ABAdrien Bonvallet

Case studies

The context, what was built, and what changed.

Payment notice automation

Property management

Payment notice automation

A tool that reads payment notices received by email, extracts the financial data with an LLM and prepares the reply email for one-click approval.

emails and documents per week
1,000+

emails and documents per week

freed up per day
4 h

freed up per day

manual re-entry
0

manual re-entry

LLMPDF extractionMicrosoft Graph APIPython

The client received PDF payment notices every day, processed by hand line by line in a shared mailbox. The whole flow depended on a single person and stopped whenever they were away.

The tool intercepts incoming emails through the Microsoft Graph API, extracts the attached PDF, then uses an LLM to identify and structure the key financial data: amounts, references, dates, payees.

A review screen lets the operator check extracted values, correct them if needed, then trigger a formatted reply email. Low-confidence extractions are flagged and never sent without validation.

Result: over 1,000 emails and documents handled every week, around 4 hours freed up per day for the team, and a process that no longer depends on one person.

More case studies are being published. Ask me for detailed references during our call.

A similar flow at your company?

Describe your process in a few lines: I'll tell you quickly whether it can be automated and what it would take.