Synthetic Users system architecture (the simplified version).

Multi-agent architecture for enhanced Synthetic User interactions

‍

In order to achieve the quality we are known for, we need different agents talking to each other to create diverse and detailed interviews. Some call this agentic UX. The reality is that this will help bring out the insights you need in your research as well as allow you to probe deeper and extend your research, e.g. run interviews then surveys then back to interviews... having the various agents explore the space where insight can be surfaced.

‍

Achieving high-quality Synthetic User interactions necessitates a multi-agent architecture where different agents collaborate, negotiate, and learn from each other. This architecture fosters:

‍

• Robust Communication Protocols: Establishing efficient channels for inter-agent communication, crucial for coordinating complex interactions and negotiations.
• Feedback Loop Mechanism: A continuous learning framework where agents adapt based on interaction outcomes, leading to iterative improvements in performance.

‍

This architecture underpins the generation of diverse and insightful Synthetic User interactions, supporting nuanced data analysis and decision-making processes.

‍

‍
Foundation models

‍

We are agnostic re which foundation model we use. If you're curious as to which datasets are used to train models, see this list. We see large langua models as increasingly capable processor machines with different nuances between them. Since models vary in the types of of biases they have, it’s our job to understand their evolving nature and ensure they are used at the right moment in our architecture. For more on bias read this.

So far, our architecture has consistently surpassed our rivals in the multi dimensional facets necessary to create a Synthetic User.
‍

• Emotional Relevance: Ability to resonate emotionally with users, increasing engagement and satisfaction.
• Moral Alignment: Adherence to ethical standards, ensuring interactions are trustworthy and safe.
• Creativity and Groundedness: Generation of novel, contextually relevant content that remains factually accurate.
• Five-Factor Model: Integration of personality dimensions (Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism) for more personalized interactions.

‍

Dealing with inception

‍

Models are increasingly using synthetic data for training. This leads to intriguing questions as these models create a kind of self-referencing reality, similar to a dream within a dream. Consider Hollywood kisses, which are mostly based on kisses from previous Hollywood movies. Eventually, they diverged from a natural kiss. More importantly, they influenced how people kiss worldwide. The imagined becomes reality.

‍

When we use synthetic data to train new models, we must make sure we stay connected to reality. Knowing which models to rely as the backbone to our Synthetic Users is a constant endeavour of comparison and evaluation. That is why we are constantly comparing. Always striving for the best Synthetic to Organic parity.

‍

‍

‍

RAG

‍

The RAG layer plays a pivotal role in tailoring Synthetic Users to specific business needs by integrating domain-specific knowledge bases. This enables dynamic content generation that is both contextually relevant and aligned with business objectives.

‍

Customization through the RAG layer involves:

‍

• Fine-tuning: Adjusting model parameters to align with the nuances of the business context.
• Adaptability Assessment: Evaluating the Synthetic Users' ability to navigate unforeseen situations and their learning agility from these interactions.

‍

The integration of RAG enhances the Synthetic Users' utility, ensuring that they serve as effective tools tailored to specific business requirements.

‍

‍

In the evolving field of user experience, the introduction of generative AI hasn't quite lived up to its transformative potential. Many companies have merely attached AI to existing products without fundamentally enhancing the user journey. Instead of offering isolated features, we are pushing for a new paradigm in UX, where AI agents provide substantial, end-to-end support across various tasks.

This transition from superficial AI integration to deep, meaningful interactions that span the entire customer journey lies at the core of what Synthetic Users is about. This involves AI agents actively assisting with cognitive, creative, and logistical tasks, transforming user interactions from mere facilitation to a comprehensive partnership.

This vision of the future is not just about using AI; it's about integrating it in ways that profoundly enhance user engagement and satisfaction and ultimately bring about the best Synthetic to Organic parity.

‍

‍

‍

‍

‍