Evaluate predictions
When an observation is added to the context from an implicit action and a prediction is made, users should be able to easily evaluate and dismiss it.
When an observation is added to the context of the AI system or a conclusion is reached, I want to evaluate and dismiss it easily, so I can ensure the information is accurate and relevant to my needs.
- Transparency in Knowledge Gathering: Make it easy for users to understand the factors that influence and shape the knowledge being gathered. When new information is added to the context, clearly communicate this to the user.
- Control over Assumptions: Provide a simple way for users to dismiss or challenge assumptions to ensure the accuracy and reliability of the knowledge base.
More of the Witlist
Voice interfaces should dynamically adapt to user interruptions, seamlessly incorporating them into the conversation ensuring a fluid and responsive dialogue.
Embedding models can rank data based on semantic meaning, evaluating each individual segment on a spectrum to show its relevance throughout the artifact.
AI excels at classifying vast amounts of content, presenting an opportunity for new, more fluid filter interfaces tailored to the content.
Letting people select text to ask follow-up questions provides immediate, context-specific information, enhancing AI interaction and exploration.
Automatic model switching in AI can boost efficiency by selecting the most appropriate model for each query, ensuring a balance between quick and accurate responses.
Generative AI can provide custom types of input beyond just text, like generated UI elements, to enhance user interaction.