Synthetic Users
Guide · 2026

The Synthetic Users
guide to supercharging
your User and Market
Research

Real world examples and use cases for Synthetic Users in research.

Empowering world leading corporations
Synthetic Users
Overview · Supercharging your Research
The shift

As AI-generated insights become faster and cheaper, the real challenge is no longer access — it's trust.

Synthetic Users are a blend of AI and real-world insights, crafting scenarios that resonate deeply and mimic real human experiences. The goal is always to make better decisions and decrease the time to insight.

We've moved beyond mimicking human behaviour to building decision-grade entities that reduce risk. Grounded in real user data, powered by multiple models to limit bias, and backed by traceable, auditable inputs — including your proprietary data — Synthetic Users enable reliable prediction and decision-making.

Synthetic Users has been mentioned in Science Magazine amongst many other publications.

Synthetic Users deliver substantially more insight than Organic Users. Synthetic Users First Insight Organic Users Final Insight

Let's explore its distinct characteristics, the methods employed to verify its reliability, and the current as well as potential ways it's being utilized.

Synthetic Users
The Offering
Continuous discovery

User and market research, throughout the product lifecycle.

Synthetic Users lets you run more research at a fraction of the time and cost of organic research. By combining synthetic participants with structured research workflows, you get continuous discovery instead of one-off studies — from early problem exploration to concept validation and usability testing.

Research Goal
Explore a topic with a clear objective
User Testing
Test your screens
Custom Script
Ask your own questions
Concept Testing
Test ideas before you build them
Problem Exploration
Discover user needs and pain points
Ethnographic Study
Observe users in real-world contexts
9:41
My Cards
Monthly spending limit
$8,545.00
$0$4,600$10,000
G
GroceryShopping
−$88
S
SpotifyMusic
−$12.99
A
Apple StoreEntertainment
−$5.99
A.R. Jonson
4562 1122 4595 7852
Expiry24/2030
CVV698
Mastercard
Synthetic Users
Speed · Synthetic vs Organic
A comparison of Synthetic and Organic research

We are not replacing organic users — just accelerating your research journey. You then decide how much organic research you need.

Research journey with Synthetic Users
Step 1 Business question
Synthetic Users
Step 2 Actionable Insight
Traditional research
weeks
Recruit, schedule, transcribe, code, synthesise.
Synthetic Users
minutes
Decision-ready insight, on-demand and on-budget.
Synthetic Users
Global coverage · 59 studies
Worldwide

We have global coverage.

From New York to Mumbai, Synthetic Users cover urban, peri-urban, and rural audiences across regulated and consumer-facing sectors.

Global coverage map showing 59 Synthetic Users studies
59
Studies
93%
Avg parity
27
Countries
12
Sectors
Synthetic Users
Multi-agent framework
Architecture

A multi-agent system where agents collaborate, negotiate, and learn from each other.

This architecture underpins the generation of diverse and insightful Synthetic User interactions, supporting nuanced data analysis and decision-making — instead of a single LLM with a single context window.

Input
Input Task
Foundation models
LLMs
GPT
Claude
Mistral
Llama
Gemini
Hermes
Agents
Qual researchers
Survey / Interview builder
Study coordinator
Historical data extractor
Audience expert
Quant researchers
Research coordinator
Insights builder
Extender · Probe
Execution
Runner
Survey / Interview runner
Multiple Interviews
Multiple Surveys
Grounding
RAG (your data)
Proprietary psychographic datasets
Organic calibration
Output
Output

Compared to "you, using one LLM": more diversity in the samples, less anchoring in one context window, more synthetic / organic parity.

Synthetic Users
Parity and Applicability
How do they measure up?

Synthetic Users vs Traditional Insights.

When applied in the right phase and product categories, Synthetic Users exhibit a remarkably high level of accuracy compared to conventional research methodologies. Read the independent parity study →

Accuracy of Synthetic Users — as rated by researchers

Four-parameter measurement
91%

Thematic overlap

92%

Depth and specificity of insights

89%

Comprehensiveness of coverage

93%

Qualitative alignment

When should you use Synthetic Users

Highest value sits in Need Identification, Concept Testing, Development, Growth, and Maturity.

This is an evolving scenario as we run more comparative studies.

01
Need Identification
Recognising a gap in the market or a specific user need.
02
Idea Generation
Brainstorming and conceptualising potential products.
03
Concept Testing
Refining the idea based on initial feedback and feasibility.
04
Development
Creating the product.
05
Launch
Introducing the product to the market.
06
Growth
Expanding market reach and product adoption.
07
Maturity
Optimisation and market saturation.
08
Pivot / Reassess
Exploring opportunities for reinvention and pivot.
Synthetic Users
If you still must ask
One LLM is not Synthetic Users

The difference between using a single LLM and using Synthetic Users is noticeable.

Less diversity in the samples, more anchoring in one context window, less synthetic / organic parity. Where you sit on this spectrum determines how much your insight is worth.

Baseline

Your org using one LLM

Single context window, single model, single voice. Convenient — but high anchoring, low diversity, no grounding in your proprietary data.

Better

Synthetic Users with proprietary datasets and multiple LLMs

Bias is reduced as multiple models negotiate. Real-world psychographic data anchors the population. Diversity rises sharply.

Best

Synthetic Users with proprietary datasets, multiple LLMs and RAG

Upload your sources. Now your synthetic population is grounded in your reality — the most defensible, decision-grade insight available.

Synthetic Users
Installing Synthetic Users
Synthetic Users for your audience

An AI-driven proxy of your real-world user base.

Your team gets access to Synthetic Users that simulate your audience's behaviours, preferences, and pain points. Gather valuable insights with far greater speed — informing product development, marketing strategy, and operational decisions.

Your Company
Product
Dept X
Marketing
Ops
Synthetic Users

A single platform that every department can task with their own audience questions — same population, consistent grounding, traceable inputs.

Synthetic Users
Learn how to accelerate time-to-insight
Get started

Step-by-step tutorials and the science behind the platform.

Webinar · Demo + AMA

How to get the most out of Synthetic Users.

A live working session with our founders and a special guest, plus an open Q&A.

Host Kwame Ferreira Founder
Host Hugo Alves Co-founder
Special guest Jimmy Wales Founder of Wikipedia
Jimmy Wales, founder of Wikipedia, special guest

Follow our YouTube channel for more tutorials.