About PumaAI
PumaAI studies systems that keep more intelligence near the user and make automated behavior easier to understand, evaluate, and control.
Useful AI should not require sending every private thought, document, or interaction to a remote service. Local models create another option, but only when the whole system—hardware, runtime, interface, and fallback—is usable.
Likewise, an agent is more than a model. Its prompts, tools, memory, permissions, and control flow determine what it can do. PumaAI researches the harness as a first-class system.
We prefer small reproducible experiments to broad predictions. A useful research artifact explains its setup, records representative failures, distinguishes measurements from interpretation, and leaves enough detail for someone else to challenge it.
Play is part of the method. Games can make long-horizon behavior visible without hiding complexity behind a single benchmark score.
Founder
Yuriy is the founder of Puma, a private-by-design mobile browser, and leads PumaAI. His background spans engineering and developer relations at Cloudant, Meteor, Parse, and Lyft.
Editorial policy
Research notes are published by PumaAI Research unless an individual author is named. Pages include publication and modification dates. Material updates should describe what changed; unmeasured proposals remain labeled as frameworks or research agendas.
Corrections and research conversations are welcome at [email protected].
Speed, grit, optimism, kindness, and curiosity. We want to move quickly without hiding uncertainty, challenge systems without being cynical, and make technical work understandable to the people it affects.
Puma is remote-friendly and hiring across engineering, research, and product. See current opportunities at puma.tech.