auroyo
Start a project
AUROYO LAB

Better questions.
More dependable AI.

We investigate how AI-assisted work can stay connected to evidence—and how to evaluate it beyond a single score.

WHAT WE ARE INVESTIGATINGCURRENT FOCUS
01 / SOURCES

What supports
the answer?

How claims in AI-generated or revised text relate to their sources, especially when the underlying evidence changes.

02 / EVALUATION

What does
a score miss?

How evaluation criteria and scoring choices affect the interpretation of model output, and where conclusions become sensitive to the method.

03 / EXPERIMENTS

Can the work
be examined?

Traceable inputs, explicit methods and experiments that can be checked and repeated. Clear limits are part of a useful result.

RESEARCH & ENGINEERING

Ideas need evidence.
Systems need to work.

Research shapes how we question an AI system: what came from a source, what came from a model, and what still needs review. Product development gives those questions a practical setting.

We bring both habits to the work—careful investigation and hands-on implementation. A research question and a working product still need their own validation.

Explore our product work
ON THE WORKBENCH

Work in progress.

Early work is shared with its status and limits.

CURRENT STUDYIN PROGRESS

Source-aware revision
of scientific text.

An ongoing study of how AI revises text when source evidence changes, and how evaluation methods affect our conclusions.

Manuscript submitted. Not accepted or published.
Research by Luyuan Liu.

Discuss the research
A QUESTION IN MIND?

Let’s look
closer.

For research discussions and enquiries about the current work, get in touch.

sales@auroyo.com