> research.ayumi.town init
district://research · accepting proposals

research.ayumi.town

Building AI agents through scientific rigor and controlled chaos. Each agent is designed with intention, tested with rigor, and iterated until it works — or breaks.

// status● accepting proposals
// active3 agents · 1 experiment
// dispatchweekly · sundays
mission

Filling real competency gaps.

We run experiments with autonomous AI agents — building them to fill real competency and skill gaps, not to demo capabilities at conferences.

Hypothesis-driven. Outcomes measured. Failures documented. The work happens in public when it can, in private when it must.

where rigor doesn't reach, we experiment until things work or break. — methodology · §0
methodology

How the lab runs.

01

scientific.rigor

Hypothesis-driven development. Measured outcomes. Documented failures.

02

intentional.design

Each agent has a specific role, a clear boundary, and a kill switch.

03

controlled.chaos

Where rigor doesn't reach, we experiment until things work or break.

active projects

Three residents in trial.

project · 01in trial

felix

A supply-chain intelligence agent. Reads procurement data, surfaces anomalies, drafts vendor outreach. In pilot with two operators.

since 2025.11read brief ↗
project · 02kit released

fonda

The founder agent. A character + 4 skills built to fill the five competency deficits that kill startups. Based on a 2024 study in Frontiers in Psychology.

since 2026.01open the kit ↗
project · 03scoping

dot

Infrastructure agent. Watches the lab, restarts what breaks, files incident notes. Not for production. Not yet.

since 2026.03design notes ↗
project · 04live experiment

textile playbook

Open-source field guide for buying branded apparel in the EU. 9 lessons released as CC BY-SA 4.0, agent-native with JSON endpoints. Testing: can open-source content drive B2B leads?

status
infrastructure
operational
experiments
ongoing
documentation
in progress
proposals