TypingMind for Teams

The UX of having lots of SSO users join the platform, but experiencing a login error until we manually bump the seat limit, is not great. On the other side, provisioning a buffer ahead of time just to avoid this possibility feels quite wasteful. Consider having a floating usage-based seat limit for teams configured with SSO, and billing at the end of the month based on how many users were actually active, a la Slack or other similar usage-based tools.

Extract text from PDFs while inserting markers for actual PDF viewer page numbers (e.g., [Page 5] at the start of each page). Pass these markers into the prompt text, so the AI can accurately reference the same page numbers seen in a PDF viewer.

I'd like to request a feature that allows AI agents to trigger and communicate with other AI agents directly from within their system prompts. Currently, the platform allows users to tag an agent in the chat interface, but there's no native capability for agents to autonomously initiate communication with other specialized agents when needed. This would enable creating hierarchical or collaborative agent networks where: A primary agent could recognize when it needs specialized knowledge The primary agent could trigger a secondary agent with specific expertise The secondary agent would provide its specialized input The primary agent would incorporate this input into its final response Similar to how users can use "@" in the chat interface, agents should be able to reference other agents within their system prompts with directives like: If you need code information, request data from @CodeAgent This would extend the current multi-agent workflows to be more autonomous and embedded within the agent's decision-making process.

For the purpose of Digital Security, Legal, and internal KPIs, I would like the TypingMind API to be updated to allow admins access to pull chat conversations from TM storage databases.

Redesign the chat logs interface in the admin panel to display a comprehensive table view with additional columns Token consumption in/out, Training datasets used

I would like to use one instance for both a public facing chat bot embedded on the website using a global system instructions and then have different set of system instructions (or AI Characters that override instructions) for logged in users. For my use case I would not like for Public users to access more advanced and complex chat features, such as the sidebar, prompt library, etc. Currently there is no way to accomplish what I am looking to do without another entirely dedicated instance just for the Public but this feature request would open up an entire new world.

Currently the only way to find out what agents a user has access to is by accessing all agents and verify users associated to the agent. This makes user/agent association and management very cumbersume - or literally impossible with 50+ agents. Suggestion: Add all agents accessible by user to the user overview page and make it possible to pause or delete agant from the user overview page. The current setup becomes unmanageable with increasing number of users paying for access to dedicated agents, or switching to different agents depending on changing coaching goals month-over-month etc. Or users not renewing coaching contracts, or cards getting rejected, requiring us to pause or cancel access to specific agents. We just need something user-centric, not agent-centric. Thanks

Support voice custom model with different endpoint like whisper-1, tts-1, tts-1-hd. and possibilities to set up it instead of Web API and hard coded Openai Whisper