Revise and resubmit food spec sheets
When labeling rules or ingredients change, AI finds likely affected products. After QA confirms, it fills each customer's template for review and submission.
- 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
In April 2026, Japan added cashew nuts to the allergens that must be labeled. Whenever ingredients or labeling rules change, staff trace affected products back through ingredient spec sheets and resubmit spec sheets to every customer that received them. Customers that don't use a shared spec-sheet service get a copy in their own template, one at a time.
The workflow in Kitewell
- AI searches ingredient spec sheets (PDF, Excel) for cashew nuts or other target ingredients and lists products likely affectedAI judgment
- QA staff confirm the affected products and the labeling changesApproval
- From the submission ledger, list the customers that received those products' spec sheets and their templatesAutomatic
- AI copies the confirmed changes into each customer's templateAI judgment
- Staff check the filled spec sheets and approve submissionApproval
- Submit through each customer's web intake screen and record the date in the ledgerWeb
What AI does
Finds mentions of target ingredients in ingredient spec sheets, quoting the matching passages. Copies the confirmed content into templates whose field names and order differ by customer.
Where people decide
QA staff decide which products are affected and how labels change. Staff also check for products the AI search may have missed.
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 target ingredients are found in ingredient spec sheets without misses
- Whether fields are copied correctly into each customer's template
- Whether each customer's terms allow automated operation of its intake screen, and how to handle customers who take spec sheets by email
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 AI decide allergen labeling?
- No. AI only finds mentions of target ingredients in ingredient spec sheets and shows where they are. QA staff confirm which products are affected and how labels change, and the approval is recorded.
- 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
Enter an Excel list into a web system
For each row of an Excel list of orders, AI enters it into a web system and writes the receipt number back into the row. Only failed rows are redone.
Enter records into a desktop accounting app
For each row of an Excel list, AI enters the record in a desktop app. A person approves before it is saved, and the slip number goes back into the row.
Read Excel purchase orders from email and enter them
AI reads Excel purchase orders in each customer's own layout, checks them against the product master, and enters them. A person checks orders that do not match.
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.