FinOps Agent -- A Use-Case for IT Infrastructure and Cost Optimization

TL;DR

FinOps data is dispersed across diverse sources, hindering timely cloud cost optimization. The authors build an autonomous FinOps agent rooted in a unified GraphQL schema and an NL2GraphQL interface, organized as a three-agent CrewAI system that retrieves data, analyzes it, and generates optimization recommendations. Key contributions include the unified data schema, NL2GraphQL layer, a multi-agent architecture with tool-calling, and a comprehensive multi-LLM evaluation showing strong performance for GPT-4o-family models and notable gaps for open-source alternatives. The results demonstrate the practical viability of agentic FinOps for cross-vendor IT infrastructure cost optimization, with implications for scalable governance and auditable decision-making in cloud spend management.

Abstract

FinOps (Finance + Operations) represents an operational framework and cultural practice which maximizes cloud business value through collaborative financial accountability across engineering, finance, and business teams. FinOps practitioners face a fundamental challenge: billing data arrives in heterogeneous formats, taxonomies, and metrics from multiple cloud providers and internal systems which eventually lead to synthesizing actionable insights, and making time-sensitive decisions. To address this challenge, we propose leveraging autonomous, goal-driven AI agents for FinOps automation. In this paper, we built a FinOps agent for a typical use-case for IT infrastructure and cost optimization. We built a system simulating a realistic end-to-end industry process starting with retrieving data from various sources to consolidating and analyzing the data to generate recommendations for optimization. We defined a set of metrics to evaluate our agent using several open-source and close-source language models and it shows that the agent was able to understand, plan, and execute tasks as well as an actual FinOps practitioner.

Figures (28)

• Figure 1: FinOps Agent Architecture.
• Figure 2: An Execution Plan generated by GPT-4o.
• Figure 3: NL2GraphQL Architecture for FinOps Agent.
• Figure 4: Logic Flow of FinOps Agent for IT Infrastructure and Cost Optimization.
• Figure 5: Demonstration of a Complete Run of FinOps Agent.