> For the complete documentation index, see [llms.txt](https://docs.zigpoll.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zigpoll.com/synthetic-research/running-your-first-research.md). # Running Your First Research This guide walks you through generating your first set of synthetic research responses, from choosing an audience to viewing results. *** ## Prerequisites * An existing survey with at least one answerable slide (any type except copy, thank-you, reward, or action). * Available synthetic response quota on your plan. See [monthly limits](/synthetic-research.md#monthly-limits) for details. *** ## Step 1: Open the Audience tab Navigate to your survey in the Zigpoll dashboard and click the **Audience** tab. If this is your first time running synthetic research on this survey, you'll see the profile builder. *** ## Step 2: Choose an audience template Select a template from the **Template** dropdown to pre-fill your audience profiles. There are 9 templates available: * US General Population * Young Professionals * Enterprise Decision Makers * Millennials * Gen Z * Gen X * Baby Boomers * New Mothers * Young Men You can also select **Build from scratch** to start with a blank profile. {% hint style="info" %} Templates are starting points — you can edit any profile's name, percentage, or demographic attributes after applying a template. {% endhint %} *** ## Step 3: Configure audience profiles Each profile represents a demographic segment of your virtual audience. For each profile, you can set: * **Profile Name** — A label for this segment (e.g., "Young Adults 18-34"). * **Percentage** — What share of total completions this profile gets. All percentages must total 100%. * **Demographic Attributes** — 10 optional fields (Age Range, Gender, Geography, Role/Occupation, Salary Range, Education, Relationship Status, Family Status, Interests, Hobbies) plus a free-form Custom Attributes field. Click **Add Profile** to add more segments. When you adjust one profile's percentage, the others automatically redistribute to keep the total at 100%. *** ## Step 4: Set research goals and context Under the **Research Goals** section, you can optionally provide: * **Research Goal** — Describe what you want to learn (e.g., "Understand customer satisfaction with our checkout flow"). This helps the AI generate more relevant and focused responses. * **Business Description** — Describe your business or product. If you have a Shopify store or domain connected, this is auto-filled for you. You can edit it at any time. Both fields are optional, but providing them significantly improves response quality. *** ## Step 5: Configure output settings Under **Output Settings**, configure: * **Number of Completions** — How many virtual respondents should complete the survey. Enter a number from 1 to 1,000. * **Response Language** — Choose from 94+ supported languages. Defaults to English. Review the **Summary** section below to see a breakdown of completions per profile and the total number of responses that will be used from your quota. *** ## Step 6: Generate Click **Generate Audience** to start the process. The AI will begin generating responses for each profile according to your configuration. *** ## Step 7: Monitor progress Once generation starts, you'll see a progress screen with: * A **progress bar** showing completions out of the total, updated every 3 seconds. * A **status badge** indicating the current state: | Status | Description | | ---------- | ----------------------------------------------------------- | | Generating | Responses are actively being generated | | Completed | All completions finished successfully | | Incomplete | Generation finished but some completions were not completed | | Failed | Generation encountered an error | | Cancelled | You manually cancelled the generation | You can **cancel** generation at any time. Any completions that already finished will be kept. {% hint style="info" %} You'll receive an email notification when generation completes or if it fails. {% endhint %} *** ## Step 8: View results Once generation finishes, you have three options: * **View Data** — Opens the standard analytics dashboard where you can see charts, response breakdowns, and AI insights for your synthetic responses. * **Reset Data** — Permanently deletes all responses, participants, and events for this survey so you can start fresh. * **Duplicate** — Creates a copy of the survey (without responses) so you can run new research with different audience profiles. {% hint style="warning" %} **Reset Data** is permanent and cannot be undone. All responses, participants, and events for the survey will be deleted. {% endhint %} *** ## Tips for better results * **Be specific with profiles** — "Female, 28-34, urban, tech worker" produces more realistic responses than just "Mixed, 18-65." * **Add business context** — Telling the AI about your industry and products helps it generate responses that feel authentic to your domain. * **Start small** — Run 10-20 completions first to check quality before scaling up to hundreds. * **Use research goals** — A clear goal like "understand purchase hesitation" produces more focused responses than leaving it blank. * **Check your survey logic** — Synthetic respondents follow your branching logic and display rules. Make sure your flows work as intended before generating. *** ## Next steps {% content-ref url="/pages/52bW7NYC6qduWDfXHEfF" %} [Audience Profiles Reference](/synthetic-research/audience-profiles-reference.md) {% endcontent-ref %} {% content-ref url="/pages/xIfRWjKlV8LQQzDo34iJ" %} [Analytics, AI, and Reporting](/analytics-ai-and-reporting.md) {% endcontent-ref %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.zigpoll.com/synthetic-research/running-your-first-research.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.