Sonder – self-hosted AI social simulation engine
Narrator mode querying agent internal states is genuinely clever social simulation.

Hand-built decision tree simulates the exact moment recruiters ask for your number.
Job seekers preparing for offer negotiations
Yoodli · Pramp · Big Interview
i kept watching friends take the first number a recruiter said out loud. not because they're bad at this, because nobody actually preps for these calls the way they'd hoped they would, when the recruiter goes "so what are you looking for?", you either say something too low, or you flip it back asking "what's the band?" and whatever they say basically becomes the ceiling anyway.
so i did some research and built a sim for that specific moment. hand-built decision tree. the optimal path borrows from fisher & ury (batna), galinsky (anchoring), and voss (the tactical pause thing).
first scenario is called "the lowball offer". you walk into a cafe. your friend/mentor kofi runs hiring at a series b. offer letter is face-down on the table. $95k base, market's around $130k. before you even flip it over, he asks: what's your walk-away number?
you dont have one. neither did you think of it
four scenes with four choices each, i'd genuinely love to know where the optimal path i designed lands wrong, because i'm sure it does somewhere.
there's a cmu stat that puts the lifetime cost of undernegiotiating at ~$500k. it's a stopper. left it out for now but happy to add it back if people think it earns its place.
Narrator mode querying agent internal states is genuinely clever social simulation.
Clever use of Claude Artifacts to gamify social anxiety practice.
This actually simulates the full write path — WAL to memtable to immutable flush — and animates cascading leveled compactions so you can watch key movement and file counts in real time. The live bloom-filter checks and amplification metrics are the parts that will teach you something immediately; it's clearly built as a learning/debugging sandbox rather than a production profiler.
Isolated NPC agents with bounded knowledge solve the omniscient LLM problem in storytelling.
Single 90-minute scenario without clear path to broader learning platform.
Challenges the Armey Curve theory using live World Bank data and client-side AIC fitting.