skip to main content
10.1145/3700824.3701093acmconferencesArticle/Chapter ViewAbstractPublication PagesmiddlewareConference Proceedingsconference-collections
research-article
Open access

A Conversational Assistant Framework for Automation

Published: 02 December 2024 Publication History

Abstract

This paper describes the design and implementation of an AI-enabled conversational assistant to enhance the efficacy of Business Process Automation (BPA) tools in the context of IBM's watsonx Orchestrate platform. It leverages the capabilities of large language models (LLMs) to interpret natural language instructions and unstructured documents, thereby simplifying the workflow development process. We detail the assistant framework's architecture, which supports extendable, event-driven interactions and dynamically integrates multiple agents. We demonstrate its utility through a real sales prospecting use case, which showcases its ability to facilitate the authoring of workflows, decision rules, and data models. Additionally, our empirical evaluation demonstrates the accuracy of routing user requests, efficacy in workflow authoring, and the precision of API field mapping recommendations.

References

[1]
Meta AI. 2024. Introducing Meta Llama 3: The most capable openly available LLM to date. https://ai.meta.com/blog/meta-llama-3.
[2]
Meta AI. 2024. Llama3. https://llama.meta.com/llama3/.
[3]
Thierry Biard, Alexandre Le Mauff, Michel Bigand, and Jean-Pierre Bourey. 2015. Separation of Decision Modeling from Business Process Modeling Using New "Decision Model and Notation" (DMN) for Automating Operational Decision-Making. In Risks and Resilience of Collaborative Networks, Luis M. Camarinha-Matos, Frédérick Bénaben, and Willy Picard (Eds.). Springer International Publishing, Cham, 489--496.
[4]
Tom B. Brown et al. 2020. Language Models are Few-Shot Learners. arXiv:2005.14165 [cs.CL] https://arxiv.org/abs/2005.14165
[5]
Dong Chen, Shaoxin Lin, Muhan Zeng, Daoguang Zan, Jian-Gang Wang, Anton Cheshkov, Jun Sun, Hao Yu, Guoliang Dong, Artem Aliev, Jie Wang, Xiao Cheng, Guangtai Liang, Yuchi Ma, Pan Bian, Tao Xie, and Qianxiang Wang. 2024. CodeR: Issue Resolving with Multi-Agent and Task Graphs. arXiv:2406.01304 [cs.CL] https://arxiv.org/abs/2406.01304
[6]
Chroma. 2024. ChromaDB. https://github.com/chroma-core/chroma.
[7]
Cognition.ai. 2024. Introducing Devin. https://www.cognition.ai/blog/introducing-devin. Accessed: 2024-07-10.
[8]
Appian Corporation. 2024. Process Automation Overview. https://appian.com/products/platform/process-automation/overview. Accessed: 2024-07-10.
[9]
Open Technologies for Integration (ot4i). 2024. App Connect Templates on GitHub. https://github.com/ot4i/app-connect-templates. Accessed: 2024-07-10.
[10]
Michael Grohs, Luka Abb, Nourhan Elsayed, and Jana-Rebecca Rehse. 2024. Large Language Models Can Accomplish Business Process Management Tasks. In Business Process Management Workshops, Jochen De Weerdt and Luise Pufahl (Eds.). Springer Nature Switzerland, Cham, 453--465.
[11]
A. Grosskopf, G. Decker, and M. Weske. 2009. The Process: Business Process Modeling Using BPMN. Meghan-Kiffer Press. https://books.google.com/books?id=UaVZAAAAYAAJ
[12]
IBM. 2024. IBM App Connect. https://www.ibm.com/products/app-connect. Accessed: 2024-07-10.
[13]
IBM. 2024. IBM Business Automation. https://www.ibm.com/business-automation. Accessed: 2024-07-10.
[14]
IBM. 2024. IBM WatsonX Orchestrate. https://www.ibm.com/products/watsonx-orchestrate. Accessed: 2024-07-10.
[15]
IBM. 2024. Introducing the Technology Behind WatsonX AI. https://www.ibm.com/blog/introducing-the-technology-behind-watsonx-ai/. Accessed: 2024-07-10.
[16]
Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. In The Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=VTF8yNQM66
[17]
Humam Kourani, Alessandro Berti, Daniel Schuster, and Wil MP van der Aalst. 2024. Process Modeling With Large Language Models. In International Conference on Business Process Modeling, Development and Support. Springer, 229--244.
[18]
Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, and Hema Venkatarangan. 2018. Hi, how can i help you? automating enterprise IT support help desks. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (New Orleans, Louisiana, USA) (AAAI'18/IAAI'18/EAAI'18). AAAI Press, Article 942, 8 pages.
[19]
Microsoft. 2024. Get Started with Copilot in Microsoft Power Automate. https://learn.microsoft.com/en-us/power-automate/get-started-with-copilot. Accessed: 2024-07-10.
[20]
Mayank Mishra, Matt Stallone, Gaoyuan Zhang, Yikang Shen, Aditya Prasad, Adriana Meza Soria, Michele Merler, Parameswaran Selvam, Saptha Surendran, Shivdeep Singh, et al. 2024. Granite code models: A family of open foundation models for code intelligence. arXiv preprint arXiv:2405.04324 (2024).
[21]
Arghavan Moradi Dakhel, Vahid Majdinasab, Amin Nikanjam, Foutse Khomh, Michel C. Desmarais, and Zhen Ming (Jack) Jiang. 2023. GitHub Copilot AI pair programmer: Asset or Liability? Journal of Systems and Software 203 (2023), 111734. https://doi.org/10.1016/j.jss.2023.111734
[22]
Vinod Muthusamy, Yara Rizk, Kiran Kate, Praveen Venkateswaran, Vatche Isahagian, Ashu Gulati, and Parijat Dube. 2023. Towards large language model-based personal agents in the enterprise: Current trends and open problems. In Findings of the Association for Computational Linguistics: EMNLP 2023. 6909--6921.
[23]
Chris Parnin, Gustavo Soares, Rahul Pandita, Sumit Gulwani, Jessica Rich, and Austin Z Henley. 2023. Building Your Own Product Copilot: Challenges, Opportunities, and Needs. arXiv preprint arXiv:2312.14231 (2023).
[24]
Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019).
[25]
Shuo Ren, Daya Guo, Shuai Lu, Long Zhou, Shujie Liu, Duyu Tang, Neel Sundaresan, Ming Zhou, Ambrosio Blanco, and Shuai Ma. 2020. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis. arXiv:2009.10297 [cs.SE]
[26]
Yara Rizk, Vatche Isahagian, Scott Boag, Yasaman Khazaeni, Merve Unuvar, Vinod Muthusamy, and Rania Khalaf. 2020. A Conversational Digital Assistant for Intelligent Process Automation. In Business Process Management: Blockchain and Robotic Process Automation Forum, Aleksandre Asatiani, José María García, Nina Helander, Andrés Jiménez-Ramírez, Agnes Koschmider, Jan Mendling, Giovanni Meroni, and Hajo A. Reijers (Eds.). Springer International Publishing, Cham, 85--100.
[27]
Yara Rizk, Praveen Venkateswaran, Vatche Isahagian, Austin Narcomey, and Vinod Muthusamy. 2024. A Case for Business Process-Specific Foundation Models. In Business Process Management Workshops, Jochen De Weerdt and Luise Pufahl (Eds.). Springer Nature Switzerland, Cham, 44--56.
[28]
Salesforce. 2024. Business Process Automation: Best Practices. https://www.salesforce.com/products/platform/best-practices/business-process-automation/. Accessed: 2024-07-10.
[29]
Swimm.io. 2024. Embeddings in Machine Learning: Types, Models, and Best Practices. https://swimm.io/learn/large-language-models/embeddings-in-machine-learning-types-models-and-best-practices. Accessed: 2024-07-10.
[30]
UiPath. 2024. UiPath Product Overview. https://www.uipath.com/product. Accessed: 2024-07-10.
[31]
UKPLab. 2024. Sentence Transformers GitHub Repository. https://github.com/UKPLab/sentence-transformers. Accessed: 2024-07-10.
[32]
Wil MP van der Aalst. 2004. Business process management: a personal view. Business Process Management Journal 10, 2 (2004).
[33]
Michael Wornow, Avanika Narayan, Krista Opsahl-Ong, Quinn McIntyre, Nigam Shah, and Christopher Ré. 2024. Automating the Enterprise with Foundation Models. Proc. VLDB Endow. 17, 11 (Aug. 2024), 2805--2812. https://doi.org/10.14778/3681954.3681964
[34]
John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. arXiv:2405.15793 [cs.SE] https://arxiv.org/abs/2405.15793
[35]
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022).
[36]
Zhen Zeng, William Watson, Nicole Cho, Saba Rahimi, Shayleen Reynolds, Tucker Balch, and Manuela Veloso. 2023. FlowMind: Automatic Workflow Generation with LLMs. In Proceedings of the Fourth ACM International Conference on AI in Finance (Brooklyn, NY, USA) (ICAIF '23). Association for Computing Machinery, New York, NY, USA, 73--81. https://doi.org/10.1145/3604237.3626908
[37]
Zihao Zhao, Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. 2021. Calibrate Before Use: Improving Few-shot Performance of Language Models. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 12697--12706. https://proceedings.mlr.press/v139/zhao21c.html

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
Middleware Industrial Track '24: Proceedings of the 25th International Middleware Conference Industrial Track
December 2024
53 pages
ISBN:9798400713194
DOI:10.1145/3700824
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License.

Sponsors

In-Cooperation

  • IFIP

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 02 December 2024

Check for updates

Author Tags

  1. agentic frameworks
  2. business process automation
  3. conversational assistant
  4. multi-agent orchestration

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

MIDDLEWARE '24
Sponsor:
MIDDLEWARE '24: 25th International Middleware Conference
December 2 - 6, 2024
Hong Kong, Hong Kong

Acceptance Rates

Overall Acceptance Rate 5 of 23 submissions, 22%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 129
    Total Downloads
  • Downloads (Last 12 months)129
  • Downloads (Last 6 weeks)58
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media