Cloud dashboards show you the problem. They don’t solve it. Every organization running in AWS, Azure, or GCP eventually faces the same issue: Idle compute running for months
Overprovisioned instances
Orphaned storage
No clear optimization decisions
No ownership Idle compute running for months Overprovisioned instances Orphaned storage No clear optimization decisions No ownership What teams need is not another dashboard. They need an intelligent control plane. In this article, I’ll walk through how to build a production-ready multi-agent FinOps system powered by: production-ready multi-agent FinOps system FastAPI (backend orchestration)
LLMs (structured reasoning)
React (dashboard UI)
Docker (deployment) FastAPI (backend orchestration) LLMs (structured reasoning) React (dashboard UI) Docker (deployment) This is implementation-focused. Minimal theory. Real architecture. Architecture The Problem: Cost Data Without Decisions Most FinOps tools stop at: Cost visualization
Alerts
Basic rule-based recommendations Cost visualization Alerts Basic rule-based recommendations But real optimization requires reasoning: Should we downsize this instance?Is this idle volume safe to delete?What’s the performance risk? Should we downsize this instance?Is this idle volume safe to delete?What’s the performance risk? Static rules are too rigid.Pure AI is too risky. The solution: Rule-based triggers + LLM reasoning + human approval. Rule-based triggers + LLM reasoning + human approval. System Architecture Overview At a high level: User → React UI → FastAPI → Agents → LLM → Structured Output → Human Approval We separate responsibilities clearly: UI handles interaction
API orchestrates
Agents apply logic
LLM provides contextual reasoning
Humans approve execution UI handles interaction API orchestrates Agents apply logic LLM provides contextual reasoning Humans approve execution This keeps the system enterprise-safe. The Multi-Agent Design Instead of one monolithic “AI service”, we use specialized agents. 1. Diagnostic Agent Detects inefficiencies and optimization opportunities. 2. Idle Cleanup Agent Identifies unused resources that may be safely removed. 3. Rightsizing Agent Recommends better instance sizing based on usage trends. Each agent follows the same pattern: Apply deterministic rules
Construct a structured context
Call the LLM with constrained instructions
Validate JSON output
Return recommendation Apply deterministic rules Construct a structured context Call the LLM with constrained instructions Validate JSON output Return recommendation This is not chat AI.This is constrained reasoning. Backend: FastAPI as the Control Plane FastAPI acts as the orchestrator. Example endpoint: @app.post("/analyze/idle")
def analyze_idle():
    data = fetch_cloud_metrics()
    result = idle_agent.analyze(data)
    return result @app.post("/analyze/idle")
def analyze_idle():
    data = fetch_cloud_metrics()
    result = idle_agent.analyze(data)
    return result Responsibilities: Route requests to the correct agent
Inject telemetry
Enforce policies
Log all decisions
Validate structured responses Route requests to the correct agent Inject telemetry Enforce policies Log all decisions Validate structured responses The API layer is critical.It prevents LLM outputs from directly impacting infrastructure. Inside an Agent Here’s what a simplified DiagnosticAgent looks like: class DiagnosticAgent:
    def __init__(self, llm_client):
        self.llm = llm_client

    def analyze(self, resource):
        if resource["cpu_avg"] < 5 and resource["days_running"] > 14:
            return self._call_llm(resource)
        return None class DiagnosticAgent:
    def __init__(self, llm_client):
        self.llm = llm_client

    def analyze(self, resource):
        if resource["cpu_avg"] < 5 and resource["days_running"] > 14:
            return self._call_llm(resource)
        return None Notice: We do not send everything to the LLM. We filter first. This reduces: Cost
Latency
Hallucination risk Cost Latency Hallucination risk Constrained LLM Prompting We never ask open-ended questions. We use structured prompts: You are a FinOps optimization engine.

Given:
- cpu_avg: 2%
- monthly_cost: $430
- environment: production

Return:
- recommendation
- risk_level
- estimated_savings
- justification

Output JSON only. You are a FinOps optimization engine.

Given:
- cpu_avg: 2%
- monthly_cost: $430
- environment: production

Return:
- recommendation
- risk_level
- estimated_savings
- justification

Output JSON only. We force: Role clarity
Schema constraints
Deterministic structure Role clarity Schema constraints Deterministic structure The output must look like: {
  "recommendation": "Downsize to t3.medium",
  "risk_level": "Low",
  "estimated_savings": 180,
  "justification": "CPU utilization below 5% for 30 days"
} {
  "recommendation": "Downsize to t3.medium",
  "risk_level": "Low",
  "estimated_savings": 180,
  "justification": "CPU utilization below 5% for 30 days"
} If parsing fails, we reject it. Never pass raw model text downstream. The Idle Cleanup Agent This agent is more sensitive. Deletion is high risk. Example logic: if resource["attached"] is False and resource["days_idle"] > 30:
    flag = True if resource["attached"] is False and resource["days_idle"] > 30:
    flag = True The LLM is not deciding whether to delete. It classifies: Risk level
Compliance concern
Savings estimate Risk level Compliance concern Savings estimate Human approval is mandatory. The Rightsizing Agent Rightsizing requires trend awareness. We analyze: Average CPU
Peak CPU
Memory utilization
30-day stability Average CPU Peak CPU Memory utilization 30-day stability Example: if cpu_avg < 40 and cpu_peak < 60:
    candidate = True if cpu_avg < 40 and cpu_peak < 60:
    candidate = True The LLM suggests a smaller instance while respecting performance buffers. Again: Recommendation, not execution. React Frontend The React dashboard shows: Optimization opportunity
Risk level
Estimated savings
Confidence score
Approve/Reject button Optimization opportunity Risk level Estimated savings Confidence score Approve/Reject button This turns AI output into decision support. Not automation. Human-in-the-Loop Execution Execution flow: Frontend → Backend → Cloud API → Confirm status Key safeguards: No production deletion without approval
Snapshot before resize
Post-change monitoring
Full audit logging No production deletion without approval Snapshot before resize Post-change monitoring Full audit logging AI assists. Humans decide. Dockerized Deployment We containerize: FastAPI service
React frontend
Optional Redis / Postgres FastAPI service React frontend Optional Redis / Postgres Example Dockerfile: FROM python:3.11
WORKDIR /app
COPY . .
RUN pip install -r requirements.txt
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"] FROM python:3.11
WORKDIR /app
COPY . .
RUN pip install -r requirements.txt
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"] This allows: Reproducible environments
Cloud-native deployment
Easy scaling Reproducible environments Cloud-native deployment Easy scaling Production Hardening This is where most AI projects fail. Enterprise safeguards include: Schema validation on every LLM output
Observability (log prompts + responses)
Retry logic with backoff
Environment restrictions (prod guardrails)
Role-based access control
Versioned prompts
Rate limiting Schema validation on every LLM output Observability (log prompts + responses) Retry logic with backoff Environment restrictions (prod guardrails) Role-based access control Versioned prompts Rate limiting AI without guardrails is a liability. AI with structure becomes leverage. Why This Architecture Works It balances: Rules + LLM + Humans Instead of replacing decision-makers, it augments them. The LLM: Explains
Quantifies
Suggests Explains Quantifies Suggests It does not: Execute
Override policies
Bypass governance Execute Override policies Bypass governance That separation is what makes this production-ready. Key Takeaways Don’t build AI monoliths — build specialized agents.
Always filter before calling the LLM.
Constrain prompts with explicit schemas.
Validate outputs before using them.
Keep humans in the loop for infrastructure changes.
Log everything. Don’t build AI monoliths — build specialized agents. Always filter before calling the LLM. Constrain prompts with explicit schemas. Validate outputs before using them. Keep humans in the loop for infrastructure changes. Log everything. This is how you move from an AI demo to an enterprise system. Final Thought FinOps dashboards show cost. Agentic AI systems generate action. When designed correctly, multi-agent architectures can transform cloud cost management from reactive reporting to intelligent optimization. The difference is not in using an LLM. The difference is in how you architect around it. Let’s connect 👇 🔗 LinkedIn:https://www.linkedin.com/in/dhiraj-srivastava-b9211724/ https://www.linkedin.com/in/dhiraj-srivastava-b9211724/ 💻 GitHub (Code & Repositories):https://github.com/dexterous-dev?tab=repositories https://github.com/dexterous-dev?tab=repositories

This story contains AI-generated text. The author has used AI either for research, to generate outlines, or write the text itself. 

Quant

Top 5 Cloud Skills That Will Matter The Most in 2026

Read My Stories

Building a Production-Ready Multi-Agent FinOps System with FastAPI, LLMs, and React

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Top 5 Cloud Skills That Will Matter The Most in 2026

Daniel Saks Predicts Agentic AI Will Empower Individuals and Boost Productivity

Active Inference AI: Here's Why It's The Future of Enterprise Operations and Industry Innovation

The Trick That Agentic Frameworks Pulled On Us

Exploring the Spatial Web Protocol at the 4th Annual Applied Active Inference Symposium

What Is Agentic AI?

Top 5 Cloud Skills That Will Matter The Most in 2026

Daniel Saks Predicts Agentic AI Will Empower Individuals and Boost Productivity

Active Inference AI: Here's Why It's The Future of Enterprise Operations and Industry Innovation

The Trick That Agentic Frameworks Pulled On Us

Exploring the Spatial Web Protocol at the 4th Annual Applied Active Inference Symposium

What Is Agentic AI?

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps