Researcher proposes ontology-driven framework for enterprise finance LLMs that prioritizes auditability and traceability alongside accuracy, addressing adoption barriers in regulated FP&A workflows.
Continue reading
Researchers audit forensic reconstruction of LLM-agent actions in banking, finding that correct answers don't guarantee proper evidence trails—tool logs and citations often fail to preserve the bin...
Firmcheck and Briefcase Ledger adopt Model Context Protocols to let Claude automate accounting tasks—AML checks, ledger management—without separate logins, raising questions about AI accountability...
As SAP, Oracle, and Workday embed AI agents into financial workflows, MindBridge explores the audit and control challenge: who verifies results when AI handles transaction creation, classification,...
Researchers present a tiered multi-agent framework with DLT audit trails designed to embed regulatory compliance into AI systems for DACH finance, treating regulation as an orientation layer rather...
Researchers introduce Policy-as-Skill, a modular runtime that packages LLM-driven policy decisions with evidence validation, version control, and audit trails—achieving 53.8% exact accuracy on 600 ...