Collias, France · Available · Remote or hybrid

Ten
products.
One person.

I spent fifteen years running operations teams across three countries. Then I started building the tools instead of specifying them. Everything below is live, in production, and built solo with AI.

2,346Listings read nightly, one product
5,500SKUs qualified in six months
25Agents managed, peak
3Countries: IE · AT · FR
Nicolas Chareille

Nicolas ChareilleCollias, France · FR / EN

I am not a developer, and that is the point. I am an operations person who learned to direct AI the way I used to direct a team: define the outcome, set the constraints, review the work, ship it.

At Google Ireland I led a Quality Engineering team building the data-quality pipelines that fed model training. At Dodax in Vienna I ran customer service for a €40M e-commerce business with 25 agents across two sites. I know what breaks at scale, and I know that an automation laid over a process nobody measured just produces the same errors faster.

Since 2025 I have shipped ten products and websites on my own: an AI phone receptionist with a number you can call right now, a back-office assistant that reads 2,346 property listings a night and has the follow-up emails drafted by morning, a film recommendation engine with payments wired. Different domains, one method.

Selected work

Every item below is live and clickable. No mockups, no concepts, no case studies for things that were never built.

01 / Consultancy

Aure-lab

My AI operations practice. The positioning is the proof: we do not hand over recommendations, we put our own products into production under our own name. Aura answers Aure-lab's phone.

PositioningOffer designCopywritingNext.js
aure-lab.com ↗
02 / Product

Aura Assistant

An AI phone receptionist for small French businesses. It answers, books into the calendar, confirms by SMS, and escalates the urgent calls to a mobile. Not a demo video — a real line you can dial.

Next.jsVoice AITelnyxCalendar APIRGPD / AI Act
04 23 34 05 62Call it — Aura answers, 24/7
€79Entry price / month, excl. VAT
aura-assistant.fr ↗
03 / Product

Aura Immobilier

The back-office assistant for estate agencies. It reads 2,346 listings across the sector overnight, scores every one against each client's real criteria, and by morning the emails are drafted in the client's own language. Dictate your notes leaving a viewing and it returns a report ready to send to the vendor.

Next.jsLLM pipelineMatch scoringBilingual outputDictation → report
2,346Listings read nightly
538Scored per client
auraimmobilier.fr ↗
04 / Productised service

Hospitalité Digital

A web studio for hotels, guesthouses and restaurants. Sites built to fill rooms and tables rather than win awards: local SEO, direct booking, and the Google presence most small hospitality businesses never get round to.

Next.jsLocal SEODirect bookingMultilingual
hospitalitedigital.fr ↗
05 / Product

MovieMuse

Pick a genre and a subgenre, and the AI ranks films by how well they fit your taste — each one scored, with a written reason for the match and where you can actually stream it. Skip, save or mark as seen, and the queue re-ranks around what you liked.

ReactViteStripeTMDBMatch scoringBilingual EN/FR

Try it — it's free right now.MovieMuse is in its founding period: everything is open, no card, no limits. The first 500 members keep Premium free for a year.

moviemuse.co ↗
06 / Product

Rate My City

A review platform for cities: what it is actually like to live somewhere, written by people who do. Built to answer a question I had myself while planning a move.

Next.jsSupabaseModerationSEO
rate-my-city.com ↗
07 / Public interest

Hypospadias

A family-support resource on hypospadias, a congenital condition my son was born with. Every medical claim on the site was reviewed and verified by Professor Kalfa, paediatric urologist. The one project here I would keep running whether or not it ever pays.

Next.jsMedically reviewedSEO
hypospadias.fr ↗

Also live

Client work. Same stack, same method, shorter story.

L'Oxalis Restaurant site — Gault&Millau 2026 distinction published live ↗ Les Chambres d'Élise Guesthouse site, statically rendered multilingual pages ↗ Energy Clinic Medical wellness clinic, Croatia — bilingual EN/HR, two sites and treatment programmes ↗

How I actually
work with AI

The interesting part is not that AI wrote the code. It is that someone had to decide what to build, judge whether the output was good, and take responsibility for shipping it.

01

Measure before automating

Volumes, contact reasons, time spent. An automation on top of an unmeasured process reproduces its errors faster. This comes straight from running support teams, not from a framework.

02

Constrain the model

Written specs, hard limits, a defined stopping point. I brief AI the way I briefed a quality engineer at Google: the outcome, the constraints, and what "done" looks like.

03

Review like a lead

Model output is a first draft from a fast junior. It gets read, questioned, and sent back. Most of the value I add is knowing which plausible-looking answer is wrong.

04

Ship, then keep it alive

Live domain, real users, monitoring, backups, and someone on call — me. A prototype that never left localhost proves nothing about operating a system.

Background

Fifteen years of operations before any of this. That is what makes the AI work land.

2025 — now Independent AI product builderAure-lab Ten live products and websites, built and run solo. An AI phone receptionist on a real line, and a back-office assistant reading 2,346 listings a night for estate agencies.
2023 — 2025 Head of Content & Project ManagerVindima / Groupe Perret, Bagnols-sur-Cèze Project managed the e-commerce site launch: kept the ERP product data clean, captured the extra attributes e-commerce needed, and set up the customer service function. 5,500 SKUs qualified in six months.
2019 — 2022 Head of Customer ServiceDodax GmbH, Vienna €40M e-commerce, ~100 staff. 25 agents across Vienna and Warsaw. Customer Service Lead → Marketplace Manager → Head of Customer Service.
2014 — 2018 Quality Engineering LeadGoogle Ireland, Dublin ML and LLM data-quality pipelines feeding model training. 20 quality engineers in Dublin, oversight on 20 more in Los Angeles.
2003 — 2014 Xerox, then CitibankDublin Financial customer service, then corporate banking. Led and trained a team of ten agents.
Education RNCP Level 6CESI · obtained January 2026 Responsable en management d'unité et de projet. Also Licence d'Anglais (Pau). French native, English fluent after fifteen years in Ireland.