Capability
Can an open model reason through a difficult task and still produce a working result?
Research
Experiments with a useful outcome.
SLAI studies open models as systems for real work, then publishes the findings, methods, and tools that can move the field forward.
Control
Can people choose both the depth of thought and the amount of work the agent performs?
Usefulness
Can the research leave the lab as a model, product, framework, dataset, or reproducible method?
Published research
From the lab.
Controlling More Than Thought
Reasoning effort controls how deeply a model deliberates. Work effort controls how far an agent carries the task. Useful systems need both dials.
Read article
The Work Begins When the Prompt Ends
A useful agent does not race from prompt to answer. It explores the project, tests its understanding, acts, and checks what actually changed.
Read article