partnership
Provenance shouldn’t be a claim. It should be a proof.
Algedonic is working with Dr. Renée Miller — Canada Excellence Research Chair in Data Intelligence at the University of Waterloo — to give agent intent the same formal rigor the database world spent decades building for data.
the partnership
Formal rigor, meet algebraic infrastructure.
Every agent framework today asks you to trust that a tool call did what it says it did. UIR — our algebraic grammar for portable agent intent — was built to end that trust exercise. Its core bet: a tool call doesn’t just perform an intent, it witnesses it, and that witness is part of the intent’s identity, not a log line bolted on after the fact.
That bet needs more than good design. It needs formal grounding in data integration, schema mapping, and provenance — the ground Dr. Miller and her group have been standing on. So we’re building UIR’s next chapter with her, not alone.
the researcher
Renée Miller has spent decades on exactly this class of problem.
Dr. Renée J. Miller
Canada Excellence Research Chair in Data Intelligence
Cheriton School of Computer Science, University of Waterloo
Renée Miller’s research has spent decades on one of computing’s most stubborn open problems — how to integrate, exchange, and make trustworthy sense of large volumes of complex, heterogeneous data — and turned it into practical systems the field actually uses. Her recent work on data and model lake management is the same shape of problem UIR needs solved next, applied to a different kind of lake.
Fellow, Royal Society of Canada · PECASE recipient · NSF CAREER Award · Foundational work on provenance semirings, schema mapping, and data exchange · ICDE 2026 keynote on Model Lake Management
the research
Three potential directions, one thesis at a time.
The collaboration is structured as co-supervised PhD research — Algedonic providing the systems and roadmap context, Dr. Miller’s group providing the formal rigor and publication path.
DIRECTION 01
Provenance Semirings for Agent Intent
Giving UIR’s tool-call witness principle a real mathematical backbone, extending provenance semiring theory from queries to agent action traces.
DIRECTION 02
Intent Exchange as Data Exchange
Treating the translation of intent across MCP, A2A, and ACP as a schema mapping problem, with the correctness guarantees data exchange theory demands.
DIRECTION 03
Capability Discovery over Tool Lakes
Adapting data lake discovery so agents can find the right tool for a given intent — out of thousands — at scale.
why it matters
SG
“Trust in agent systems shouldn’t be a matter of taking someone’s word for it. It should be provable. That’s the whole point of building this with people who’ve spent their careers proving exactly this kind of thing.”
— Sandeep Gopisetty, Founder & CEO, Algedonic
get involved
Two ways in.
For prospective PhD students
We’re looking for students who want their thesis to matter twice — once as rigorous, publishable research, and once as infrastructure that ships. If a formal-methods, database-theory, or IR/ML-systems background sounds like a fit, we want to hear from you.
For partners, reviewers & press
This collaboration is one signal among several that UIR is being built the way infrastructure should be — reviewed, argued with, and stress-tested by people who’ve spent their careers getting this exact class of problem right.
