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.

MCP Server Documentation

Gather Synthetic for Claude

Run synthetic brand, messaging, competitive, and thought leadership research directly from Claude using the Model Context Protocol. No context switching. No forms. Just ask.

Connect in Claude →MCP Endpoint ↗

MCP Server URL: https://synthetic.gatherhq.com/api/mcp4 toolsOAuth 2.0Streamable HTTP

Quick Start

Connect in Claude

Visit claude.com/connectors, search for "Gather Synthetic", and click Connect.

Authenticate

Start researching

Ask Claude to run a study, fetch a report, or browse existing research. Claude handles the rest.

Or connect directly via Claude Code:

claude mcp add --transport http gather-synthetic https://synthetic.gatherhq.com/api/mcp

Tools

run_researchwrite~30–60 seconds

Run a full synthetic research study. Simulates interviews with AI personas and synthesizes findings into a structured report.

Parameters

Name	Type	Required	Description
`topic`	`string`	yes	The research question. Be specific. E.g. "How do mid-market CFOs evaluate consolidating point solutions vs best-of-breed?"
`study_type`	`enum`	yes	brand \| product \| concept \| competitor \| cx \| pricing \| messaging \| winloss \| churn \| segmentation \| custom
`audience`	`enum`	yes	b2b (uses CMO/CTO/CFO personas) or b2c (uses Gen Z/millennial/consumer personas)
`persona_ids`	`string[]`	no	Optional: specific persona IDs to interview. Leave blank for auto-selection based on audience.
`n_per_persona`	`number`	no	Interviews per persona. Default 2 (= 8 total with 4 personas). Max 3.

Returns: Structured report with headline finding, executive summary, key findings, opportunity/risk, messaging implications, quant metrics (NPS, confidence, sentiment), and link to full report.

get_reportread-only~< 1 second

Fetch findings from an existing research project by ID or URL.

Parameters

Name	Type	Required	Description
`project_id`	`string`	yes	Project UUID or full report URL (https://synthetic.gatherhq.com/report/UUID)

Returns: Full synthesis: headline finding, executive summary, key findings, opportunity, risk, quant metrics.

list_studiesread-only~< 1 second

Browse recently completed research studies. Use to find existing research before running a new study.

Parameters

Name	Type	Required	Description
`limit`	`number`	no	Number of studies to return. Default 10, max 20.
`study_type`	`enum`	no	Filter by type, or "any" for all.
`audience`	`enum`	no	b2b \| b2c \| any

Returns: List of studies with topic, type, audience, date, headline finding, report URL, and project ID.

list_study_typesread-only~< 1 second

Returns all available study types, available personas with details, and usage guidance.

Returns: Complete reference: all study types with descriptions, all personas with role/industry/traits, usage tips.

Examples

Example 1

Run a brand health study

User prompt

“Using Gather Synthetic, run a brand health study on how Gen Z consumers perceive Olipop vs. Poppi. Focus on purchase drivers and loyalty.”

What happens

Calls run_research with study_type=brand, audience=b2c
Interviews 8 synthetic consumer personas
Returns headline finding, key insights, and messaging implications
Provides full report URL with transcripts

Example output

Headline: "Olipop wins on gut health credentials but Poppi is winning on taste and TikTok virality — 6/8 personas cited flavor first, health second."

Example 2

Competitive intelligence on AI coding tools

User prompt

“Run a competitive analysis on how developers choose between Cursor, GitHub Copilot, and Windsurf. What drives switching?”

What happens

Calls run_research with study_type=competitor, audience=b2b
Interviews CTO, PM, and engineering personas
Returns switching triggers, loyalty drivers, and messaging gaps

Example output

Headline: "Cursor wins on context window quality but Copilot wins on enterprise IT approval — the real battle is procurement, not features."

Example 3

Find existing research before running a new study

User prompt

“Before I run a new pricing study, check if Gather Synthetic has any existing research on SaaS pricing and mid-market buyers.”

What happens

Calls list_studies with study_type=pricing, audience=b2b
Returns recent matching studies with headlines and report URLs
You can call get_report on any result for full findings

Example output

Returns list of relevant studies with topics, dates, confidence scores, and full report URLs.

Example 4

Fetch a specific report

User prompt

“Get the findings from this Gather Synthetic report: https://synthetic.gatherhq.com/report/abc-123”

What happens

Calls get_report with the URL
Returns complete synthesis: headline, executive summary, key findings
Includes quant: NPS, confidence %, sentiment score

Example output

Full structured report with findings, opportunity, risk, and messaging implications.

Example 5

Thought leadership content generation

User prompt

“Run a thought leadership study on how CMOs think about AI research tools in 2025, then help me write a LinkedIn post based on the findings.”

What happens

Runs study with study_type=thought_leadership, audience=b2b
Returns specific quotes and data points
Claude then drafts LinkedIn post grounded in real synthetic findings

Example output

Research-backed LinkedIn post with specific findings, percentages, and quotes from synthetic CMO personas.

Personas

Each study interviews 4–8 synthetic personas. Personas are AI archetypes grounded in real buyer demographics, job contexts, and decision-making patterns. B2B studies default to executive buyers; B2C studies default to consumer segments.

p_cmo

Priya S.

CMO

Enterprise Retail

brand-consciousboard pressureNPS-focused

p_cto

Alex R.

CTO

Series C SaaS

build vs buysecurity-firstvendor fatigue

p_cfo

James L.

CFO

Mid-Market Co

ROI-firstskepticalbenchmark-obsessed

p_vp_mktg

Marcus T.

VP Marketing

Series B SaaS

data-drivenROI-obsessedex-agency

p_vp_sales

Tanya M.

VP Sales

Enterprise SaaS

quota-obsessedloves social proof

p_pm

Jordan K.

Senior PM

Fintech Startup

lean methodologyuser research believer

p_demand

Chris W.

Head of Demand Gen

Series A Startup

pipeline-obsessedCAC-conscious

p_cs

Keisha N.

VP Customer Success

Mid-Market SaaS

churn-paranoidchampion builder

p_millennial_mom

Ashley R.

Marketing Manager

Ad Agency

convenience-firstbrand loyal

p_gen_z

Tyler H.

Graphic Designer

Freelance

value-consciousanti-adcommunity-driven

p_high_income

David L.

Partner

Law Firm

premium-biasedtime-scarcestatus-conscious

p_budget

Maria G.

Nurse

Regional Hospital

price-sensitivereviews-driven

p_early_adopter

Raj M.

Software Engineer

Big Tech

tech-firstbeta tester

Authentication

The Gather Synthetic MCP server uses OAuth 2.0 Authorization Code flow. Claude handles the OAuth dance automatically when you connect from the Connectors Directory.

Authorization endpoint

https://synthetic.gatherhq.com/api/oauth/authorize

Token endpoint

https://synthetic.gatherhq.com/api/oauth/token

Revocation endpoint

https://synthetic.gatherhq.com/api/oauth/revoke

Discovery URL

https://synthetic.gatherhq.com/.well-known/oauth-authorization-server

Scopes

research:read research:write

Token lifetime

30 days

Direct API access (Bearer token)

curl -X POST https://synthetic.gatherhq.com/api/mcp   -H "Authorization: Bearer YOUR_TOKEN"   -H "Content-Type: application/json"   -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'

Study Types

brand

Brand Perception

How audiences perceive a brand — affinity, trust, associations, and competitive positioning.

messaging

Messaging & Positioning

Which messages, claims, and frames resonate vs. trigger skepticism with your target audience.

competitor

Competitive Intelligence

Switching intent, competitive positioning, why buyers choose alternatives.

pricing

Pricing Research

Willingness to pay, price sensitivity, tier preferences, and model preference (seat vs usage).

concept

Concept Testing

Validate new product ideas, features, or positioning concepts before building.

cx

CX / NPS

Customer experience, friction points, NPS drivers, and retention signals.

winloss

Win / Loss Analysis

Why deals are won or lost — decision factors, competitive dynamics, objection patterns.

thought_leadership

Thought Leadership

What B2B buyers actually think about emerging trends, categories, and strategic questions.

churn

Churn & Retention

Why customers leave, what would keep them, and what predicts early churn.

product

Product Feedback

Feature value, adoption barriers, pain points, and improvement priorities.

segmentation

Segmentation

Identify and characterize distinct buyer segments with different needs and behaviors.

custom

Custom Research

Open-ended research on any topic. Best for novel questions without a clear study type.

Pricing

Free tier

5 interviews free — no credit card required

B2C interviews

$0.50 per interview (consumer personas)

B2B interviews

$5.00 per interview (executive buyer personas)

read_report / list_studies

Free — no charge for reading existing research

A default study runs 4 personas × 2 interviews = 8 interviews. B2B default: $40/study. B2C default: $4/study. First 5 interviews free — that's one full B2C study at no cost.

Data & Disclaimer

Synthetic data: All research conducted through this MCP server uses AI-generated synthetic respondents — not real human survey participants. Findings are directional signal, not statistically valid measurements. Quantitative projections carry a ±15–20% margin of error. Treat findings as hypotheses to validate, not as definitive measurements.

Brand independence: Studies mentioning specific brands, products, or companies are independent research conducted by Gather. They are not affiliated with, commissioned by, sponsored by, or endorsed by any brands mentioned.

Primary research: For statistically valid research with real human respondents, visit gatherhq.com.

Support

✉

support@gatherhq.com

◎

Browse Reports

synthetic.gatherhq.com/reports

◈

Primary Research

gatherhq.com

⚖

synthetic.gatherhq.com/privacy