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.
- 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
Posts that came from influencer requests or free products are quoted on product pages as reviews or customers' voices. Since October 2023, hiding the fact that something is an ad has been regulated under Japan's Act against Unjustifiable Premiums and Misleading Representations, and the rules apply to the advertiser. With many quotes on the pages, staff compare each one with the log to see whether it was commissioned and whether it is clearly marked as an ad.
The workflow in Kitewell
- Add the log of requests and free products (who, which product, which post, what was provided) to a batch sheetAutomatic
- Open product pages on your site and each marketplace, and save the quoted reviews, customer stories, and social posts with screenshotsWeb
- AI matches the quotes against the log and flags commissioned posts with no clear ad labelAI judgment
- Staff review the findings and decide whether to add a label or remove the quoteApproval
- Write the results to the sheet and post the pages to fix to SlackAutomatic
What AI does
Matches the quoted text, poster names, and text inside images against the log and shows quotes that may come from commissioned posts. It also shows whether a label such as "Ad" or "PR" appears, and where.
Where people decide
Staff confirm whether a post was commissioned and judge whether the label is sufficient. Staff also decide how to fix the label or whether to stop showing the quote.
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 the log of requests and free products holds enough to match quotes (poster, post date, URL, and so on)
- Whether each marketplace's terms allow automated checks of product pages, and, if social posts themselves are checked, whether each platform's terms allow it
- Whether your company has set rules for what counts as a clear ad label
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
- Are we responsible for posts made by influencers?
- Japan's Consumer Affairs Agency states that the stealth marketing rules apply to the business supplying the product or service (the advertiser), not to the influencers it commissions. When you quote a commissioned post on your own product page, you need to check, as the advertiser, that it is clearly marked as an ad. Whether the label is sufficient is for staff to judge.
- 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
Track competitor prices
Check chosen competitor product pages every day, record price and stock changes, and alert the owner to large moves.
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.
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.
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.