Real environments
Research questions come from operating work rather than constructed demonstrations.
We study agents, adaptive systems, and the forms of software developing around them.
Today's software encodes a workflow and asks people to follow it. As agents become more capable, that relationship can change. Systems can learn from the people they serve, reshape themselves around real work, and improve without waiting for another product release. The model supplies general intelligence. The surrounding system gives that intelligence a place, a memory, and a way to change. Today, that system is usually called a harness. We think it will become a new form of software.
Rifty maintains a private agent system that operates across tools, companies, and work that continues over time. It gives us a place to study what happens when tasks are ambiguous, requirements change, and the effects of a decision may not appear until days later. The system is not publicly distributed. We publish the parts that can stand on their own: findings, methods, evaluations, guides, and experimental tools.
Research questions come from operating work rather than constructed demonstrations.
Failures, corrections, and changing requirements become new experiments.
Work that generalizes beyond the private system is separated, documented, and published.
Findings and arguments from our work on adaptive agent systems.
Closer examinations of system behaviour, experiments, and design choices.
Methods for people building systems around their own work.
Ways to test memory, adaptation, reliability, and long-running agency.
Small releases for exploring one idea without adopting an entire system.
Problems we do not yet have good answers to, published so others can investigate them too.