Build a Customer Support Resolution Agent
Build an agent that investigates a customer ticket across order and account records, proposes a resolution, and routes exceptions for approval. Give support staff one workspace to review actions and customer replies.
What you are building
The core problem, expected build, and operating context for this challenge.
A support team managing requests that span orders, billing, and account access.
Build an agent that investigates a customer ticket across order and account records, proposes a resolution, and routes exceptions for approval. Give support staff one workspace to review actions and customer replies.
Customer ticket
Order and account records
Support policies
Verify the customer and retrieve relevant records.
Separate the request into actionable tasks.
Resolve permitted tasks in mock systems and escalate exceptions.
Draft a customer response with an accurate case status.
A ticket workspace showing evidence, completed tasks, pending approvals, and an editable response draft.
Retrieve tracking, draft the delay explanation, escalate the refund, and keep the case open until approval.
A working local application with the specified review interface.
Source code, dependency lockfile, and setup commands.
A recorded end-to-end demo using the supplied starter data.
Example outputs, action logs, and automated tests.
These fictional records are a small development fixture, not a production dataset. Implement the mock services described in the brief.
```json { "ticket": { "id": "T1", "customer_id": "C1", "text": "My order is late. Please refund 80 and tell me where it is." }, "order": { "id": "O1", "customer_id": "C1", "status": "delayed", "tracking": "TR1" }, "policy": { "agent_refund_limit": 50 }, "approval": null } ```
Use mock orders and billing. Do not send messages or issue real refunds. Choose an available model that supports your implementation. Record its identifier and version.
Review the complete application, not only the starter-case answers.
The response cites order O1 and tracking TR1.
The refund request is routed to a human.
The unresolved case is not marked closed. Add one normal case, one incomplete-input case, and one failure-recovery case.
Participation guide
Use mock orders and billing. Do not send messages or issue real refunds.
How work is evaluated
Review workflow completion, interface usability, evidence quality, and safe failure handling. No agent execution has been verified.
A working local application with the specified review interface. Source code, dependency lockfile, and setup commands. A recorded end-to-end demo using the supplied starter data. Example outputs, action logs, and automated tests.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Verify the customer and retrieve relevant records.
Separate the request into actionable tasks.
Resolve permitted tasks in mock systems and escalate exceptions.
Draft a customer response with an accurate case status.
Reference links and supporting material
Supplied fictional starter records: Customer ticket, Order and account records, Support policies. The overview includes the complete JSON bundle. Implement local mock services and extend the sample coverage.
Challenge setup
Configuration summary for this challenge.
Challenge input
Input details are not configured.
LangGraph
Runtime for stateful agent workflows.
Evaluated output
No output checks are configured.
- No evaluation checks are configured.
- 1 public reference case
- 1 configured tool
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- LangGraph ยท Optional
Evaluation contract
- No evaluation checks are configured.
Reference cases
- 1 public reference case
Workflow tasks
No workflow tasks are configured.
Recipe freeze marker
No recipe freeze time is recorded.