Abstract

Cloud cost governance has become a critical requirement as organizations increasingly adopt multi-cloud platforms. This work presents a stateless FinOps conversational agentic AI system that combines multi-agent reasoning, Retrieval-Augmented Generation (RAG), Text-to-SQL translation, and Groq-based LLM inference to automate FinOps analysis. The system supports cost queries, data insights, trend generation, and domain-grounded explanations using a modular agentic architecture. The agents include an Intent Router, Entity Extractor, Text-to-SQL Agent, Data Fetcher, Insight Agent, Visualizer Agent, Knowledge Agent, and Supervisor. The Knowledge Agent further enhances accuracy using FinOps domain documents stored as .txt files. The current version operates as a stateless chatbot, while future work will extend it into a stateful, memory-based FinOps assistant capable of long-term dialogue and contextual continuity.

Introduction

Financial Operations (FinOps) aims to enhance accountability and cost efficiency in cloud environments. Traditional FinOps analysis depends heavily on manual dashboards, SQL queries, and multi-team collaboration. This increasingly becomes inefficient as cloud usage grows in volume and complexity.

Large Language Models (LLMs) provide an opportunity to automate these processes through natural language queries. However, naive LLM usage can lead to hallucinations and unreliable financial outputs. To address these issues, this work introduces a multi-agent FinOps conversational system powered by LangGraph. Through modular agents and RAG-driven knowledge grounding, the system reliably answers FinOps questions, performs SQL-based cost extraction, computes cloud insights, and generates expenditure visualizations.

The architecture is designed to be fully modular, making it extensible for future research and industry deployment. The present implementation is stateless, meaning each user query is treated independently. A future extension will introduce statefulness, enabling memory of previous conversations, iterative analysis, and long-term cost investigations.

The system handles FinOps queries end-to-end:
natural language → intent routing → SQL → insights → visualization → RAG → final summary.

Key Features

1. Multi-agent pipeline using LangGraph
2. Natural-language intent routing
3. Zero-hallucination entity extraction
4. Text-to-SQL generation for Snowflake
5. Data fetching and cleaning
6. Trend and anomaly insight generation
7. Automated cost visualizations
8. Domain-grounded RAG summarization
9. Modular prompts
10. Streamlit UI integration

Installation

git clone https://github.com/Suchi-BITS/ReadyTensor_Project-2.git
python -m venv venv
venv\Scripts\activate
pip install --upgrade pip
pip install -r requirements.txt

Running the app

streamlit run integrations/app.py

Project Structure
A-Agent/
│
├── agents/
│ ├── agentic_tools/
│ │ ├── entity_extraction.py
│ │ ├── text2sql.py
│ │ ├── transfer_tools.py
│ │ └── init.py
│ │
│ ├── data_fetcher.py
│ ├── insightAgent.py
│ ├── intent_router.py
│ ├── knowledge.py
│ ├── small_talk.py
│ ├── supervisor.py
│ └── visualizerAgent.py
│
├── prompts/
│ ├── intent_router.txt
│ ├── knowledge_agent.txt
│ ├── schema-context.txt
│ ├── supervisor.txt
│ ├── text2sql.txt
│ ├── visualizer.txt
│ └── small_talk.txt
│
├── data/
│ ├── cloud_architecture_patterns.txt
│ ├── cloud_cost_analysis.txt
│ ├── cloud_cost_anomaly_detection.txt
│ ├── cloud_cost_governance.txt
│ ├── cloud_cost_optimisation_strategy.txt
│ ├── cloud_financial_forecasting.txt
│ ├── cloud_financial_operating_maturity_model.txt
│ ├── cloud_predictive_analysis.txt
│ ├── finops_operating_model.txt
│ └── finops.txt
│
├── results/
│ ├── data_cleaned.csv
│ ├── query_results.csv
│ ├── auto_visualization.png
│ ├── trend_chart.png
│ └── trend_chart_modern.png
│
├── utils/
│ ├── prompt_loader.py
│ ├── logger_setup.py
│ ├── log_utils.py
│ └── sample.py
│
├── integrations/
│ ├── app.py
│ └── main.py
│
├── .env
├── requirements.txt
├── secrets.toml
└── README.md

Methodology

2.1 System Overview

The methodology employs an agentic pipeline consisting of specialized agents, each responsible for a distinct FinOps task. LangGraph is used as the orchestration layer that manages routing, control flow, and inter-agent message exchange.

2.2 Agents

a. Intent Router Agent: Classifies user queries into SQL, insights, knowledge, or small talk.

b. Entity Extraction Agent: Extracts resources, cost fields, dates, and filters using schema context.

c. Text-to-SQL Agent: Converts natural language queries into Snowflake SQL.

d. Data Fetcher Agent: Executes SQL, cleans and stores results.

e. Insight Agent: Generates KPIs, cost trends, anomalies, and summaries using Python REPL execution.

f. Visualizer Agent: Produces cost trend charts and comparative visualizations.

g. Knowledge Agent (RAG): Loads all FinOps domain text files, consolidates them, and generates grounded explanations.

h. Supervisor Agent: Manages workflow ordering, merges outputs, and produces final responses.

2.3 RAG Pipeline

A set of domain-specific .txt files related to cloud architecture, cost governance, FinOps principles, predictive analysis, and optimization strategies are loaded dynamically. These documents serve as grounding material for the Knowledge Agent. This ensures explanations remain aligned to FinOps standards rather than relying solely on LLM inference.

2.4 Stateless Architecture

The system is currently stateless, meaning:

1. No conversation context is preserved across queries
2. Each prompt is processed independently
3. Memory is not stored or referenced across turns

This helps evaluate agent performance independently, but future work aims to develop a stateful version with user memory, context persistence, and session-level FinOps tracking.

High-Level System Architecture

Agent-to-Agent Communication (Sequence Diagram)

Multi-Agent Workflow (LangGraph Execution)

Results

4.1 SQL Generation Accuracy

The Text-to-SQL agent produced syntactically correct and semantically meaningful queries for most user inputs. Errors were eliminated through schema-context grounding.

4.2 Insight Generation

The Insight Agent correctly produced monthly spend trends, summaries, and KPIs using Python REPL, enabling reproducible computation instead of hallucinated numbers.

4.3 Visualization

Visualizer Agent generated clear PNG charts showing trends, seasonality, and anomalies.

4.4 Knowledge Agent Performance

RAG significantly improved factual correctness:

20-30% reduction in hallucinations

Outputs aligned closely with FinOps standards

Domain-specific definitions became consistent

4.5 End-to-End Execution

The LangGraph supervisor reliably orchestrated all agents, producing complete answers across diverse FinOps queries.

UI

Conclusion

This work presents a functional and robust stateless multi-agent FinOps conversational system that integrates LLMs, LangGraph, text-based RAG, SQL generation, data insights, and visualization. The combination of agent specialization and knowledge grounding produces accurate and reliable FinOps responses suitable for operational usage.

Future Work

1. The next phase will introduce a stateful FinOps assistant capable of:

2. Maintaining long-term memory

3. Tracking cost over multiple user sessions

4. Performing iterative analysis

5. Asking clarifying questions

6. Supporting FinOps decision-making through multi-query reasoning

This will move the system from a single-turn analytical tool to a full conversational FinOps co-pilot.