I'm super unfamiliar with limitations surrounding AI mechanics, so I'll just be commenting on the game design itself, assuming the AI works flawlessly.

I REALLY like your game idea. I'm a huge fan of TTRPGs, and this gives off the exact vibe I've been wanting from a TTRPG turned video game for ages now. I think you've given quite a lot of thought to the narrative and setting elements and have a lot of really good content to work with. That being said, I'm imagining this game from the position of someone with no AI experience. I think you could do a good job using only scripted events and variations of them, and even then, I think this would fall into its own social-strategy roleplaying game genre. some more detail would be needed in your GDD before usage, like menus. While you told the concept of the different actions, how they will actually function is also critical information to have. Very good idea overall. 

On reading your GDD I'll preface my comment saying I understand if time was a significant constraint; it was one for me too.

Your game does have elements of social deduction in combination with responsive/semi-intelligent dialogue. To make a truly "AI-powered" dialogue system may take much more work than using certain pre-defined values and "line pools" the characters can select from to add just enough variety through a game loop without being overbearing to manage/train.

The game makes me think of a combination of the Salem Witch Trials online game with (oddly enough) dating sim-esque dialog interaction and status adjustment features. I made a similar genre/game comparison or association in my doc so I can respect the parallels between those games and yours. However, much like how I tried to present mine perhaps it's not wholly a new genre.

The length of the gameplay loop is intriguing to note. It reminds me of an expected gameplay session time of most Turn-Based/RTS hybrid games like Total War. 

The social events you have planned in your game system gives it good variety potential and gives many factors to consider. Though in that depending on how gameplay is or isn't tutorialized/introduced players may wander into it confused when they're getting backstabbed by the Duke of Doughnuts after they called him a "fat man" on the first night.

All this to say, I think this game has promise as a standalone title and good inspiration behind it! With a little more visual reference and gameplay loop walkthrough it can shape up to be something awesome!

So I'm filing this under "Brilliant if it works, but I have serious doubts whether it would work." Not because I doubt your design chops at all--it's just fundamentally I'm not sure either the human players or the algorithms will behave the way the concept requires.

My personal observation is that, once you take the human element out of a social game, what you have is no longer a social game, but a strategy game, more like, eg, Crusader Kings. First because it's no longer symmetrical--the computer doesn't know it's playing a game and won't be gaming the player the way the player is gaming it. And second because, even if the gameplay is truly identical, players will act differently if they know it's not another human. (For example, players will test the algorithm and try to find stock phrases that always yield a favorable response, something that's inherently not possible with humans.)

That said, all that is just my skepticism, and by all means, prove me wrong and I will happily eat crow, because it is a very cool idea. I like your setting and a lot of the details of the concept, like making the interface resemble a tabletop game. And it definitely rises to Willem's challenge, because if it works, it'll definitely be a whole new thing that many other games are guaranteed to copy.

I also liked the write up about how it's genre defining, though it's a little like cheating by telling us how it's a new genre. :)

I also wanted more -- somehow this felt incomplete, though I'm not sure why.

I'm curious about the AI usage. How will you program the character AIs? Would each have unique aspects or all the same algorithm?

There are a bunch of submissions and I wanted to give feedback to everyone, so I'm going to list some strengths and weaknesses that I perceive from the GDD's in this challenge (take with a grain of salt, I recognize the challenge this jam theme + time limitations, especially during a holiday weekend).

Strengths: I appreciate your section about why this game would qualify as genre-defining, and I appreciate the thought that went into creating a social deception/deduction game that can be enjoyed alone (although comparing to Among Us is a little misleading, its main focus is social deduction). 

Weaknesses: I would also like to see more technical descriptions behind how your status systems work, and how they impact other systems. While there are fairly simple mechanics in this game, I feel like systems interactions are much more complex than currently addressed, so I can't immediately imagine how these will work, some of them seem incredibly difficult to implement.

Overall: if you manage to make this game work, I will play the hell out of it.