Check product pages across marketplaces
Check prices, comparison prices, origin, and "No. 1" claims on each marketplace and your own site against the product master. Staff decide the fixes.
- Runs on your own PCs and servers
- Use Azure OpenAI, Amazon Bedrock, Google Vertex AI, or an in-house model
- Its engine is Descarty's open-source Dagu (GPL-3.0)
The problem today
The same products are sold on Rakuten Ichiba, Amazon, Yahoo! Shopping, and your own site. A multi-channel tool registers them in bulk, but how each storefront actually shows the price and country of origin is only visible by opening the page. Wrong comparison prices or countries of origin can lead to cease-and-desist orders from Japan's Consumer Affairs Agency, and some orders have covered dozens to over a hundred products at once. There are too many pages to keep checking.
The workflow in Kitewell
- Add the products to check, with the product master's price, country of origin, and supporting evidence, to a batch sheetAutomatic
- Open each product page on every marketplace and your own site, and collect the price, comparison price, origin, and claims such as "No. 1"Web
- AI points out claims that differ from the product master and wording with no supporting evidence registeredAI judgment
- Staff review the findings and decide what to correctApproval
- Write the results to each row and post the products to fix to TeamsAutomatic
What AI does
Reads prices, comparison prices, country of origin, and wording such as "No. 1" or "lowest price" from pages laid out differently on each storefront, and compares them with the product master. Comparison prices and "No. 1" claims with no supporting evidence on the sheet are flagged as needing a check.
Where people decide
Staff decide whether a claim is a problem under Japan's Act against Unjustifiable Premiums and Misleading Representations and how to fix it. AI never makes the legal call.
Prove Kitewell on your own systems
Try it free for 14 days on your own PC. To see it working first, ask for a 30-minute demo. There is also a one-month onboarding (¥500,000 before tax), where we build your first job together.
What to check when you try this work
- Whether each marketplace's terms and guidelines allow automated checks of product pages
- Whether prices, comparison prices, and country of origin can be read correctly from each storefront's pages
- Where the supporting evidence comes from, such as sales records behind comparison prices and surveys behind "No. 1" claims
- Whether the number of items sent to staff stays manageable
How the onboarding runs
- Week 1Requirements and success criteria
- Weeks 2 to 3Build
- Week 4Verify on production screens
- Final dayReport
One-month onboarding
- Length
- One month
- Cost
- ¥500,000 (tax excluded). Your staff build, with the developer beside them
- If you go on to a license
- The onboarding fee is credited to the first year's contract
- Without the onboarding
- At Team scale, start on Team monthly (¥14,800 per computer a month, tax excluded), and cancel in any month
You can try it first on your own PC, in the free 14-day trial.
Frequently asked questions
- Does a clean check mean our pages comply with the Act?
- No. Kitewell shows only claims that differ from the product master and wording with no supporting evidence found. Whether a claim is appropriate is for staff or your legal team to decide.
- How is this different from registering products with a multi-channel tool?
- A multi-channel tool registers and updates product information on each storefront. This check opens the pages each storefront actually shows and confirms they match what was registered. The tool keeps doing registration; only the checking is automated.
- Do our documents and screens leave the company?
- Kitewell runs on your own PCs and servers, and Descarty never receives your business data. You choose the AI model: a cloud API, or an in-house or local model with an OpenAI-compatible API. With an in-house model, no data leaves the company. With a cloud model, what the AI reads is sent to the model's provider.
- What if the AI misreads something?
- A person checks what the AI produced before the work goes on. In a sheet, every value the AI reads shows the quote it came from, and rows below your confidence threshold go to a person. Reviewers can send work back with notes on what to fix, and who approved what is kept in the run history.
- What happens when a screen changes or a run stops?
- When a screen changes, the AI reads it again, relearns the step, and carries on. The relearned step is saved, and later runs repeat it. If a run still stops, ask the assistant right there, and it finds the cause and proposes a fix. A proposal is not saved until a person applies it.
- What happens to the RPA and systems we use today?
- Keep them. Kitewell operates screens the way a person does, so it works with systems that have no API. Move the robots that keep stopping and the work you gave up automating because it needs judgment, and leave fast, fixed processing in your current RPA.
- What does it cost?
- ¥14,800 per computer per month, or ¥148,000 per computer when paid yearly, before tax. A computer costs the same whether it builds or runs. You can try it free for 14 days. The one-month onboarding, where we build your first job together, is ¥500,000 before tax, credited to the first year if you go on.
Related use cases
Match food product pages to spec sheets
AI reads suppliers' food spec sheets and compares them with the ingredients, allergens, and origin on your product pages. Staff confirm before pages change.
Check testimonials quoted on product pages
Match reviews and posts quoted on your product pages against your log of commissioned posts. AI flags undisclosed ads; staff decide the fix.
Classify inquiries and draft replies
AI classifies messages from the inquiry form and drafts replies to common questions. A person reviews every reply before it is sent.
See this work in a demo
A 30-minute demo shows this workflow running. The 14-day free trial lets you check it on your own systems.