Enter customer RFQs into your quoting system
AI reads part details from emailed RFQs and drawings, and they go into your quoting system with past quotes and costs. Estimators set the price.
- 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
Requests for quotation arrive by email or through customer portals, with drawings and specifications attached. Estimators pick out the material, dimensions, quantity, and surface treatment from the drawing's title block and notes, look up past quotes and actual costs for the same or similar parts in separate screens, and then enter it all in the quoting system. Only experienced staff know where to look, and when requests pile up, replies are late.
The workflow in Kitewell
- Receive the RFQ email and save the attached drawings and specificationsEmail
- AI reads the part number, material, dimensions, quantity, surface treatment, and requested date from the drawing's title block, notes, and specificationsAI judgment
- Look up past quotes and actual costs for the same or similar parts in the production management systemDesktop
- Enter the items read and the costs found in the quoting system and save it as a draftDesktop
- The estimator sets the processes, hours, and price, and finishes the quoteHuman task
- A manager reviews and approves the quoteApproval
- Send the approved quote as a reply to the RFQ emailEmail
What AI does
Reads the items a quote needs from RFQs and drawings in varied formats. Items it cannot read, or where the request and the drawing disagree, are pointed out to the estimator to confirm.
Where people decide
The estimator decides the processes, hours, price, and whether to take the job. A manager approves each quote before it is sent.
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 items you need are read correctly from your main customers' drawings and RFQs
- Whether AI can read and operate the quoting and production management systems' screens
- Which AI models your confidentiality agreements with customers allow drawings to be read by, including in-house and local models
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 set the price?
- No. AI reads the RFQ and drawings, looks up past quotes and costs, and enters them in the quoting system. The estimator decides processes, hours, and price, and a manager approves.
- Does it work for RFQs that arrive through customer portals?
- Yes. The first step is replaced with opening new RFQs in the customer portal and downloading the drawings. The PoC checks whether the portal's terms of use allow automated operation.
- 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.
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.
Turn supplier price increases into customer requests
Read suppliers' price-increase emails and list the items, dates, and margin impact. AI drafts each customer's revision request for the sales manager to approve.
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.