After the credit decision, an account manager retypes the customer, asset, schedule and interest from Soft4Leasing into a Word contract and annexes, and the error comes to light at signing in DocuSign. AI fills the template approved by your lawyers from Soft4Leasing data, flags non-standard terms, and people approve the document.
Built for ISO 27001NIS2 DORA
When the credit committee approves an application in Soft4Leasing or Business Central, the account manager opens the contract template in Word and retypes the customer details, the asset data with the VIN or serial number from the vehicle registry, the payment schedule, interest and insurance terms, then prepares the annexes: the handover certificate, the schedule and the insurance requirements. If the customer was granted a non-standard term, for example a deferred first instalment, it has to be entered correctly and agreed with the lawyer. Then the document is uploaded to DocuSign for signature. An error in the schedule or the VIN is noticed at signing or, worse, at handover of the asset. The lawyer checks every contract from scratch, because there is no way to know where the account manager may have departed from the template.
After the credit decision status in Soft4Leasing or Business Central, the solution reads the customer, asset, schedule, interest and insurance data with read-only access and passes it to Claude running on Amazon Bedrock in an EU region. The model fills in the contract template and annexes approved by your lawyers from a SharePoint document library, picks the right version for the product and customer type, cross-checks the asset data against the vehicle registry extract, and lists every term that differs from the standard in a separate list with an explanation. The account manager reviews the data, the lawyer reviews only the flagged places, and both approve in SharePoint. Only then does the flow send the document for signature via DocuSign, and the signed version returns to the contract in Soft4Leasing. We connect to Soft4Leasing through the Business Central API, a file export or an e-mail flow, depending on the version. The template text is never altered, customer data is not used for training, and every draft and approval is logged in line with GDPR and DORA.
Four steps from input to a record in your system, with human approval wherever there is risk.
When a Soft4Leasing or Business Central application reaches approved status, the flow reads the customer details, asset data, payment schedule, interest and insurance terms with read-only access and checks the VIN against the vehicle registry extract. If a required field is missing, for example the insurer, no draft is created and the account manager gets a notification.
The model picks the current template version from the SharePoint document library by product and customer type, and fills in the contract and annexes: the schedule, the handover certificate and the insurance requirements. Every term that differs from the standard text or from the credit decision in Soft4Leasing is listed with an explanation.
The account manager reviews the customer and asset data and the schedule, and the lawyer reviews only the flagged non-standard places. Both approve in SharePoint, and only then does the flow send the contract for signature via DocuSign. The signed version returns to the contract in Soft4Leasing. Without both approvals the document stays a draft.
If the credit decision contains a term that the template has no place for, the draft stops and goes to the lawyer for manual drafting. All drafts, changes, approvals and DocuSign sends are logged. When your lawyers update a template in SharePoint, the new version is used immediately, and we check the field mapping against Soft4Leasing.
Reading data from Soft4Leasing or Business Central after the credit decision, checking the VIN against the vehicle registry and pulling templates from the SharePoint library by version.
Mapping of each template and annex field to Soft4Leasing data, documented and approved by your lawyers.
Automatic flagging of differences from the standard text and from the credit decision, with explanations for the lawyer's review in SharePoint.
Approval by the account manager and the lawyer in SharePoint, sending via DocuSign only after both, return of the signed version to Soft4Leasing and a log for audit.
Claude via API on Amazon Bedrock in an EU region + data from Soft4Leasing or Business Central, templates from SharePoint, sending for signature via DocuSign. We connect to Soft4Leasing through the Business Central API, a file export or an e-mail flow, and to DocuSign through its API, depending on your version; we choose the method after a check. Read more about this service and its limits on the service page.
No. The model only fills in fields in the template approved by your lawyers and flags differences. The template text is changed only in your lawyers' SharePoint library, and all versions are kept.
Yes. We take the data after the credit decision through the Business Central API that Soft4Leasing runs on, or through a file export and an e-mail flow for older versions. We send the document to DocuSign through its API and return the signed version to the contract. We choose the integration method after a check in the first week.
The Claude model runs on Amazon Bedrock in an EU region, and data does not leave the EU or get used for training. Drafts are stored in your SharePoint, signed documents in Soft4Leasing, and we document the flow in your GDPR and DORA registers.
What is my balance, when is the next instalment, how do I settle early, send me a copy of the invoice: account managers answer this all day,…
Every day a collections specialist picks customers from the Business Central overdue report and writes reminders, arrangement offers and warnings…
An application with a balance sheet, profit and loss statement, bank statements and an asset quote: the risk analyst retypes everything into…
The appraiser's report based on Autovista or Eurotax, the seller's invoice, vehicle registry data and the insurance policy each contain a VIN, an…
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
AI risks are identified and managed like any other IT risk.
We reply within 1 business day
