Agentic Research

The customer-research API for AI agents

Q: How do I connect my AI agent to User Intuition?

Add the User Intuition MCP server to your client's config — Claude Desktop, Cursor, Claude Code, and VS Code share the same snippet (your API key goes in as an environment variable). ChatGPT connects via the official OAuth connector instead. Full setup instructions are at docs.userintuition.ai/mcp-server/overview.

Q: What clients are supported?

Claude Desktop, Cursor, Claude Code, and VS Code today. ChatGPT via its OAuth connector. Any agent framework that supports the open Model Context Protocol (MCP) standard — backed by Anthropic, OpenAI, Google, and Microsoft — can connect. The compatible client list keeps growing as MCP adoption expands.

Q: Do I need a User Intuition account?

Yes. Sign up at app.userintuition.ai and generate an API key from Settings → API Keys. For Human Signal studies, the rate is $10 per interview. Full studies are priced from $150. A Starter account includes 3 free interviews with no credit card required.

Q: Is the dashboard still required?

No. Every research action — creating studies, recruiting participants, retrieving transcripts, querying the Intelligence Hub, generating reports — is exposed as an MCP tool. Your agent can run the full research workflow without a human opening the dashboard. The dashboard remains available for reviewing results visually or managing account settings, but it is not required for any step an agent takes.

Q: How is this priced?

Human Signal studies are billed at $10 per interview. Full AI-moderated interview studies start at $125 — $25 per quality interview on Professional, only billing for sessions that pass automatic Length, Depth, and Coverage checks. The Professional plan ($2,499/month) includes 100 quality voice interviews. A Starter account is free and includes 3 free quality interviews to test the platform. All plans include API and MCP access.

Q: Do I only pay for completed quality interviews when agents run studies?

User Intuition only bills for quality interviews — sessions that pass automatic Length, Depth, and Coverage checks. This applies whether a human or an AI agent commissions the study. Misses aren't charged, no refund request required. Kantar reports researchers discard 38% of survey data on average due to quality concerns — agent-driven research programs are especially exposed to bad-data waste at scale. User Intuition's quality-only billing model keeps agentic research budgets aligned with usable signal.

Q: What is the difference between Human Signal and Studies?

Human Signal is the fast path, exposed via 5 MCP tools. Pick one of three modes — preference, claim, or message — supply the stimuli and a sample size, and structured results land in hours. Studies is the full interview-workflow path, exposed via 13 MCP tools. Create a custom study with your own moderation prompt, configure screeners, manage individual participant invites, and access raw transcripts and call recordings. Both return structured results. Human Signal is built for speed and directional signal; Studies is built for depth and custom design.

Q: Can I use my own customer list?

Yes. Invite your own customers, prospects, or specific segments via the API. If Shopify or HubSpot is connected, the integration keeps your segment fresh and handles the invites. You can also blend your own list with our 4M+ vetted panel by ordering a panel survey alongside your custom invites.

Q: What data formats are returned?

Human Signal results return a structured object with a headline metric, driving themes ranked by prevalence with participant counts, minority objections with verbatim quotes, and a data quality score. Full study results include transcripts, message arrays, recording URLs, per-call analysis, and a study-level AI-generated report. All data is JSON — no PDF parsing or manual extraction required. Every finding traces back to specific participant quotes for evidence-backed decision-making.

Q: What is agentic research?

Agentic research is when an AI agent autonomously commissions, runs, and consumes real customer research without a human in the loop. Instead of reasoning from training-data averages, the agent calls MCP tools to recruit real people, run AI-moderated interviews, and retrieve structured results — preference splits, agreement rates, minority objections — that no LLM simulation can produce. User Intuition's MCP server is the infrastructure that makes this workflow possible.

Your agent designs the study, recruits real people, runs the interviews, and returns analyzed insight — 72 MCP tools, no dashboard required.

Get an API Key Read the Docs

Works with Claude, ChatGPT, Cursor, Claude Code & VS Code

One API key, no dashboard required

Researcher using User Intuition AI-moderated research platform

Live

app.userintuition.ai/dashboard

Study Dashboard 3 Active

MCP Tools

▲ 2.1%

Capability Groups

▲ 3.5%

<3hrs

To Results

▼ 1.2%

4M+

Panel Size

▲ 6.3%

Response Trend 7 days

Choose study type

Win/Loss

Churn

NPS

Brand

Custom

<3hrs To Results ▲ 2.1%

78% Complete

Live

Trusted by teams at

TL;DR

AI agents running customer research autonomously — commissioning interviews, recruiting respondents, and returning analyzed insight — are becoming standard infrastructure for product and insights teams. User Intuition is the MCP server that gives any AI agent access to this infrastructure: 72 tools across 9 capability groups, from study design to analyzed results. User Intuition's AI moderator runs voice, chat, and video customer interviews with real panelists, probing 5-7 layers deep so agents receive decision drivers, not just surface preferences. Dashboard-only tools require a human to log in and configure each step; an MCP-native research interface removes that bottleneck for agent workflows entirely. A User Intuition agentic study starts at $150, returns structured results in 24 hours through a single API key, and draws from a 4M+ global panel in 50+ languages. User Intuition returns preference splits, agreement scores, ranked themes, and minority objections with verbatim quotes — every interview compounding in the Intelligence Hub for the next agent query.

The Problem

Why Agents Can't Use Dashboard-Only Research Tools

Most research platforms were built for humans opening a browser. Four structural gaps make them incompatible with agent-native workflows.

Your agent can't open the dashboard

Qualitative research tools are designed for human clicks: log in, configure a study, wait for results, export a PDF. An AI agent can't do any of that. Without a programmatic interface, the agent has to hand off to a human at every step — eliminating the autonomy that makes agentic workflows valuable.

Survey APIs are not moderated interviews

Survey-distribution APIs return static responses to static questions. They can't probe why a respondent chose Option A, surface the minority objection that explains churn, or ladder down from a stated preference to the decision driver beneath it. AI-moderated interviews produce the depth that survey logic can't.

Scraped data is not real human signal

Web scraping, social listening, and review mining tell you what people said publicly, not how they react to your specific content today. An agent building a message test or concept validation needs fresh, targeted human reactions — not a corpus of historical mentions.

LLM inference collapses variance

Asking an LLM to simulate audience reactions flattens the real distribution: the 15% who reject your claim and the 52% who love it get averaged into one confident answer. Real participants surfacing genuine skepticism, confusion, and emotional responses are the only source of evidence an agent can trust for high-stakes decisions.

The Fix

What the MCP Server Gives Your Agent Instead

What matters most to teams after switching to AI-moderated research.

Programmatic research tools

Every step of the research workflow — study creation, participant recruitment, interview analysis, report generation — exposed as MCP tools an agent can call directly

Real human signal, not simulation

Real

AI-moderated voice, chat, and video customer interviews with vetted panelists, returning genuine preference splits, agreement rates, and minority objections no LLM can fabricate

Agent-native turnaround

< 3 hrs

From a single agent call to structured results while the decision window is still open — no export, no PDF parsing, no human relay required

Intelligence Hub memory

Compounds

Every study automatically feeds the Intelligence Hub so agents can query accumulated research history, not just the latest run

Definition

What Is the User Intuition MCP Server?

The User Intuition MCP server is the full User Intuition research platform exposed as 72 MCP tools — callable directly from Claude, ChatGPT, Cursor, Claude Code, VS Code, or any agent that supports the Model Context Protocol. One API key. No dashboard login. Your agent designs the study, recruits participants, runs AI-moderated interviews, and retrieves structured results programmatically.

The server registers 72 tools across 9 capability groups covering the complete research arc: Human Signal (quick paid-panel studies), Studies (full AI-moderated interview workflows), Invites & Participants, Calls & Interviews, Voice & Reports, Intelligence Hub (search and synthesis across all past research), Integrations & Panels (Shopify / HubSpot segment sync), Monetization & Utilities, and Account.

Connects to Claude Desktop, Cursor, Claude Code, and VS Code through the standard MCP config, and to ChatGPT via OAuth. Full setup is in the docs.

Every study feeds User Intuition's Customer Intelligence Hub — a searchable knowledge base where findings compound over time. When your agent asks “what have we learned about checkout messaging?” it draws on months of accumulated insight, not just the latest study. The MCP server exposes the full Intelligence Hub query surface, so agents build organizational memory without a human ever opening the dashboard.

Quick Answers

How Does an AI Agent Run Customer Research?

An AI agent runs customer research by calling User Intuition's MCP tools directly: create a study, recruit participants from a 4M+ global panel or your own customer list, wait for AI-moderated interviews to complete, then pull back preference splits, agreement scores, themes, and verbatim quotes — all through the API. No dashboard login, no manual export — the agent owns the full loop.

Which AI clients are supported?

Claude Desktop, Claude Code, Cursor, and VS Code connect through the standard MCP config with an API key. ChatGPT connects via OAuth. Any agent framework that supports the open Model Context Protocol (MCP) standard can connect — full setup snippets are in the docs.

What is the difference between Human Signal and Studies?

Human Signal (5 tools) is the fast, paid-panel path: your agent specifies a mode (preference, claim, or message), stimuli, and sample size, and gets back a structured result in hours. Studies (13 tools) is the full interview-workflow path: the agent creates a custom study with its own screeners and moderation prompts, manages participant invites, and triggers transcript analysis. Both return structured results; Human Signal is optimized for speed and directional signal, Studies for depth and custom design.

Do I need a User Intuition account?

Yes. Sign up at app.userintuition.ai, then generate an API key from Settings → API Keys. That key is the only credential most clients need; ChatGPT uses OAuth instead.

Compare

Agent-Native Research vs. Dashboard-Only Tools
vs. Data & Scraping APIs

Dimension	User Intuition MCP	Dashboard-Only Tools	Data & Scraping APIs
Agent access	Native MCP — 72 tools, no dashboard login	Human must log in and configure each study	API exists but returns historical or scraped data
Interview depth	AI-moderated conversations with 5-7 layer laddering	AI-moderated or human-moderated, but dashboard-gated	No interviews — static data or social content
Real people	Yes — 4M+ vetted panel or your own list	Yes — but manual export blocks agent consumption	Depends — some panels exist, no moderation
Result format	Structured JSON — agent-ready, no parsing	PDF or dashboard UI — not agent-consumable	Raw text, ratings, or embeddings — requires post-processing
Fresh signal	On-demand — agent triggers a new study any time	On-demand — but requires human setup	Historical or batch — not specific to your content today
Cost	From $125 per study, $25/interview	Varies — often $5K–$15K+ per project	Varies — often cheap per record, but low validity
Compounding memory	Every study feeds Intelligence Hub	Standalone reports, not queryable by agents	No organizational memory layer

Vs. Other AI Tools

How does User Intuition compare to other AI-moderated interview tools?

Easier setup

Brief in, study live in five minutes. No discovery workshop, no kickoff cadence. Competitors typically require a 30–60 minute onboarding call.

5 minutes from brief to launch

Faster fieldwork

User Intuition owns a 4M+ verified panel, plus vetted external panels for hard-to-reach segments. Competitors lean on third-party recruiters or make you bring your own.

Studies fill in hours, not days

Deeper insights

Adaptive 5–7 level laddering on every response — the same probing technique a senior qualitative researcher uses. Most AI moderators stop at one or two follow-ups before moving on.

Probes 5–7 levels deep, every interview

Lower risk

Every interview is auto-scored against your brief on length, depth, and coverage. Conversations that miss the bar aren't charged. No refund request required, no manual review.

Only pay for quality interviews

See full comparisons →

72 Tools, 9 Groups

The Full User Intuition Research Platform via MCP

Every capability is a tool an agent can call. No dashboard required for any of them.

Human Signal (5 tools)

Create and manage paid panel studies that ask real people what they think — preference checks, claim reactions, and message tests returning structured results in hours.

5 tools for paid-panel study creation and results

Studies (13 tools)

Build, configure, and manage full AI-moderated interview studies end-to-end — create assistants, set screeners, upload concept links, and control panel surveys.

13 tools for study lifecycle management

Invites & Participants (8 tools)

Recruit from your own customer list or our 4M+ vetted panel — create individual or bulk invites, manage participant records, and send participant rewards on completion.

8 tools for participant management

Calls & Interviews (7 tools)

Access transcripts, recordings, and analysis for every completed interview — list calls, fetch individual transcripts, update visibility, and trigger study-level report generation.

7 tools for interview access and analysis

Voice & Reports (2 tools)

Select from the catalog of available interviewer voices and retrieve the latest AI-generated analysis report for any study.

2 tools for voice selection and report retrieval

Intelligence Hub (18 tools)

Search and synthesize all accumulated research — query across past studies, manage conversation history with the Hub, and generate reports or PowerPoints from the full evidence base.

18 tools for research memory and synthesis

Integrations & Panels (5 tools)

Sync customer segments from Shopify or HubSpot, list external participants, check integration status, and order panel surveys for a study.

5 tools for external data and panel access

Monetization & Utilities (8 tools)

Manage your wallet, browse subscription and billing plans, redeem coupon codes, and handle referral invitations — all programmatically from your agent.

8 tools for billing and account utilities

Account (6 tools)

Retrieve organization details and member lists, update your profile, submit feedback on a study, and contact sales or support — without leaving your agent workflow.

6 tools for organization and profile management

Developer Setup

Connect Your AI Agent in Minutes

One-time MCP setup. Works with any compatible client — no dashboard login required after setup.

2 min

Get an API Key

Sign up at app.userintuition.ai and generate an API key from Settings → API Keys. That's the only credential most clients need.

2 min

Connect Your Client

Add User Intuition to your MCP config — Claude Desktop, Cursor, Claude Code, and VS Code share the same snippet; ChatGPT connects via OAuth. Copy the exact config from the docs.

30 sec

Your Agent Calls a Tool

The agent picks the right path: a quick Human Signal study for fast directional reads, or a full AI-moderated study for depth. Specify mode, stimuli, sample size, and audience — the platform handles the rest.

2-3 hrs

Real Interviews Run

Participants join AI-moderated voice, chat, or video conversations. The AI moderator probes 5-7 layers deep to separate stated preferences from decision drivers. Preview cost and timeline before each study commits.

Instant

Analyzed Results Return

Pull back preference splits, agreement scores, ranked themes, minority objections with verbatim quotes, and a data quality score. Every study automatically feeds the Intelligence Hub for future queries.

See it in action →

Use Cases

What Agents Use the MCP Server For

See how agent-driven workflows map to specific research solutions.

Concept & Message Testing

Agent runs a message- or preference-mode study to validate copy, positioning, and creative before launch.

→

Win-Loss Analysis

Agent spins up a win-loss study to understand the real reasons deals are won or lost.

→

Brand Health Tracking

Agent schedules recurring Brand Health studies to track perception and competitive positioning over time without manual setup.

→

NPS + CSAT Deep Dives

Agent triggers NPS + CSAT interviews with detractors to surface the drivers behind scores — not just the numbers.

→

Consumer Insights

Agent runs preference checks and claim-reaction studies to uncover purchase motivations and unmet needs at scale.

→

User Research

Agent commissions usability and concept-test studies with your own customer list via Shopify or HubSpot segments.

→

Explore all solutions →

Methodology & Trust

When Should an Agent Use Human Signal vs. a Full Study?

Human Signal is optimized for speed and directional signal — preference checks, claim reactions, and message tests returning results in hours. Full studies are better for deep exploration, complex audience segmentation, and board-level deliverables.

Use Human Signal When

You need quick signal on messaging or creative before launch
Comparing headlines, taglines, or product name options
Checking whether a claim feels believable to your audience
Testing if messaging is clear and lands the way you intend
Running iterative test-and-revise cycles inside an agent workflow
You need directional validation in hours, not days

Use Full Studies When

Deep exploratory research requiring 30+ minute AI-moderated conversations
Custom screeners and audience segmentation beyond panel defaults
Concept testing with external links or video stimuli
Board-level deliverables with full evidence trails and PowerPoint output
Longitudinal tracking using the same study design over weeks or months
Recruiting from your own customer list via Shopify or HubSpot segments

Both Human Signal and full studies feed the same Intelligence Hub — findings compound regardless of which tools created them.

"We were about to launch a rebrand with copy our AI helped write. Ran a message test first — 24% of respondents found the tagline confusing. We caught a $200K mistake in 3 hours for less than the cost of lunch."

VP of Marketing — Series B SaaS, 150 employees

FAQs

Frequently Asked Questions