Realtime voice interfaces
Voice interfaces should dynamically adapt to user interruptions, seamlessly incorporating them into the conversation ensuring a fluid and responsive dialogue.


I want my assistant to really listen and adjust based on where I jump in, just like a human would.


- Natural Interaction: Creates a more natural conversation experience by allowing interruptions while keeping the right context by removing interrupted output.
- Improved Responsiveness: Ensures AI can quickly adapt and pick up on changes and feedback in conversation, enhancing the flow of the conversation
- Contextual Understanding: By understanding the reason behind the interruption, the AI can tailor its continuation of the conversation to align with the user’s intent, maintaining relevance and coherence.

More of the Witlist

Comprehend and compare large documents by visualizing embeddings and their scores, enabling a clear and concise understanding of vast data sources in a single, intuitive visualization.

AI excels at classifying vast amounts of content, presenting an opportunity for new, more fluid filter interfaces tailored to the content.

Proactive agents can autonomously initiate conversations and actions based on previous interactions and context providing timely and relevant assistance.

Ordering content along different interpretable dimensions, like style or similarity, makes it navigable on x and y axes facilitating exploration and discovery of relationships between the data.

Starting with a blank canvas can be intimidating, but providing prompt starters can help individuals overcome this initial hurdle and jumpstart their creativity.

LLM’s are great at organizing narratives and findings. It's helpful to see the sources that support these conclusions, making it easier to understand the analysis and where it comes from.