>I am building a therapy bot and I need help with developing it

Best of luck, no doubt something needed. Many other big teams working on it.

Check out: https://developers.google.com/health-ai-developer-foundation...

Or you can look chatgpt and their 'safety' stuff around people using chatgpt for therapy and friendship.

There's obviously many literal therapy bots: https://ai.nejm.org/doi/full/10.1056/AIoa2400802

https://www.trytherabot.com/ is the above one that's funded by microsoft.

Personally? I wouldnt even consider trying to go down this path to compete against these folks.

I need a team of coders to help me build the bot and I am building a focus group of mental health experts (therapists and psychology grads) to help me fine tune the bot to medical perfection

This is one of the more concerning LLM use cases I would say is not a good idea. Most LLMs I’ve tested have the DSM-5 and other psych texts baked in. The problem I see with the idea is that they can’t proof their results. These inference engines can do sentiment analysis, which opens up a really good tooling opportunity for aiding a trained professional. What I see being problem though is that it’s too easy for a lay person to taint the context in ways the LLM can’t recover from. Also an LLM will have a really hard time calling someone out if they are blatantly lying to it.

Good luck with the massive liability you'll be incurring.