Suggest New Features 💡

I have a Team account with you.com , and while I find it superior in many ways to Gemini Pro and Perplexity for research, it has a significant commercial flaw: ARI. Under the Team, which I had hoped to extend to other analysts in my team, IO get 5 ARI generations in a month. However... when these generations return clearly incorrect data, and I request a search to fix that information, a second ARI credit is used, even when the requirement is relatively minor. A case in point is a research study into ICT project costs, where the staff size of the companies examined was found to be ridiculous. For example, an organisation with tens of thousands of staff was listed as having just 5 staff. Requesting the staff sizes of the listed organisations to be re-researched incurs a full ARI credit. The result is that in practical terms, you.com is not a viable research service: at best it can start a search, but I end up needing to move flawed reports to other services. While it is possible to move reports into other streams of prompts, that provides no research productivity compared to keeping everything inside Gemini or using other AI workflows. I wanted to provide this feedback so that you can reconsider the way the ARI workflow is deployed. A simple fix would be to automatically switch from ARI to a general prompt once a report has been completed. A more effective solution would be to address the ridiculously low monthly research threshold. I'd be happy to pay a higher price, or a per-research call, but not with the current workflow.

Displaying digital documents/information like Claude does with Artifacts, in a panel to the side, would be great.

Just like Google and Microsoft did!

Implement a user-friendly browser extension that acts as an MCP (Model Context Protocol) server, allowing You.com AI to securely access users' local documents without requiring technical setup or compromising data privacy. ## User Value Proposition One-click installation via standard browser extension stores (Chrome, Firefox, Edge) Personalized AI responses leveraging private documents and knowledge bases Complete privacy as files remain local and only relevant snippets are shared with queries Simple interface designed for non-technical users to easily select documents and folders ## Business Value Proposition Maximize user adoption through the familiar browser extension installation process Competitive differentiation with a zero-setup local knowledge integration solution Reduced server costs by offloading embedding generation and vector search to client devices Enhanced user retention through deeper integration with personal workflows Enterprise appeal with straightforward deployment for business users ## Implementation Overview Browser Extension Development : - Create a lightweight MCP server within a browser extension framework - Implement simple document selection UI with drag-and-drop functionality - Handle document processing, embedding generation, and retrieval locally You.com Integration : - Detect when the extension is installed and enable local knowledge features - Add intuitive UI controls for managing document access and knowledge base - Develop query augmentation system to incorporate local context via MCP Deployment Strategy : - Distribution through Chrome Web Store, Firefox Add-ons, and other extension marketplaces - Single-click installation process with clear permission explanations - Guided onboarding to help users select their first documents This implementation makes local knowledge integration accessible to all users regardless of technical ability, while maintaining the benefits of the MCP approach for security, privacy, and reduced computational costs.

Hello, I'm on the team plan. And it seems that while the "Megabytes" were extended all the way up to a generous 50MB, the "file limit" is still quite low. 20 to be exact. I find that odd because a lot of my use cases are "Numerous files with not a lot of context". Let's say for programming questions, a lot of the times you try to separate multiple variables, classes, methods in different files. As such a lot of files have basically 20 lines of code each, which is not a lot of context, but the 0/20 makes it difficult and to simulate my use case I need as I need to basically "Merge the context in" to several big huge files.

While there is a button to "Copy text", but that copy seems to only copy one response. It is certainly desirable to copy the whole chat session (questions and answers).

have you.com respond in audio text to speech please

It would be awesome if premium users could access the new GPT-4o image generation model for editing images once the API is available.

Google Gemmi live has coherent two-way voice chat with one another. if you cuold implement a much more improved voice system that actually has fluent conversations,it wuold make it feel more realistic. can only be used if the user has a mic. i am making a seperate post without upvoting others because others just want the mobile app upgraded,i wuold perfer both (or just the website)

Dear Team, I am requesting for a voice command feature to be included in you.com . The feature should allow users to perform various tasks through voice commands. For example, it should enable users to search for content and open different pages on the website, as well as control the playback of audio and video files. Similar voice commands have been implemented in existing applications such as Google Assistant, Alexa and Siri. The feature should be able to understand user language and convert it into actionable commands. Additionally, the feature should be able to recognize multiple languages and accents. The feature would be used by all types of users who are comfortable with using their voice for controlling their devices. It would benefit users by providing them with a faster and more convenient way of navigating through the website compared to using a mouse or keyboard. I am hoping that this feature can be ready for implementation within the next three months. Please let me know if any additional information is needed in order to better understand my request.