Automating the Enterprise with Foundation Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wornow, Michael, Narayan, Avanika, Opsahl-Ong, Krista, McIntyre, Quinn, Shah, Nigam H., Re, Christopher
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929336773246976
author Wornow, Michael
Narayan, Avanika
Opsahl-Ong, Krista
McIntyre, Quinn
Shah, Nigam H.
Re, Christopher
author_facet Wornow, Michael
Narayan, Avanika
Opsahl-Ong, Krista
McIntyre, Quinn
Shah, Nigam H.
Re, Christopher
contents Automating enterprise workflows could unlock $4 trillion/year in productivity gains. Despite being of interest to the data management community for decades, the ultimate vision of end-to-end workflow automation has remained elusive. Current solutions rely on process mining and robotic process automation (RPA), in which a bot is hard-coded to follow a set of predefined rules for completing a workflow. Through case studies of a hospital and large B2B enterprise, we find that the adoption of RPA has been inhibited by high set-up costs (12-18 months), unreliable execution (60% initial accuracy), and burdensome maintenance (requiring multiple FTEs). Multimodal foundation models (FMs) such as GPT-4 offer a promising new approach for end-to-end workflow automation given their generalized reasoning and planning abilities. To study these capabilities we propose ECLAIR, a system to automate enterprise workflows with minimal human supervision. We conduct initial experiments showing that multimodal FMs can address the limitations of traditional RPA with (1) near-human-level understanding of workflows (93% accuracy on a workflow understanding task) and (2) instant set-up with minimal technical barrier (based solely on a natural language description of a workflow, ECLAIR achieves end-to-end completion rates of 40%). We identify human-AI collaboration, validation, and self-improvement as open challenges, and suggest ways they can be solved with data management techniques. Code is available at: https://github.com/HazyResearch/eclair-agents
format Preprint
id arxiv_https___arxiv_org_abs_2405_03710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automating the Enterprise with Foundation Models
Wornow, Michael
Narayan, Avanika
Opsahl-Ong, Krista
McIntyre, Quinn
Shah, Nigam H.
Re, Christopher
Software Engineering
Artificial Intelligence
Machine Learning
Automating enterprise workflows could unlock $4 trillion/year in productivity gains. Despite being of interest to the data management community for decades, the ultimate vision of end-to-end workflow automation has remained elusive. Current solutions rely on process mining and robotic process automation (RPA), in which a bot is hard-coded to follow a set of predefined rules for completing a workflow. Through case studies of a hospital and large B2B enterprise, we find that the adoption of RPA has been inhibited by high set-up costs (12-18 months), unreliable execution (60% initial accuracy), and burdensome maintenance (requiring multiple FTEs). Multimodal foundation models (FMs) such as GPT-4 offer a promising new approach for end-to-end workflow automation given their generalized reasoning and planning abilities. To study these capabilities we propose ECLAIR, a system to automate enterprise workflows with minimal human supervision. We conduct initial experiments showing that multimodal FMs can address the limitations of traditional RPA with (1) near-human-level understanding of workflows (93% accuracy on a workflow understanding task) and (2) instant set-up with minimal technical barrier (based solely on a natural language description of a workflow, ECLAIR achieves end-to-end completion rates of 40%). We identify human-AI collaboration, validation, and self-improvement as open challenges, and suggest ways they can be solved with data management techniques. Code is available at: https://github.com/HazyResearch/eclair-agents
title Automating the Enterprise with Foundation Models
topic Software Engineering
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.03710