Skip to content
Perrine HonoréPerrine Honoré · AI & automation

AI integration and business process automation

In short

I integrate generative AI where it replaces real work: sorting and answering email, extracting data from documents, searching your internal documentation, first-line customer support. Agents, n8n workflows and OpenAI integration wired into the tools you already use, with the gain measured before anything is rolled out further.

Discuss my project
Book a free call30 minutes · No commitment

At a glance

Use cases
email triage, document extraction, internal search, first-line support
Technologies
OpenAI, Claude, RAG, embeddings, n8n, vector databases
Approach
one measured use case first, generalisation second
Integration
wired into your current tools, without replacing them
Data
hosting and retention settled before development starts
Deliverable
full source code and documented workflows

How the project runs

  1. First conversation

    Through the form or a free 30-minute call. You describe your need, I ask my questions and tell you frankly whether I'm the right person to build it.

  2. Scoping: scope, budget, schedule

    I put in writing what will be delivered, what won't, the budget and the schedule. The main screens are approved with you before development. The quote covers that written scope.

  3. Design and development

    The software is built in steps, with regular demos: you test progress as it happens. Any out-of-scope request is priced and approved in writing before it starts, never billed afterwards.

  4. Testing, launch and handover

    You have 7 working days after delivery to report a defect or a mismatch with the scope. Then launch, and handover of the code and access on your own accounts.

After delivery

Defect fixes
30-day warranty after delivery on critical and blocking defects in the delivered code.
Maintenance
Optional, as a monthly package defined in the quote. With an active contract: critical outage handled within 24 working hours, non-blocking defect fixed within 72 working hours.
New features
Each new feature gets an additional quote or amendment, approved before work starts.
Hosting
On your infrastructure or mine, your choice; terms are set out in the quote.
Code ownership and access
The code built for you is yours once fully paid, stored in your own space (e.g. your GitHub account). No technical or contractual lock-in.
Switching provider
You can hand maintenance or new work to someone else at any time: I create no deliberate dependency.

Full details are in the terms and conditions.

Frequently asked questions

What can AI actually do in my processes?

It reliably handles tasks that are repetitive, high-volume and stable in their rules: sorting incoming email, extracting data from documents, answering from internal documentation, handling first-line support. Expect two to four weeks for a first well-built workflow, and a 30 to 70 % time saving on the targeted task.

Does my data go to OpenAI?

That depends on choices made at scoping, and they are written down before development: which data leaves your infrastructure, to which provider, and under what retention terms. Where a genuine constraint blocks the cloud, a self-hosted open-weights model is an option, at the cost of GPU infrastructure to run and secure.

What does AI cost to run?

The recurring API bill is the item almost everyone underestimates, and it grows with usage while development is paid once. It is controlled by choosing the model per task rather than defaulting to the most capable one, and by limiting the context sent with each request.

How do I know the system is working well?

Through evaluations: a body of real cases with quality criteria, replayed whenever the model or the prompt changes. A generative AI feature is not deterministic, so conventional tests aren't enough: without evaluations, quality drift stays invisible until a customer reports it.

Do we have to replace our current tools?

No, and that is usually the wrong move. The workflows plug into what you already run: email, CRM, document storage, business tools. Replacing a working tool to accommodate an automation adds a migration project to an automation project.

AI is only worth it where it replaces real work

Most AI projects that fail did not fail technically. They failed because nobody could say which task was being replaced, or how the gain would be measured. "We want AI in our product" is not a use case; "our support team spends two hours a day sorting incoming email" is.

So the first conversation is not about models. It is about which task is repetitive enough, high-volume enough and stable enough in its rules to be worth automating, and what would count as success once it is.

The use cases that hold up in production

Four families cover the large majority of what I deliver, and they share a property: the rules are stable and the output is checkable.

  • Document processing: extracting structured data from invoices, contracts, forms or CVs, in a format your systems can consume directly.
  • Internal documentation search, a RAG assistant that answers from your own procedures and product sheets, citing its sources, instead of from general knowledge.
  • First-line customer support, an agent that genuinely resolves part of the requests and escalates explicitly as soon as it leaves its scope.
  • Automation workflows, connecting the tools you already use so information stops being copied by hand between them.

Measure before generalising

A generative AI feature is not deterministic: the same input can produce ten different outputs. Conventional tests don't catch that, which is why the first thing built alongside any AI feature is a set of evaluations: a body of real cases with quality criteria, replayed whenever the model or the prompt changes.

Without that, quality drift is invisible until a customer sends you a screenshot of your assistant inventing a policy that doesn't exist. With it, you know before they do, and you can change model without crossing your fingers.

Your data, and where it goes

Every AI project raises the same question, and it deserves a direct answer rather than reassurance: what leaves your infrastructure, to which provider, under what retention terms. These are settled at scoping, in writing, before any development.

Self-hosting an open-weights model is a legitimate option, but it trades a usage bill for GPU infrastructure to run, secure and keep updated. For the vast majority of products the cloud API wins on cost and quality. Where a genuine constraint blocks it, the self-hosted route is the right call, and I'll say which case you're in.

When another solution will fit better

  • AI projects without an identified use case. If we can't name the task being replaced, there is nothing to build.
  • Automating processes that aren't stable. Automating a process nobody agrees on hard-codes the disagreement.
  • Training models from scratch. I adapt and integrate existing models; I don't train foundation models.
  • Guaranteeing a percentage gain before measurement. Anyone promising a figure before seeing your data is selling, not estimating.

Let’s talk about your project.

Describe what you need in a few lines: I reply within one working day. Prefer a call? It's free and with no commitment.

Prefer to talk it through?

Book a free call30 minutes · No commitment

Required fields. Everything else is optional.

A few lines are enough: who it's for, what it should do, and what already exists.

Optional details

Reply within one working day. Your details are only used to reply to you (privacy).