Intelligence takes root, and the world bears fruit.
Latest research
All research- The compliance paradox: Rule conflicts in Asimov's Three Laws and in AI behavior guidelinesEven as AI gets better at following rules, failures remain when the rules conflict with one another. Drawing on Asimov's robot stories, this paper identifies three ways in which rule conflicts surface as failures and four ways of resolving them, and examines them against the revisions of OpenAI's Model Spec. It shows that resolving a conflict does not eliminate its cost but moves it elsewhere, and proposes a procedure for checking new or changed rules for conflicts with existing ones.
- Organizational memory for interchangeable agentsIn organizations where AI agents do the work, models and agents are replaced frequently. This paper proposes keeping memory in documents the organization manages rather than inside any model, and turning working records into verified knowledge in stages. It presents a five-stage flow (Trace, Episode, Research, Review, Library) and its invariants, then reports observations from use, a discussion, and limitations.
- Allocating human attention in agent-led software developmentWhen AI agents carry software development from planning through verification, where to spend limited human attention becomes a central design question. This paper proposes AFHL (Agent-first, Human-last), a method that concentrates human involvement in a final evaluation of the user experience, and describes its structure: two working modes and a rule for reporting verification status. It also discusses the risks this allocation carries and the limits of its current application.
What we work on
Ideas get better in the open.
Our research on the latest AI is open for anyone to read. Ideas go into Notes, findings into Papers, and each one is read, questioned, and refined, version by version.
- Organizational memory
- AI-native management
- Human–agent collaboration
Design is how it works.
The way a button answers your touch. A flow you never get lost in. We design the parts you can’t see, too.
- Design system
- UI / UX
- Brand
From research to running software.
We turn ideas from our research into apps people use every day. We build them with Moss, a system that records each task and feeds it into the next, and AFHL, a way of working that divides the work between agents and people.
- Moss
- AFHL
- iOS & macOS apps
Products
All productsSnapCap
Available on the Mac App Store
One click opens your iPhone’s camera. The photo lands on your Mac’s screen, ready to drag into any app.
Learn more

We are developing several more apps and will release each one as it is ready.

