Jun 2026 – now · Casablanca, Morocco

Osoul
Technical Founder
Context
Fine-dining restaurants lose most of the data that would tell them who their guests are and what they come back for. Osoul is Revenue as a Service (RaaS): a SaaS growth engine built around specific revenue KPIs, with management tools built in, that captures that data and turns it into better KPIs.
My part
I am the technical founder and own the platform end to end: the multi-tenant backend on NestJS, PostgreSQL, Redis and Keycloak, and the three front ends.
- AI assistant: LangChain tools that act with the user’s own permissions, with personal data redacted and a confirmation before anything is written.
- Recommendations: dish and drink pairings, meal-completion promos and event-based dynamic menu pricing.
- Ad signals: a tracking event schema and signed server-side CAPI events for ad-audience optimisation.
- Ordering and sessions: NFC/QR table ordering with short-lived table sessions for anonymous diners.
- Reservations: deposits, queues, multi-channel reminders and bots, with loyalty used to smooth peak hours.
- Operations: diner identity merging, POS/PMS integrations, occupancy and SLA tracking.
- Front ends: Osoul Portal (web), Osoul Guest App and Osoul Waiter App (React Native).
Stack
Outcome
Live in two venues so far, from Barceló Group and Atlas Group. Revenue figures per KPI are on the Osoul case study.
What I'd do differently
I would have shipped the diner-identity merge before the recommendation engine, because every recommendation is only as good as the guest record behind it.




Projects at Osoul
All projects →
Flagship
Osoul platform
Revenue as a Service for fine dining. A multi-tenant SaaS that captures the data restaurants usually lose and turns it into revenue KPIs.

Deep dive
Multi-tenant platform with owned provisioning
Custom onboarding and Osoul-owned tenant provisioning, with full isolation of data, identity and configuration between restaurant groups.

Flagship
Osoul: an AI assistant that acts as the user
A LangChain assistant in the Osoul Portal that redacts personal data, calls tools with the user's own permissions, and asks before it writes anything.

Flagship
Osoul: recommendations and dynamic pricing
Dish and beverage recommendations, pairings and meal-completion promos in the Guest App, plus event-based dynamic menu pricing, on one menu data model.

Deep dive
Secure NFC/QR table sessions
How a tap on a table's NFC tag or QR code opens a short-lived session for an anonymous diner, bound to one table and one visit.

Flagship
Osoul: server-side tracking and CAPI sync
A tracking service built on the open-source tracking kit, turning guest events into signed server-side Conversions API events for ad-audience optimisation.