How systems change through use.
We study how an AI system can learn from experience without drifting away from the person it serves.
Learning without driftWe study how agents learn through use, retain what matters, and become more useful without losing human direction.
The research moves across six connected areas. Each one asks what an agent needs in order to work well over time, in a particular environment, for particular people.
We study how an AI system can learn from experience without drifting away from the person it serves.
Learning without driftWe study what should survive across tasks and how past experience should shape future work.
Across tasksWe study how agents pursue longer-running work across tools, interruptions, and changing conditions.
Long-running workWe study how to distinguish useful improvement from a system that has merely changed.
Evidence of progressWe study how intent, taste, and judgment can guide a system without being reduced to a settings page.
Human directionWe study what becomes possible when software is formed around a particular person or organization.
Particular systemsRifty maintains a private agent system that works across tools, companies, and tasks that continue over time. It exposes problems that are easy to miss in a demonstration: incomplete information, changing standards, delayed consequences, and decisions without one correct answer.
Research articles, technical reports, and evaluations will appear here once the underlying work is ready to be examined.
Coming soon