Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environments

TL;DR

The paper introduces Compliance Brain Assistant, an AI conversational agent designed to improve enterprise compliance tasks by intelligently routing queries between fast and full agentic modes, significantly outperforming standard LLMs.

Contribution

It presents a novel query routing mechanism that balances response quality and latency, enhancing compliance task efficiency in enterprise AI assistants.

Findings

CBA outperforms baseline LLMs on key compliance metrics.

Routing mechanism improves accuracy and efficiency.

Balanced mode achieves better results with similar runtime.

Abstract

This paper presents Compliance Brain Assistant (CBA), a conversational, agentic AI assistant designed to boost the efficiency of daily compliance tasks for personnel in enterprise environments. To strike a good balance between response quality and latency, we design a user query router that can intelligently choose between (i) FastTrack mode: to handle simple requests that only need additional relevant context retrieved from knowledge corpora; and (ii) FullAgentic mode: to handle complicated requests that need composite actions and tool invocations to proactively discover context across various compliance artifacts, and/or involving other APIs/models for accommodating requests. A typical example would be to start with a user query, use its description to find a specific entity and then use the entity's information to query other APIs for curating and enriching the final AI response. Our experimental evaluations compared CBA against an out-of-the-box LLM on various real-world privacy/compliance-related queries targeting various personas. We found that CBA substantially improved upon the vanilla LLM's performance on metrics such as average keyword match rate (83.7% vs. 41.7%) and LLM-judge pass rate (82.0% vs. 20.0%). We also compared metrics for the full routing-based design against the `fast-track only` and `full-agentic` modes and found that it had a better average match-rate and pass-rate while keeping the run-time approximately the same. This finding validated our hypothesis that the routing mechanism leads to a good trade-off between the two worlds.