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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Shitong, Fang, Chenhao, Larson, Derek, Pochareddy, Neel Reddy, Rao, Rajeev, Zeng, Sophie, Peng, Yanqing, Summer, Wendy, Goncalves, Alex, Pudota, Arya, Robert, Hervé
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915413040824320
author Zhu, Shitong
Fang, Chenhao
Larson, Derek
Pochareddy, Neel Reddy
Rao, Rajeev
Zeng, Sophie
Peng, Yanqing
Summer, Wendy
Goncalves, Alex
Pudota, Arya
Robert, Hervé
author_facet Zhu, Shitong
Fang, Chenhao
Larson, Derek
Pochareddy, Neel Reddy
Rao, Rajeev
Zeng, Sophie
Peng, Yanqing
Summer, Wendy
Goncalves, Alex
Pudota, Arya
Robert, Hervé
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17289
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environments
Zhu, Shitong
Fang, Chenhao
Larson, Derek
Pochareddy, Neel Reddy
Rao, Rajeev
Zeng, Sophie
Peng, Yanqing
Summer, Wendy
Goncalves, Alex
Pudota, Arya
Robert, Hervé
Artificial Intelligence
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.
title Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environments
topic Artificial Intelligence
url https://arxiv.org/abs/2507.17289