I’m not interested in the extensive library, cause I believe in the long-run they will be built inhouse.

BUT: I am desperately looking for a tool that I can connect and push the same prompt to 3 LLMs simultaneously (gpt-5, Claude, grok) - because I found that all have strength and weaknesses and comparing the results gives me the best input. But it’s annoying browser switching between the tools.

Is there a way, you could make an output comparison? I.e. I make a prompt, select the models, and you show me the 3 outputs in a split screen? Similar to your board view when comparing prompts?

This alone would be worth the 200$ to me 😄