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
Starting with a blank canvas can be intimidating, but providing prompt starters can help individuals overcome this initial hurdle and jumpstart their creativity.
Letting people select text to ask follow-up questions provides immediate, context-specific information, enhancing AI interaction and exploration.
AI collaboration agents can act as writing partners that assist people by enhancing their content through transparent, easily understandable suggestions, while respecting the original input.
Voice interfaces should dynamically adapt to user interruptions, seamlessly incorporating them into the conversation ensuring a fluid and responsive dialogue.
Spatial prompting integrates spatial relationships into prompts, offering a novel approach to manipulate concepts. This dynamic approach can lead to more intuitive and creative outcomes.
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.