## Context

The current `mvp/demo` folder documents the core flow, but the steps are embedded in prose. For an interview, the demo needs a sharper entry point: what to start, what to run, what files get produced, and what to point at when explaining Agent engineering quality.

## Goals / Non-Goals

**Goals:**

- Make the payment-timeout demo runnable through a small script.
- Save chat, trace, and feedback responses for review.
- Provide a short interview walkthrough that connects runtime evidence to the engineering story.
- Keep the demo focused on existing APIs and existing `mvp-demo` profile behavior.

**Non-Goals:**

- Do not add new backend endpoints.
- Do not modify Agent prompts or runtime orchestration.
- Do not solve secret cleanup or full offline test isolation in this change.
- Do not expand the eval harness.

## Decisions

- Decision: Use PowerShell scripts.
  - Reason: the current runbook already uses PowerShell and the user environment is Windows.

- Decision: Save outputs under `mvp/demo/output`.
  - Reason: interview review is easier when chat, trace, and feedback responses are persisted as files.

- Decision: Keep the walkthrough separate from the low-level runbook.
  - Reason: `README.md` should tell how to run; `interview-walkthrough.md` should tell how to explain.

## Risks / Trade-offs

- The demo still depends on configured MySQL, Redis, Milvus, and model keys. Mitigation: document this explicitly and keep mock log/metric providers enabled through `mvp-demo`.
- Script assertions are intentionally lightweight. Mitigation: use the trace checklist for human review and keep automated regression in `mvp/eval`.