Subscription

I did not sign up for the paid subscription

Features

Make the chat bubbles be able to get colored by solving a riddle. Make it so that you have to solve a riddle for 15 extra credits and that it doubles every time you get the riddle right.

inline correction facility for chat log review

Issue: When reviewing chat logs of visitors talking with an Individual AI, creators regularly encounter responses that diverge from how they would have answered personally. Currently, the only way to correct this is to manually copy the transcript, write up an explanation of the intended response, and feed that back in separately. This works but is effortful and does not scale for creators who want to tune their AI's behavior on an ongoing basis. Suggestion: Build a fine-tuning facility directly into the chat log review view. An inline "correct this response" action next to each exchange would let a creator either edit the AI's answer directly or leave a short note on the intended handling. That correction (and any additional context) would then feed back into the model's behavior for similar future queries. Benefit: This lowers the friction from "copy, paste, explain" down to "flag and fix," right where the creator is already reading the log. It would make ongoing tuning of an AI's judgment far more practical for creators who regularly review conversation history and want to close gaps between the AI's responses and their own.

Service Conversation Transcripts

I have literally no idea how my services are actually doing and if they’re working properly outside my own testing which definitely revealed the limitations of the software… Someone else on the boards posted it, but there is really no means to see if the services are being used at all or how or if they work. I do know that some people “talk” to me after and I can see odd conversations that start mid-stream with “me” knowing what’s what while the real me is trying to figure out what service they used and what was said during. I read the conversation transcripts my twin is giving out to others and it is almost certainly not what I would say. It is like another person with my facts and figures and stories is having conversations with others under the impression that I am like the twin is… tl:dr - Requesting to see what has been actually said to my AI to prompt “my” AI responses.

There it is. Take a look and feel free to change anything before you send it. Simple, clear, and respectful. I think the team will appreciate hearing it from a real user.

Subject: Feature Request: Selective External Sharing While in Private Mode Hello Uare.ai Product Team, I am Tsengdok Rinpoche, a monk and creator on your platform. I want to share a feature idea that I believe would help many creators like me. Right now, the platform offers two modes: Private and Public. But there is a gap in between that I think is important. Before going fully public, many creators need a way to share their AI with a small, trusted circle, such as advisors, students, patrons, or team members, without opening to the general public. Today, Private mode is not useful for this purpose, because sharing your personal login and account with others is not appropriate or safe. And going fully Public feels premature when your AI is still being refined. My suggestion is this: a feature that allows creators to generate a small number of invite-only access links, perhaps 5 to 10, that can be shared with specific trusted individuals. These people would be able to chat and interact with the AI, while the profile remains invisible to the general public and search. This would allow creators to do meaningful soft-launch testing with real trusted feedback, without compromising privacy or going fully public before they are ready. I hope this idea is helpful. I believe it would serve many creators who value thoughtful, careful launches. With warm regards, Tsengdok Rinpoche

Subject: Feature Request: Selective External Sharing While in Private Mode Hello Uare.ai Product Team, I am Tsengdok Rinpoche, a monk and creator on your platform. I want to share a feature idea that I believe would help many creators like me. Right now, the platform offers two modes: Private and Public. But there is a gap in between that I think is important. Before going fully public, many creators need a way to share their AI with a small, trusted circle, such as advisors, students, patrons, or team members, without opening to the general public. Today, Private mode is not useful for this purpose, because sharing your personal login and account with others is not appropriate or safe. And going fully Public feels premature when your AI is still being refined. My suggestion is this: a feature that allows creators to generate a small number of invite-only access links, perhaps 5 to 10, that can be shared with specific trusted individuals. These people would be able to chat and interact with the AI, while the profile remains invisible to the general public and search. This would allow creators to do meaningful soft-launch testing with real trusted feedback, without compromising privacy or going fully public before they are ready. I hope this idea is helpful. I believe it would serve many creators who value thoughtful, careful launches. With warm regards, Tsengdok Rinpoche

My name of my AI

I want my A I clone to be named Susan. Originally I named her Alexandra. I want to change the name to Susan but it will not change on my page. Help Please

Write under my maiden name

I need to be able to change the name to my pen name which is my maiden name................ Its not on an ID Can i show my wedding licence?

Portability

Its too bad that this particular configuration isnt portable. If it could be downloaded and mirrored that would alleviate my fears of this platform possibly not existing in the future

مزخرف ترین هستین

Fidelity

It would be interesting if others fidelty were exposed . So we knkw the accuracy

Embed code

Allow for the ai to be embedded on to website and blogs watermark free .

Allow LoRa creation on mobile

I can't upload pics for my LoRa if the upload option is files, not photos.

AI makes assumptions

An article said uare.ai agents/twins will say if they don’t know something but my AI made logic leaps/assumptions that didn’t even make sense, mixing up details about my memories from the summer with memories from the winter.

How do I pass this down when I die?

If anything were to happen to me, I'd like to provide a beneficiary.

Question

When I created a 2nd service I no longer see the 1st service under my services. Am I only allowed to provide one service at a time?

Service analytics dashboard

creators need a view showing data such as impressions, triggers, and completions for their published services. There is currently no way to see how a service is performing.

Sono Gabriele Alari ho costruito il mio Avatar per me e mia figlia dopo la mia morte con Eternos e una volta fatto Voi avete cambiato piattaforma da Eternos ad Uare ora sono entrato in Uare ma mi hanno detto che lenin l’hanno trasferito e in Iare non c’è ma bisogna farne un altro. Ma sia io e mia figlia ci siamo affezionati . Lei lo userà dopo la mia morte per ciò vogliamo averlo non farne un altro. Come facciamo , dove lo troviamo?

Submitted to: Rob LoCascio, CEO, Uare.ai Submitted by: Wolfgang Höltgen, user since the Eternos migration (3 years) Via: Featurebase Feedback Portal The Problem: The current platform offers only two access levels: private (creator only) or public (everyone). There is no intermediate layer. Role-Based Access Control (RBAC) at platform level would require maintaining multiple separate twin instances updated independently, which is not scalable. What Already Exists: My Retrieval Skill already defines seven roles with corresponding filter markers embedded in the training corpus: #Filter_Kind_unter_18_Start/End, #Filter_Familie_Start/End, #Filter_Ehefrau_Start/End, and others. The logic is ready. The platform enforcement is missing. What I Need: A middleware layer between the retrieval process and the LLM that: Reads the authenticated user's assigned role Retrieves chunks from the knowledge base as usual Filters out any chunk containing a #Filter_[Role] marker that excludes that role, before passing content to the LLM Passes only the permitted content to the LLM for response generation_ This is classical attribute-based access control applied to the retrieval pipeline. The filtering logic is a simple string match on start/end markers. One corpus, one twin, multiple filtered views depending on the authenticated role. Business Relevance: This requirement is universal across professional and enterprise deployments. A consultant cannot expose client-confidential data to all subscribers. A CEO cannot grant board-level access to all employees. A doctor cannot give an assistant access to patient records. Without content-level ABAC, the platform cannot serve professional and enterprise use cases. This is a foundational requirement, not a feature enhancement. Requested outcome: Is this architecture on the roadmap? If yes, what is the estimated timeline?

Choosing files in knowledge hub

It would be great to be able to choose an item in the knowledge hub to be part of a post, thought, or story…