KUALA LUMPUR, July 10 (Bernama) -- RegASK, a regulatory intelligence for consumer goods and life sciences provider, has launched the industry’s first agentic artificial intelligence (AI) architecture built for regulatory operations.
RegASK Chief Executive Officer and Co-Founder, Caroline Shleifer said the new AI system gives compliance teams the executional agility needed to navigate market entry and regulatory risk.
“It is a critical advantage for making smarter decisions in high-stakes, highly regulated environments,” she said in a statement.
Meanwhile, its Chief Product and Technology Officer, Amenallah Reghimi said the company’s goal is to simplify complexity stating: “By assigning focused tasks to AI agents and orchestrating them efficiently, we are reducing operational friction and helping teams respond faster to evolving regulatory demands.”
The new architecture pairs RegASK’s vertical large language model (V-LLM) with specialised AI agents to deliver personalised insights and streamline how teams find, understand, and act on regulatory information.
These agents are capable of executing distinct regulatory tasks such as document retrieval, summarisation, translation, and risk assessment. A coordinating ‘project manager’ agent oversees task execution, while an evaluator agent validates outputs to ensure reliability.
Trained on millions of regulatory data points, the embedded V-LLM delivers faster and more relevant outputs by understanding domain-specific context. This architecture also supports multi-step workflows and offers deeper automation across compliance tasks.
RegASK has also introduced a redesigned user interface featuring enhanced regulatory change tracking and customisable alerts, helping teams identify and act on critical updates with greater speed and accuracy.
Designed for interoperability, the architecture supports emerging AI standards such as the Multi-Agent Communication Protocol (MCP) and Agent-to-Agent (A2A) collaboration, positioning RegASK to integrate seamlessly with external platforms for broader enterprise deployment.
-- BERNAMA