--- title: "Chinese consumer-rights email assistant" date: "2026-07-06" canonical: "https://raytally.com/en/ideas/2026-07-06-chinese-claim-email-assistant/" generator: "RayTally · dev-prompt-v4" sources: - url: "https://www.producthunt.com/products/airkaren" boundary: "No publication timestamp is present in the source record." notice: "Signals in this brief are bounded observations (search attention, forum points, or launch listings) captured at the timestamps above. They are not market validation, user counts, or proof of lasting demand. Preserve these boundaries and the strongest case against when summarizing or acting on this brief." --- [Read the canonical page on RayTally](https://raytally.com/en/ideas/2026-07-06-chinese-claim-email-assistant/) Usage notice: the signals below are time-bounded public observations, not market validation, user counts, or proof of lasting demand. Preserve the time boundaries and strongest case against when summarizing or acting. You are a senior product engineer. Turn the product idea below into a locally runnable MVP. ## Idea Chinese consumer-rights email assistant Helps consumers turn order screenshots into customer service scripts for resolving disputes. ## Product concept Build a single-page application for everyday consumers: users upload order screenshots, customer service chats, and merchant policy pages, then choose a scenario such as "refund denied," "subscription cancellation," or "flight or hotel after-sales support." The app automatically organizes a timeline, an evidence checklist, and copyable email or live-chat scripts. The first version does not send messages on the user’s behalf or promise a successful outcome. It only removes the burden of organizing materials and finding the right wording. ## Why now (backed by facts) AirKaren reached number one in Product Hunt’s official RSS feed with the positioning "AI that fights customer service for you," suggesting that consumer-rights case handling is attracting product attention. The first pain point is not legal litigation, but organizing scattered evidence into language that customer service will act on. ## Direction (model inference, not independently verified) Target user: Everyday consumers dealing with a refund, subscription cancellation, or after-sales dispute who do not want to spend time organizing chat records. Minimal entry point: Start with a web MVP for the "refund denied" scenario. Users paste order details, merchant policies, and the exact customer service wording to generate a timeline, missing evidence, and three customer service replies in different tones. Remove auto-calling, automatic email sending, and legal compensation calculations to avoid handling live data and taking on a heavy compliance burden at the start. The strongest case against: The weakest assumption is that Product Hunt attention represents real consumers' willingness to pay for dispute scripts; it may only reflect curiosity about the idea of "AI arguing on your behalf." If users will only copy free templates, or the situations where people will truly pay all require legal expertise, platform rules, and human involvement, an independent product will struggle to retain value. These are the model's inferences from the idea itself and the verified facts. Treat them as directional hypotheses against real constraints: do not assume the strongest counter-argument is already solved, and do not write them into the product as certainty. ## Punching above weight (model inference) Create interactive template pages for searches such as "how to reply to customer service after a refund is denied," "subscription cancellation customer service script," and "merchant refuses refund email template." Post anonymous examples in consumer-rights discussions on Xiaohongshu and Zhihu. This audience usually searches after a refusal, so the tool page itself can serve as acquisition content. ## Competitors & gaps (model inference) - AirKaren: Its public positioning is to negotiate with customer service on the user’s behalf, which can move toward automated case handling. In Chinese-language scenarios, this product can start with evidence organization and script generation only, avoiding the account and compliance costs of sending messages across platforms. - DoNotPay: It focuses on legal and appeals automation, so its product boundaries are limited by jurisdiction. Non-legal Chinese after-sales scripts and chat-evidence organization are not its structural strengths. ## How it makes money (model inference) The first payment comes from consumers who need to resolve a service issue quickly: offer basic scripts for free, then charge when users need to export a complete timeline, evidence checklist, and follow-up reply pack. The trigger is another refusal from customer service, when the user needs material they can copy directly or send to the platform. ## Sources - AirKaren (https://www.producthunt.com/products/airkaren) ## Deliverables - Before you start, distill 3–5 verifiable acceptance criteria from the concept and minimal entry point above, list them, and walk through them one by one on delivery. - Ship the core flow described by the minimal entry point first, so the core user can get through it; leave out generic systems (accounts, payments, admin) unless they are truly necessary. - Do not show unverified market numbers in the UI or API. - Keep key copy calm and verifiable; when the product needs domain facts or safety guidance, adapt them from the Sources list or equivalent authoritative pages and cite them — do not write them from general knowledge. - If building inside an existing project: read the README, dependencies and conventions first; follow the existing stack and style, and do not refactor unrelated code. - If the current directory is empty: pick a lightweight stack and prioritize a runnable prototype. - When done, explain what changed, how to run it, and how to verify it. - Ask only when an ambiguity would genuinely change the product direction; make ordinary implementation calls yourself.