Agentic-Workflows are applicable to a variety of business process like sales, marketing, customer support, HR, or Finance. For now, let’s consider the Swiss (or any) banking sector, which faces a constant influx of new regulations covering everything from anti-money laundering (AML) and Know Your Customer (KYC) to data privacy and capital requirements. Traditionally, staying compliant means manual review, extensive impact assessments across countless internal policies, and painstaking coordination to implement changes — a notoriously slow and costly process.
This is where Agentic Workflows shine, enabling what we can call an “Agentic-Regulatory-Radar”. We will introduce the Agent as a technical concept later, for now, just imagine it as an autonomous AI-helper. Something like a ChatGPT Model that works on its own based on a set of pre-defined instructions without you having to chat with it:
- Research-Agent: This agent continuously monitors the websites of Swiss regulatory bodies (e.g., FINMA, SNB) and public news sources. It generates a weekly summary of key regulatory changes.
- Compliance-Agent: The weekly summary then goes to the Compliance-Agent. This agent scans the bank’s internal databases (directives, contracts, manuals) to identify all affected products, services, systems, or processes, producing an impact report.
- Policy-Writer-Agent: Both the summary and impact report are sent to the Policy-Writer-Agent, which drafts proposed policy amendments by cross-referencing the regulatory summaries with the identified internal assets.
- Human-in-the-Loop — Compliance Officer Review: A human Compliance Officer receives a weekly brief detailing the changes, impacted policies, and suggested amendments. They provide expert feedback and request refinements, leveraging their deep understanding of legal and business implications.
- The task then goes back to the Policy-Writer-Agent who then incorporates this feedback and resends the draft to the human expert for final review.
This example clearly illustrates how repetitive, cognitive tasks — like reading, analyzing, decision-making, and writing — could be partially handed off to AI agents, significantly transforming efficiency in critical business functions.
