Visual grounding
Using the source input as ground truth will help trust the system and makes it easy to interpret its process and what might have gone wrong.
When checking data, I want to be able to see how the system arrived at its answer, so I can trust the data and identify any potential errors in the process.
- AI Transparency and Explainability: Make AI systems transparent and understandable by explaining how and why decisions are made.
- Multimodal Context: In this example we used the context of an image of a receipt, but it can also include other modalities, such as audio.
More of the Witlist
Guide users to understand what makes a good prompt will help them learn how to craft prompts that result in better outputs.
AI actions often take time to complete. To improve user experience, use descriptions of what is happening combined with basic animations that represent different types of actions.
Proactive agents can autonomously initiate conversations and actions based on previous interactions and context providing timely and relevant assistance.
An intelligent assistant that analyzes emails to identify questions and feedback requests, providing pre-generated response options and converting them into complete and contextually appropriate replies.
Voice interfaces should dynamically adapt to user interruptions, seamlessly incorporating them into the conversation ensuring a fluid and responsive dialogue.
Presenting multiple outputs helps users explore and identify their preferences and provides valuable insights into their choices, even enabling user feedback for model improvement.