Agentic Enterprise AI Architecture for Autonomous CRM Decision Orchestration Using Salesforce Agentforce and AWS
Article Sidebar
Main Article Content
Abstract
Enterprise CRM platforms have evolved from rule-based to autonomous, reasoning agents. In this paper, the authors integrate the insights from the aforementioned twenty publications into an agentic enterprise architecture for autonomous decision orchestration for a CRM system based on Salesforce Agentforce and Amazon Web Services (AWS) large language model (LLM) based multi-agent system. The synthesis looks at an evolution across three generations – deterministic RPA, predictive AI-CRM and agentic AI-CRM – and correlates the generations with the autonomy, latency and human intervention metrics. A layered architecture is proposed with data ingestion layer, predictive personalisation layer, agent orchestration layer, reasoning and planning layer, explainability and governance layer, and finally a cloud infrastructure layer with AWS services being deployed at each layer. Literature review reveals that implementing AI-powered CRM systems is linked to tangible improvements in customer retention, first-response time, and predictive customer service, with agentic architectures also contributing to a decrease in human escalations compared to traditional automation. The major hurdles to enterprise-wide deployment are security, privacy and explainability. The paper introduces a reusable reference architecture, a comparative evaluation framework with confidence-based escalation and autonomy-index formulations, and a set of governance recommendations for organisations that are moving toward using autonomous CRM orchestration. We discuss implications for competitive advantage and operational cost as well as directions for further empirical validation of agentic reasoning loops in production CRM environments.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[1] V. Bhardwaj, “A systematic review of robotic process automation in business operations: contemporary trends and insights,” J. Intell. Syst. Control, vol. 2, no. 3, pp. 153–169, 2023, doi: 10.56578/jisc020304.
[2] J. Brás, R. Pereira, and S. Moro, “Intelligent process automation and business continuity: Areas for future research,” Information, vol. 14, no. 2, p. 122, 2023, doi: 10.3390/info14020122.
[3] S. Chatterjee, S. K. Ghosh, R. Chaudhuri, and S. Chaudhuri, “Adoption of AI-integrated CRM system by Indian industry: from security and privacy perspective,” Inf. Comput. Secur., vol. 29, no. 1, pp. 1–24, 2021, doi: 10.1108/ICS-02-2019-0029.
[4] S. Chatterjee, N. P. Rana, K. Tamilmani, and A. Sharma, “The effect of AI-based CRM on organization performance and competitive advantage: An empirical analysis in the B2B context,” Ind. Mark. Manag., vol. 97, pp. 205–219, 2021, doi: 10.1016/j.indmarman.2021.07.013.
[5] K. Coussement, M. Z. Abedin, M. Kraus, S. Maldonado, and K. Topuz, “Explainable AI for enhanced decision-making,” 2024, Elsevier. doi: 10.1016/j.dss.2024.114276.
[6] T. Guo et al., “Large language model based multi-agents: A survey of progress and challenges,” arXiv Prepr. arXiv2402.01680, 2024, doi: 10.24963/ijcai.2024/890.
[7] M. Hakimi, G. A. Amiri, S. Jalalzai, F. A. Darmel, and Z. Ezam, “Exploring the integration of AI and cloud computing: navigating opportunities and overcoming challenges,” TIERS Inf. Technol. J., vol. 5, no. 1, pp. 57–69, 2024, doi: 10.38043/tiers.v5i1.5496.
[8] P. Hofmann, C. Samp, and N. Urbach, “Robotic process automation: P. Hofmann et al.,” Electron. Mark., vol. 30, no. 1, pp. 99–106, 2020, doi: 10.1007/s12525-019-00365-8.
[9] C. Khneyzer, Z. Boustany, and J. Dagher, “AI-driven chatbots in CRM: Economic and managerial implications across industries,” Adm. Sci., vol. 14, no. 8, p. 182, 2024, doi: 10.3390/admsci14080182.
[10] C. Ledro, A. Nosella, and A. Vinelli, “Artificial intelligence in customer relationship management: literature review and future research directions,” J. Bus. Ind. Mark., vol. 37, no. 13, pp. 48–63, 2022, doi: 10.1108/JBIM-07-2021-0332.
[11] J. S. Park, J. O’Brien, C. J. Cai, M. R. Morris, P. Liang, and M. S. Bernstein, “Generative agents: Interactive simulacra of human behavior,” in Proceedings of the 36th annual acm symposium on user interface software and technology, 2023, pp. 1–22. doi: 10.1145/3586183.3606763.
[12] D. Pramod, “Robotic process automation for industry: adoption status, benefits, challenges and research agenda,” Benchmarking an Int. J., vol. 29, no. 5, pp. 1562–1586, 2022, doi: 10.1108/BIJ-01-2021-0033.
[13] J. Ribeiro, R. Lima, T. Eckhardt, and S. Paiva, “Robotic process automation and artificial intelligence in industry 4.0–a literature review,” Procedia Comput. Sci., vol. 181, pp. 51–58, 2021, doi: 10.1016/j.procs.2021.01.104.
[14] T. Schick et al., “Toolformer: Language models can teach themselves to use tools,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 68539–68551, 2023, doi: 10.48550/arXiv.2302.04761.
[15] M. U. Tariq, M. Poulin, and A. A. Abonamah, “Achieving operational excellence through artificial intelligence: Driving forces and barriers,” Front. Psychol., vol. 12, p. 686624, 2021, doi: 10.3389/fpsyg.2021.686624.
[16] A. Uklańska, “Robotic process automation (RPA)–Bibliometric analysis and literature review,” Found. Manag., vol. 15, no. 1, pp. 129–140, 2023, doi: 10.2478/fman-2023-0010.
[17] R. Syed et al., “Robotic process automation: contemporary themes and challenges,” Comput. Ind., vol. 115, p. 103162, 2020, doi: 10.1016/j.compind.2019.103162.
[18] M. Wooldridge and N. R. Jennings, “Intelligent agents: Theory and practice,” Knowl. Eng. Rev., vol. 10, no. 2, pp. 115–152, 1995, doi: 10.1017/S0269888900008122.
[19] S. Yao et al., “React: Synergizing reasoning and acting in language models,” arXiv Prepr. arXiv2210.03629, 2022, doi: 10.48550/arXiv.2210.03629.
[20] J. W. Yoo, J. Park, and H. Park, “The impact of AI-enabled CRM systems on organizational competitive advantage: A mixed-method approach using BERTopic and PLS-SEM,” heliyon, vol. 10, no. 16, 2024, doi: 10.1016/j.heliyon.2024.e36392.