What is synthetic research?

Synthetic research uses AI-powered personas that simulate how real buyers, customers, or market segments would respond to your research questions. It produces directional signal — insights to sharpen your hypotheses — before you invest in real primary fieldwork. Gather Synthetic runs AI-moderated interviews across any audience archetype in minutes, not weeks.

How is synthetic research different from real research?

Synthetic research generates directional signal using AI personas, while real primary research collects data from actual people. Synthetic pre-research is faster (minutes vs. weeks), cheaper, and ideal for hypothesis generation and stakeholder alignment. It is not statistically valid and should be used to focus and prioritize real fieldwork, not replace it. Gather offers both synthetic pre-research and real AI-moderated interviews with actual respondents.

What types of research can Gather Synthetic run?

Gather Synthetic supports 14 study types: Brand Perception, Product Feedback, Concept Testing, Competitive Intelligence, CX/NPS Deep Dive, Messaging & Claims Testing, Win/Loss Analysis, Market Segmentation, Pricing Research, Ad & Creative Testing, Customer Journey Mapping, Feature Prioritization, Churn & Retention Analysis, and Audience Discovery.

How much does synthetic research cost?

The first 5 synthetic interviews are free. After that, B2C audience interviews cost $0.50 each and B2B audience interviews cost $5.00 each. There is no subscription required.

How accurate is synthetic research?

Synthetic research is directional, not statistically accurate. Confidence scores reflect internal AI response consistency, not statistical significance. Quantitative projections carry a ±15–20% margin of error. Treat findings as educated hypotheses to validate with real primary research, not as definitive measurements.

REST API v1

Gather Synthetic API

Run synthetic brand, messaging, competitive, and pricing research programmatically. Integrate AI-moderated research studies into any product or workflow.

Base URLhttps://synthetic.gatherhq.com/api/v1

Authentication

All API requests require a Bearer token in the Authorization header. Contact mayank@gatherhq.com to get an API key, or use your ADMIN_SECRET for internal Gather platform calls.

Header

Authorization: Bearer your_api_key_here

POST/studies

Run a study

Run a full synthetic research study. Returns structured findings when complete (30-90s).

Parameters

Name	Type	Required	Description
`topic`	`string`	yes	Research question. Be specific — 10+ characters.
`study_type`	`string`	yes	One of: brand, product, concept, competitor, cx, pricing, messaging, winloss, churn, segmentation, custom
`audience`	`string`	yes	b2b or b2c — determines default persona selection
`persona_ids`	`string[]`	no	Specific persona IDs to interview. Max 4. See GET /personas.
`n_per_persona`	`number`	no	Interviews per persona. 1-3, default 2. Total = personas × n_per_persona.
`webhook_url`	`string`	no	URL to POST study.completed event to when finished.

Request body

{
  "topic": "How do mid-market CFOs evaluate AI-powered FP&A tools?",
  "study_type": "competitor",
  "audience": "b2b",
  "persona_ids": ["p_cfo", "p_cto"],     // optional — defaults auto-selected
  "n_per_persona": 2,                     // optional — 1-3, default 2
  "webhook_url": "https://your.app/hook"  // optional — POST on completion
}

Response

{
  "id": "d80af9bb-797f-43d2-9cb3-8ac822c7d3e4",
  "status": "complete",
  "topic": "How do mid-market CFOs evaluate AI-powered FP&A tools?",
  "study_type": "competitor",
  "audience": "b2b",
  "slug": "mid-market-cfos-ai-fpa-tools-competitive-analysis",
  "report_url": "https://synthetic.gatherhq.com/report/d80af9bb-...",
  "headline_finding": "CFOs trust vendors who lead with ROI proof...",
  "executive_summary": "...",
  "overall_confidence": 68,
  "avg_sentiment": 6.2,
  "key_findings": [
    {
      "finding": "...",
      "evidence": "...",
      "implication": "...",
      "strength": "strong"
    }
  ],
  "opportunity": "...",
  "risk": "...",
  "messaging_implications": ["...", "..."],
  "quant": { "projected_nps": 32, ... },
  "created_at": "2026-03-25T14:30:00Z"
}

GET/studies

List studies

List completed studies with pagination and filtering.

Parameters

Name	Type	Required	Description
`limit`	`number`	no	Results per page. Default 20, max 100.
`offset`	`number`	no	Pagination offset. Default 0.
`study_type`	`string`	no	Filter by study type.
`audience`	`string`	no	Filter by audience: b2b or b2c.

Response

{
  "studies": [
    {
      "id": "d80af9bb-...",
      "topic": "...",
      "study_type": "brand",
      "audience": "b2c",
      "slug": "starbucks-brand-perception-brand-study",
      "report_url": "https://synthetic.gatherhq.com/report/d80af9bb-...",
      "headline_finding": "...",
      "overall_confidence": 68,
      "avg_sentiment": 6.5,
      "created_at": "2026-03-25T14:30:00Z"
    }
  ],
  "total": 48,
  "limit": 20,
  "offset": 0
}

GET/studies/:id

Get study

Retrieve full study results including synthesis, quant data, and all interview transcripts.

Parameters

Name	Type	Required	Description
`id`	`string`	yes	Study UUID

Response

{
  "id": "d80af9bb-...",
  "status": "complete",
  "topic": "...",
  "headline_finding": "...",
  "executive_summary": "...",
  "key_findings": [...],
  "consensus_themes": [...],
  "opportunity": "...",
  "risk": "...",
  "competitive_signals": [...],
  "decision_criteria": [...],
  "messaging_implications": [...],
  "research_agenda": [...],
  "quant": { ... },
  "interviews": [
    {
      "persona_id": "p_cfo",
      "persona_name": "James L.",
      "persona_role": "CFO",
      "transcript": [
        { "q": "...", "a": "..." }
      ],
      "analysis": {
        "sentiment": "mixed",
        "sentiment_score": 5.5,
        "key_themes": [...],
        "standout_quote": "...",
        ...
      }
    }
  ]
}

GET/personas

List personas

Get all available synthetic personas with demographics and traits.

Response

{
  "b2b": [
    {
      "id": "p_cmo",
      "name": "Priya S.",
      "age": 41,
      "role": "CMO",
      "company": "Enterprise Retail",
      "industry": "Enterprise",
      "income": "$240k",
      "location": "New York, NY",
      "traits": ["brand-conscious", "board pressure", "agency veteran"]
    },
    ...
  ],
  "b2c": [...],
  "defaults": {
    "b2b": ["p_cmo", "p_cto", "p_cfo", "p_vp_mktg"],
    "b2c": ["p_millennial_mom", "p_gen_z", "p_high_income", "p_budget"]
  }
}

GET/study-types

List study types

Get all available study types with descriptions.

Response

{
  "study_types": [
    {
      "id": "brand",
      "label": "Brand Perception",
      "description": "How audiences perceive a brand — affinity, trust, associations.",
      "default_audience": "b2c"
    },
    ...
  ]
}

Errors

All errors return a JSON body with error and message fields.

Status	Error code	When
`400`	`invalid_topic`	topic is missing or under 10 characters
`400`	`invalid_study_type`	study_type is not a recognized value
`400`	`invalid_audience`	audience is not 'b2b' or 'b2c'
`400`	`invalid_json`	Request body is not valid JSON
`401`	`unauthorized`	Missing or malformed Authorization header
`403`	`invalid_key`	API key is not recognized
`404`	`not_found`	Study ID does not exist
`500`	`research_failed`	Study execution failed (timeout, model error)

Webhooks

Pass a webhook_url when creating a study. We'll POST to it when the study completes:

Webhook payload

{
  "event": "study.completed",
  "study_id": "d80af9bb-...",
  "report_url": "https://synthetic.gatherhq.com/report/d80af9bb-...",
  "topic": "...",
  "study_type": "brand",
  "audience": "b2c"
}

Rate limits & pricing

Studies take 30-90 seconds to complete. The API is synchronous — the response includes the full results.

Pricing: B2C interviews $0.50 each, B2B interviews $5.00 each. Default study = 4 personas × 2 interviews = 8 interviews. A B2B study costs ~$40, a B2C study costs ~$4.

Rate limit: 10 concurrent studies per API key. Contact us for higher limits.

Quick start

cURL

curl -X POST https://synthetic.gatherhq.com/api/v1/studies \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "topic": "How do consumers perceive Starbucks after recent controversies?",
    "study_type": "brand",
    "audience": "b2c"
  }'

JavaScript / TypeScript

const res = await fetch("https://synthetic.gatherhq.com/api/v1/studies", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    topic: "How do consumers perceive Starbucks after recent controversies?",
    study_type: "brand",
    audience: "b2c",
  }),
});

const study = await res.json();
console.log(study.headline_finding);
console.log(study.report_url);

Python

import requests

res = requests.post(
    "https://synthetic.gatherhq.com/api/v1/studies",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "topic": "How do consumers perceive Starbucks after recent controversies?",
        "study_type": "brand",
        "audience": "b2c",
    },
)

study = res.json()
print(study["headline_finding"])
print(study["report_url"])

Data disclaimer

Synthetic data: All research uses AI-generated synthetic respondents — not real humans. Findings are directional signal with ±15-20% margin of error. Treat as hypotheses to validate.

Brand independence: Studies mentioning brands are independent research, not affiliated with or endorsed by those brands.

Primary research: For real human respondents, use gatherhq.com.