Suggest New Features 💡

Currently chat's are grouped by today, yesterday, past week, and past month. I think it should be grouped by each day, up until a month. So it should be today, yesterday, 12/11/24, 11/11/24... etc etc.

The key parameters users would like to be able to configure are: 1) Temperature: Adjusting the temperature would allow users to control the "creativity" and randomness of the agent's responses, from more deterministic and logical (low temperature) to more varied and exploratory (high temperature). 2) Top P: For OpenAI models, the ability to set the Top P (nucleus sampling) parameter would give users control over the diversity of tokens the model considers, from a broader (high Top P) to a more focused (low Top P) distribution. 3) Frequency Penalty and Presence Penalty: Similarly for OpenAI models, allowing users to adjust the frequency and presence penalties would enable them to encourage or discourage the model from repeating certain words or phrases, or introducing new ones. 4) Response Mode: For Anthropic models, users would like the option to choose between "Full Responses" (more verbose, with explanations) or "Concise" mode (shorter, more direct responses). Providing these customization options would give greater control over the agent's personality and outputs. This level of configurability would significantly improve the flexibility and utility of Custom Agents.

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

Edit a previous message you sent instead of refreshing through the "try again" button and sending your message again, in order to keep things neater and more organized. Also allow single messages to be deleted.

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

<Enter> should not send the prompt, but <CTRL>+<ENTER>. It's so easy to send your prompt inadvertently when all you want is a line feed.

Hi there, Thanks to the new “Auto” setting that automatically chooses the best language model. That's a so great feature! However: After a request finishes, there’s no indication of which model was actually used... I can’t configure a block-list / allow-list to exclude certain models (for cost, latency, or compliance reasons). As a result, it’s hard to debug quality differences, reproduce results, or forecast cost, even if the answers are usually really good to me. This leads to several impacts: • It's totally impossible to trace surprising answers back to a specific model. • It would be harder to maintain consistency in production workflows. • It could lead to potential budget/quotas overruns if a "high-cost" model was silently chosen. • It has a significant compliance risk: some projects must eventually avoid certain models whose... That said, here are some suggestions: Surface the chosen model • Show it in the UI (badge under the answer). • Eventually return it in the API response header / JSON ( "model": "gpt-4o" ) for API users (if this is not the case, i can't check that) Propose a configurable allow / block list • Let users exclude models globally in settings or per-request via a parameter. • Alternatively, let us set a preferred order. Usage analytics • Add a dashboard card summarizing how often each underlying model was selected by Auto mode over time. This could clearly leads to some benefits: • Transparent debugging and reproducibility. • Controlled quotas and compliance. • Greater trust in Auto mode, leading to wider adoption in professional workflows.

Hi there, I’m on the You.com Pro plan and sometimes hit “quota exceeded” errors without any way to know which limit I supposedly crossed. Maybe am i wrong but it seems that there is no public documentation of: • the exact number of requests allowed per minute / hour / day; • how these quotas differ by model or by agent; • what the UI does when a threshold is reached (soft warning vs. hard block). Because of this opacity it’s impossible to tell whether an error is legitimate, a bug, or an accidental abuse, and it prevents us from integrating You.com reliably into production workflows. Impact • Production jobs can stop unexpectedly. • We purposely under-use the service for fear of being blocked. • Not in my case but: finance / IT of a company could not budget or approve the tool without hard numbers. Here are some of my suggestions: Publish a table of soft & hard limits per plan, per model, per time window. Eventually return clear 429 errors with JSON details, e.g. ```json { "error": "quota_exceeded", "quota": "requests_per_minute", "limit": 120, "retry_after": 47 } ``` Add a real-time usage dashboard showing “XX / YY requests” and 70 % / 90 % warnings. Offer e-mail or webhook alerts when usage crosses configurable thresholds. Provide controlled over-quota “burst” credits or pay-as-you fallback to avoid hard stop. Expose downloadable error / usage logs for auditing and debugging. Not in my use case but eventually: allow sub-quotas per API key so a test project can’t drain the whole company allocation. (Obvious) benefits: • Predictable capacity and cost planning. • Fewer support tickets about unexplained blocks. • Easier enterprise adoption thanks to transparent metrics. • Stronger trust in You.com as a professional platform.

Some times user wants compose complex prompt but the chat input box isn't quite friendly, e.g. they might inadvertently press Enter and send a cut off message, or they want to add bullet points to the message, which isn't very convenient with the current chatbox. It'd be beneficial to provide a dedicated editor interface for user to type complex prompt, for example a small "expand" button at the bottom of the input box to enter this mode.

I'd like to be able to organize my saved chats in to folders.