What is RAG and why it’s important for Synthetic Research
Ahead of our RAG launch we explain Retrieval-Augmented Generation (RAG) and how it enhances Synthetic Users by providing increased realism, contextual depth, and adaptive learning, with profound implications for market research, user experience testing, training, education, and innovative product development.
Imagine Retrieval-Augmented Generation (RAG) as an advanced AI system that’s a bit like a hybrid between a creative writer and a savvy researcher. It’s built from two main parts: the large AI model that can chat about a wide range of topics because it contains the whole of the public internet (think of it as the creative writer) and a super-efficient information lookup system (our savvy researcher).
This setup allows RAG to dig into a huge pool of knowledge - like having access to an enormous digital library - to find information that's not just on-topic but also detailed and accurate, much like a knowledgeable friend who always has the facts to back up their stories. So, when you ask RAG a question, it gives you an answer that’s both informative and interesting, blending the best of creativity with the precision of real-world information.
Enhancing Synthetic Users with RAG:
Synthetic Users, powered by standard LLMs, have pushed the boundaries in simulating user interactions. However, their responses can sometimes lack the depth or specificity that comes from real-life experiences and knowledge. Integrating RAG transforms these interactions by:
Increased Realism: RAG enables Synthetic Users to access a broader range of real-world knowledge, making their responses more authentic and varied.
Contextual Depth: By retrieving information related to the specific context of an interview question (you define this), RAG enhances the relevance and depth of Synthetic User responses. In other words, the responses will be more relevant to your context.
Adaptive Learning: As RAG models can pull from recent and up-to-date sources, they ensure that Synthetic Users' responses evolve with current trends and information.
How much better is it?
We compared the same Synthetic Interviews with Synthetic Interviews enriched with RAG and found that the latter provide more depth and detail on the personal stories — something that had been lacking from the synthetic / organic parity studies we had performed without RAG. The improvements are obvious and notable in the Depth and Specificity of insights and Comprehensiveness of coverage.
Real-World Applications:
The implications of RAG-enhanced Synthetic Users are profound across various industries:
Market Research: Our clients can now conduct more nuanced and informative user interviews, obtaining insights that further mimic those from real consumer feedback.
User Experience Testing: Designers and developers can iterate on products and services with feedback that feels genuinely user-driven, accelerating the design process but also anchoring it in reality.
Training and Education: RAG can simulate diverse user interactions for training customer service and sales teams, providing a range of scenarios that prepare employees for real-life encounters.
Innovative Product Development: RAG-enhanced Synthetic Users revolutionize product development by providing realistic feedback for testing new ideas. This allows for accurate predictions of market trends and user acceptance, ensuring innovations meet real user needs.
Releated Articles
More articles for you
The Lie We Tell Ourselves About Customer Research
Most research asks what people say. The problem is people don't do what they say. This piece breaks down the gap between stated and revealed preference — and why behavioral modeling, not better interviews, is how you close it.
Two ways to run research with Synthetic Users and why the difference matters
Iris, what is the difference of using agents to accelerate research.
Synthetic Users vs digital twins
You don’t need a twin for “a parent in rural Ohio who shops weekly at Walmart, prefers fragrance-free, and has a toddler with eczema.” You sample a parent profile with relevant traits and constraints, add retail and dermatology context, and generate behaviors consistent with both.
Two major papers. One shared direction.
LLM-powered Synthetic Users have crossed from concept to validated method. This proves they can predict human behavior accurately, letting teams run fast, low-cost behavioral experiments without replacing real participants.
Gartner says we lead. That's kind of them.
Gartner’s latest report on AI-powered synthetic user research cites Synthetic Users as a leader.
Introducing Shuffle v2
Shuffle v2 is a feature that intelligently shuffles between multiple large language models via a routing agent to produce more realistic, diverse Synthetic Users with better organic parity.
Chain-of-feeling
Synthetic Users use a “chain-of-feeling” approach—combining emotional states with OCEAN personality traits—to produce more human-like, realistic user responses and yield richer UX insights.
Generative Agent Simulations of 1,000 People
A paper that thoroughly executes a parity study between Synthetic and Organic users.
21 Peer reviewed papers that support the Synthetic Users thesis
Here is a compilation of all the papers that help make a case for Synthetic Users.
Why we shuffle between models — to ensure both parity and diversity!
Synthetic Users balances aligned and unaligned models to maintain diversity and authenticity in simulated users while ensuring ethical standards and user expectations are met.
Latest press articles for Synthetic Users
Synthetic Users and AI are transforming research methodologies, offering innovative, cost-effective alternatives to traditional human subject studies.
Comparison studies. The opportunity lies in the deviation.
When we compare different studies, especially looking at what synthetic (artificial interviews) and organic (real-world interviews) data tell us, we often find they mostly talk about the same things but there's also a bit where they don't match up. This gap is super interesting because it's like finding hidden treasure in what we thought we knew versus what we might have missed.
How we deal with bias
Harnessing the power of AI in our Synthetic Users, we strive for a balance between reflecting reality and ethical responsibility, ensuring diversity and fairness while maintaining realism.
The transition to Continuous Insight
The transition towards Continuous Insight™ aligns research activities more closely with the dynamic needs of the business and ensures that product development is continuously informed by up-to-date user insights.
The Art of the Vibes Engine
Large language models (LLMs) like GPT-4 serve as powerful "vibes engines," empathizing with diverse groups and generating contextually relevant content. Their applications span market research, customer support, user experience design, and mental health support, offering invaluable insights and personalized experiences. While not infallible sources of truth, LLMs enable creativity, personalization, and connection within the realm of human language.
There is a faster and more accurate way to do research. Use Synthetic Users.
How Synthetic Users is changing the research process.
The wisdom of the silicon crowd
In the light of an ancient parable, we explore a new paper that dives into how ensembles of large language models match the prediction accuracy of human crowds. It reveals that combining machine predictions with human insights leads to the most robust forecasting results.
Three research papers that helped us build ❤️ Synthetic Users
For the sceptics amongst us who need more tangible research in order to engage with this brave new world. Full disclosure: we are part of the sceptics.
What is RAG and why it’s important for Synthetic Research
Ahead of our RAG launch we explain Retrieval-Augmented Generation (RAG) and how it enhances Synthetic Users by providing increased realism, contextual depth, and adaptive learning, with profound implications for market research, user experience testing, training, education, and innovative product development.
Synthetic Users system architecture (the simplified version).
Foundation models underpin Synthetic Users with advanced capabilities, enhanced by synthetic data and RAG layers for realism and business alignment, all within a collaborative multi-agent framework for richer interactions.
Saturation score. How do we know how many interviews to run?
Determine your interview target for achieving topic saturation using our efficient approach, leveraging the historical wisdom of research pioneers. This method ensures deep insights with theoretical sampling at its core.
How Synthetic Users are gaining depth
Synthetic Users are evolving to address criticism about their generalist nature by incorporating representative data sets and personal narratives.
How we compare interviews to ensure we improve our Synthetic Organic Parity — 85 to 92%
How do we know we are right? How do we know our Synthetic Users are as real as organic users? We compare.
Synthetic Users: Merging Qualitative and Quantitative Research, in seconds.
At Synthetic users we are blurring the lines between qualitative and quantitative research. Here's how we are going about this transformative approach.