Active Discovery of Hidden Business Cascades under Rule Drift
Hidden business dependencies and cascades as operational rules change.
Research on how AI agents receive authority, stay within it and answer for every effect.
As AI moves from answering to acting, the hard questions move with it: who authorized this step, what the agent knew when it acted, and how its work is checked, stopped or recovered. We study these questions with formal models, reference implementations and reproducible evaluations, and publish the results as open working papers and an open protocol.
Recent working papers follow agents through changing business rules and evidence: assembling time-consistent context, scheduling around approvals, repairing memory and task graphs, and recovering from partial execution. Others cover tool dependencies, multilingual business semantics, and how authority and budgets carry through delegation.


Recent papers from Accentrust research, presented with their relationship to the systems and projects they extend.
Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution
Runtime Authorization for Resources Acquired by AI Agents
Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBoundHidden business dependencies and cascades as operational rules change.
Time-consistent evidence drawn from documents and transactional records.
Context scheduling when cached information expires and human approvals take time.
Business-semantic consistency, contract checks, and failure diagnosis across languages.
Tool discovery that accounts for dependencies in changing enterprise catalogs.
Our working papers group around four questions every governed agent has to answer: what it may do, how its effects are checked, what it knows, and how it recovers.

Authority bound to what the current request justifies, checked again for the resources and subgoals an agent acquires, and revoked cleanly across delegated and asynchronous work.

Draft-first writes, server-verified action claims and dependency-closure binding, so every tool effect is checked against current facts before it lands.

Time-consistent evidence across documents and transactions, context scheduled around approvals, and memory, plans and business meaning repaired as rules and evidence change.

Resuming after partial execution and ambiguous tool outcomes, clarifying within a shared question budget, and measuring how memory, approval, execution and recovery interact.
Projects are where the research becomes working software. OpenPort turns our governance work into an open protocol any runtime can implement.

An open protocol for reliable AI tool access—authorization-aware discovery, draft-first writes, and stable responses that hold up in real workflows.

We study the moment an AI system’s intention becomes an effect, and design the controls that make that moment accountable.
We start with the workflow, not the demo. We study the moments where information is fragmented and responsibility is real—handoffs, approvals, and decisions that have consequences in the world.
We state what each result proves and the conditions it holds under, so others can build on it with confidence.
We treat systems as living. Evaluation, monitoring, and feedback loops are how prototypes become practice—and how they keep improving as data and needs change.
We publish openly: working papers anyone can read, an open protocol with public code, and research with academic partners.
Academic partners


