Tuna Gül

AI

simengine Research

A library that simulates how a population responds, using LLM personas, and checks every result against simple baselines.

Role
Designed and directed (AI agent team)
Period
Oct 2026
Team
Solo, with coding agents
Stack
Python · scikit-learn · LLM APIs
Impact
Open source (AGPL-3.0)

Code ↗

Illustration of a light swarm of persona dots dropping answers, one column at a time, into a stacked-dot response distribution that fills up to, but never above, a plain ochre baseline curve.

What I did

I built simengine with an AI agent team: a library that simulates population responses (surveys, A/B tests, segments) with LLM personas. Its evidence pipeline compares results with simple baselines, audits them for leakage and memorisation, and can seal predictions before the real answer is revealed, so they cannot be adjusted afterwards.

Results

Its main finding is that pure persona panels rarely beat those simple baselines.

Related

blueprint (bp)

blueprint (bp) Live

A command-line tool that turns AI coding agents into one team that can find and message each other, on one machine or across many.
Ridgeline of smoothed choice distributions in the 11-20 money request game: humans (ochre, front) mostly ask for 17 or 18, while LLM agents under seven persona methods (navy rows) pile up at 19 and 20.

LLM agents in economic games Research

Putting LLM agents into real economics experiments, alone or next to human players, to see what kind of society they form when they share a pot, punish and vote on their own rules.
Illustration of a weekly AI lesson: two white cards, on the left a small 2-4-4-1 neural network with one path from input to output picked out in dark navy, on the right its learning curve falling over training, with twelve evenly spaced checkpoint dots and the last one in ochre.

AI Lead, CompEC

I lead AI at CompEC, Boğaziçi University's computer club, and give weekly AI lessons to students.