IF the controlling question is a SINGLE-CHOICE question on the SAME screen, and the trigger is one of that question's options (operator "is" or "is not"). Cross-screen conditions are NOT supported - keep the controlling question and the dependent question on the same screen. Use this only for genuine branching (e.g. ask "What went wrong?" only when Satisfaction is "Dissatisfied"). WRITING RULES - One idea per question - no double-barreled questions. - Neutral, non-leading, professional wording. - No redundant or overlapping questions; progress logically from general to specific. - Keep the survey appropriately short. OUTPUT - give me BOTH of the following: (A) A numbered list, grouped by screen. For each question, show the question text, the answer type, and the answer options (when relevant). Mark any conditional question with "(show only if ...)". I will paste this into AutoSurvey's in-app AI step. (B) Two import tables. Questions table - columns, in this order: API Name | Question | Display Type | Screen | Section | Option Set | Required | Visibility | Help Text - Use these EXACT Display Type values: Text (short open text), Text Area (long open text), RadioVertical (single choice, up to 10 options), Picklist (single choice with more than 10 options), Checkbox (multi-select), RadioHorizontal (Likert 1-5), NPS, Star, Slider, Matrix. - Section is ONLY for Matrix rows (the shared grid title); leave it blank otherwise. - Option Set is the NAME of the answer set for choice/rating/matrix rows; leave it blank for Text, Text Area, NPS, Star, and Slider. - Required is TRUE or FALSE. Help Text is an optional one-line hint (leave blank if not useful). - Visibility (optional) expresses a same-screen condition as: ControllerApiName = 'OptionValue' (use != for "is not"). The controller must be a single-choice question on the same screen. - API Name: a short unique identifier using letters, numbers and underscores, starting with a letter (e.g. Recommend_Likelihood). - If a single- or multi-choice question needs an open-ended escape hatch, prefer an "Other (please specify)" choice over a separate text question: note it in output (A), and in the table add an "Allow Other" column set to TRUE on that row. Option Sets table - columns, in this order: Option Set | Label | Value | Order | Score - One row per option. Label is what the respondent sees; Value is the stored value (defaults to the Label if blank). Score is an optional number for analytics (e.g. 5,4,3,2,1 for a 5-point scale). Reuse the same Option Set name across questions that share a scale. Do not invent question types, Display Type values, or columns beyond those listed above. ================================================================================ THE LITE PROMPT (for lighter models — copy from here to the next divider) ================================================================================ You are an expert survey designer. Design a complete, well-structured survey that I will build in AutoSurvey (a Salesforce app that turns a list of questions into a deployable survey). Keep to the simple question types below - this version is tuned for lighter AI models, so do not use matrices, NPS, star, slider, or conditional (show-if) logic. MY SURVEY - Topic / goal: [DESCRIBE WHAT YOU WANT TO LEARN] - Audience / respondents: [WHO IS TAKING THIS] - Approx length: [E.G. 10-15 QUESTIONS ACROSS 2-3 SCREENS] - Must include: [ANYTHING REQUIRED] (If I left any of these blank, ask me before generating.) QUESTION TYPES YOU MAY USE (use ONLY these) - Single choice - pick exactly one option from a list. - Multi choice - "select all that apply". - Rating (Likert) - a labeled 1-5 scale (agree/disagree, satisfaction) for a single item. Needs a named set of answer labels. - Short text / Long text - open-ended single-line / paragraph input. Do NOT use matrices, NPS, star, slider, or conditional show-if logic. STRUCTURE RULES (must follow) - Group questions into a few logical screens (pages). Aim for 3-5 questions per screen, 7 maximum. Keep related questions together; put optional open-text follow-ups at the end of a screen. - Screen names must be 35 characters or fewer. - Every choice and rating question must come with a clear, sensible set of answer options. Give each option set a short NAME (e.g. "Satisfaction5") and reuse the same set whenever the scale is identical. WRITING RULES - One idea per question - no double-barreled questions. - Neutral, non-leading, professional wording. - No redundant or overlapping questions; progress logically from general to specific. - Keep the survey appropriately short. OUTPUT - give me BOTH of the following: (A) A numbered list, grouped by screen. For each question, show the question text, the answer type, and the answer options (when relevant). I will paste this into AutoSurvey's in-app AI step. (B) Two import tables. Questions table - columns, in this order: API Name | Question | Display Type | Screen | Option Set | Required | Help Text - Use these EXACT Display Type values: Text (short open text), Text Area (long open text), RadioVertical (single choice, up to 10 options), Picklist (single choice with more than 10 options), Checkbox (multi-select), RadioHorizontal (Likert 1-5). - Option Set is the NAME of the answer set for single choice, multi choice, and rating rows; leave it blank for Text and Text Area. - Required is TRUE or FALSE. Help Text is an optional one-line hint (leave blank if not useful). - API Name: a short unique identifier using letters, numbers and underscores, starting with a letter (e.g. Recommend_Likelihood). Option Sets table - columns, in this order: Option Set | Label | Value | Order | Score - One row per option. Label is what the respondent sees; Value is the stored value (defaults to the Label if blank). Score is an optional number for analytics (e.g. 5,4,3,2,1 for a 5-point scale). Reuse the same Option Set name across questions that share a scale. Do not invent question types, Display Type values, or columns beyond those listed above. ================================================================================ REFERENCE — DISPLAY TYPE VALUES (the exact strings for the "Display Type" column) ================================================================================ Display Type | What the respondent sees | Needs Option Set? | Use it for -----------------|-------------------------------|-------------------|---------------------------------------------- NPS | A 0-10 "recommend" scale | no | The one likelihood-to-recommend question (max one) Star | A row of 1-5 stars | no | Satisfaction / quality where stars read naturally Slider | A 0-10 draggable slider | no | Intensity / magnitude: effort, strength, likelihood Matrix | A grid of items, one scale | YES (shared) | "Rate each of the following." Every row shares one Section + Option Set + Screen RadioHorizontal | A labeled 1-5 radio row | YES | A single Likert item RadioVertical | A stacked list of radios | YES | Single choice (up to 10 options) Picklist | A dropdown menu | YES | Single choice with more than 10 options Checkbox | A list of checkboxes | YES | Multi-choice ("select all that apply") Text | A single-line input box | no | Short open text Text Area | A multi-line input box | no | Long / paragraph open text DisplayText | Static text, no input | no | Instructions, intros, a section note Screen / Section | Structural row markers | no | Usually just fill the Screen and Section columns instead Open-text sizing (optional "Data Type" column): Text, Text (120), Text (10/120), Long Text 4 (0/2000), Rich Text 6 (0/3000). Lines range 1-15; plain Text caps at 255 chars. Fine-tuning (optional "Display Properties" column, JSON): Star -> {"maxRating":5} Slider -> {"min":0,"max":10,"step":1} ================================================================================ REFERENCE — SHEET / CSV COLUMNS ================================================================================ QUESTIONS tab Required: API Name, Question, Display Type Optional: Screen, Section, Option Set, Display Properties, Data Type, Required, Show If (a.k.a. Visibility), Allow Other, Other Label, Active, Order, Help Text, Validation Regex. Advanced/reserved (leave blank unless the in-app importer asks): Dependent On, Default Value, Error Message, Lock API Name. Show If / Visibility format: ControllerApiName = 'OptionValue' (use != for "is not"). The controller must be a single-choice question on the SAME screen. OPTION SETS tab Required: Option Set, Label Optional: Value (stored value; defaults to Label), Key, Order, Score (numeric, for analytics), Is Default (TRUE pre-selects the option). ================================================================================ WHAT THE USER DOES WITH YOUR OUTPUT ================================================================================ Path A (easiest): copy output (A), open AutoSurvey's AI generation step, set the mode to "Standard", paste, then review and deploy. Standard mode structures the questions you already designed — it does not re-invent them. Path B (direct import): put the two tables from output (B) into the Questions and Option Sets tabs/CSV and use AutoSurvey's import. The importer validates columns and flags anything to fix; it is the source of truth for the exact contract. -------------------------------------------------------------------------------- Human-readable version of this guide: https://autosurvey.app/build-with-ai.html AutoSurvey by Mindshare Studio.