International Journal of Leading Research Publication

E-ISSN: 2582-8010   •   Impact Factor: 9.56

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Monthly Scholarly International Journal

Call for Paper Volume 7 Issue 1 January 2026 Submit your research before last 3 days of to publish your research paper in the issue of January.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 1
January 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Cost-Aware Agentic Architectures for Multi-Model Routing and Tool-Use Optimisation in CRM Workflows

Author(s) Sri Hari Deep Kolagani, Dr Mamata Bhandar
Country India
Abstract The study presents research into the application of cost-conscious agentic support in the field of multi-model routing and tool-use optimization to the CRM post-sale processes. It is focused on how to dynamically dispatch tasks to suitable model tiers (small, medium, large LLMs) with a view to the minimum expense of API services and high software quality. The study aims to examine how Salesforce Service Cloud can be used to carry out post-sales CRM activities, including case escalation and email summarization. The major observations include that Dynamic task routing led to a saving of 33% of API cost, relative to using the largest LLM at all times, without any substantial decrease in Customer Satisfaction (CSAT) (>90%), nor First-Contact Resolution (FCR) (>85%). Query optimization of the vector database and limiting of external API calls resulted in a 15-20% reduction in query time and a 10%-15% cut in total operating expense per agent. The findings indicate that multi-tier model routing can be helpful to cut costs in CRM workflow, with the potential highest savings in operation costs of up to 35%, while providing quality service. This research offers an effective, cost-effective model of refining CRM processes and proposes great insights to future studies on edge computing and reinforcement learning towards further optimization.
Keywords CRM workflows, multi-model routing, cost optimization, LLMs, Salesforce Service Cloud, API costs.
Field Engineering
Published In Volume 6, Issue 7, July 2025
Published On 2025-07-10
DOI https://doi.org/10.70528/IJLRP.v6.i7.1866
Short DOI https://doi.org/hbhpsj
View / Download PDF File

Share this



CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJLRP DOI prefix is
10.70528/IJLRP

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 12 Cover Page Vol 6 Isu 10 Cover Page Vol 6 Isu 9

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJLRP
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijlrp.com