ABAdrien Bonvallet
AI automation · SMBs, firms and mid-market

Your documents handled
without manual entry.

Emails, PDFs and invoices read by custom AI tools, checked, then delivered clean into your systems. Your team validates instead of retyping.

Reply within one business day · First call with no commitment

Experience gained at

Sopra SteriaEPITECHCSU Long Beach

The hidden cost of manual entry

Three symptoms that show up in almost every company I work with.

An inbox that never empties

Dozens of requests a day to read, sort and reassign by hand. The whole process depends on one person, and stops when they are away.

PDFs retyped by hand

Invoices, payment notices, purchase orders: the same amounts and references keyed two or three times into two or three different tools.

Data nobody can read

The information exists, but it sits in raw exports nobody opens. Decisions end up being made on gut feel.

What I put in place

Proven building blocks, assembled around your existing process — not the other way round.

Your inbox, handled on its own

Every incoming email gets read, understood and sorted automatically. The right actions fire without anyone opening the mailbox.

LLMMicrosoft Graph APIFunction callingAsync queue

PDFs in, clean data out

Invoices, quotes, contracts: documents are read and turned into usable data. No manual re-entry.

OCRVision LLMSchema validationAPI / CSV export

Data your clients actually read

A clean interface where your clients and teams see what matters, instead of a raw export to decode.

Next.jsReactPostgreSQLRole-based auth

From idea to app in production

The full product, built end-to-end: back end, interface, deployment and support once it is live.

TypeScriptNode.jsReact NativeCI/CD
See services in detail
Measured client results

1,000+

emails and documents handled every week by the delivered tools

4 h

freed up every day in the teams using them

24 h

business-day response time on any request

Figures observed in production at a client. Results depend on your volume and data quality.

Payment notice automation
Case study

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
Read the case study
A four-step method

Every step has a deliverable and a price agreed up front. You can stop at the end of any of them.

  1. 015 days

    Diagnostic

    I observe the real process, measure the time spent and map the flows. Deliverable: a costed scoping note with expected gain and implementation cost.

  2. 022-3 weeks

    Prototype

    A first working version on your real data, tested by your team. Goal: validate accuracy before investing further.

  3. 032-4 weeks

    Production

    Integration with your tools, edge-case handling, consistency checks, logging and manual fallback whenever confidence is low.

  4. 04ongoing

    Support

    Monitoring, adjustments and new features. The code and documentation are yours: your team can take over at any point.

Let's talk about your process

Thirty minutes to understand your document flow and tell you, plainly, what can be automated and what cannot.