Tuna Gül

AI

discit Archive

A prototype "AI ERP": an LLM sales agent qualifies leads and hands orders to an operations agent.

Role
Designer and lead (agent-assisted)
Period
Feb–Mar 2026
Team
Solo (a collaborator drafted the v2 architecture)
Stack
Python · FastAPI · Postgres
Impact
Benchmarked against simulated customers

Illustration of leads from chat and shop channels streaming as particles into a sales agent, with a few unqualified leads peeling away before it and qualified orders passing on to an operations agent that feeds stock levels.

What I did

I prototyped an "AI ERP" in which an LLM sales agent qualifies leads from WhatsApp and Shopify and hands orders to an operations agent that handles stock and production. Simulated customer personas benchmark how well it converts. I stopped the project in March 2026.

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 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.

simengine Research

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