AI Customer Support · E-commerce Refunds
An autonomous LangGraph agent that verifies customers, validates orders, applies your refund policy, and resolves support cases end-to-end — without a human in the loop.
Traditional e-commerce support is slow, manual, and inconsistent. The cost is measured in churned customers and agent burnout — not just ticket volume.
Customers wait 24–48 hours for refund decisions that a policy-aware agent can make in under 10 seconds. Every hour of delay is a loyalty risk.
Support agents spend more time digging through policy documents than helping customers. Queues pile up while the answer is buried in a PDF.
Identical refund cases get different outcomes depending on which agent handles them. Inconsistency erodes trust and opens legal risk.
Built on LangGraph, the agent iterates through a tool-calling loop — each step grounded in real data — until it reaches a policy-backed decision.
The customer describes their situation in plain language — no forms, no ticket IDs required to start.
The agent calls lookup_customer to verify the account, tier, and history before any decision is made.
Order ownership is confirmed. The agent checks delivery date, product category, and sale status.
Every applicable rule is evaluated — no hallucination, no shortcuts. The policy document is the ground truth.
The agent approves or denies with a refund ID or a rule-cited reason, completing the case end-to-end.
Architecture: FastAPI (SSE) → LangGraph StateGraph → ChatOpenAI (gpt-4o-mini) tool-calling loop → tool execution → state update → next iteration or END node → WebSocket broadcast to Admin.
Every layer — from the agent loop to the admin dashboard to the Docker production setup — is built for real-world use, not just demos.
Token-by-token SSE streaming keeps the UI responsive. No loading spinners — you see the agent think.
Rules live in a Markdown document. The agent reads and cites them. Zero hallucination on eligibility.
Every tool call, input, and output is logged per session and visible live in the Admin dashboard.
ElevenLabs STT transcribes speech to text (with smart ID normalization) and TTS reads responses aloud.
WebSocket-powered dashboard shows sessions, reasoning steps, and refund decisions as they happen.
Multi-stage Docker builds, nginx reverse proxy, non-root containers, health checks, SSE + WS support.
Tech Stack
Live Demo
Tell the agent your Customer ID and Order ID. Watch it look up your account, check the order, apply the policy, and issue a decision — all in a single conversation.
Try: Customer ID CUST001 · Order ID ORD1017