Work

Context, what was built, the numbers

Never the other way around: no storytelling before the result.

LuxenCrest — digital content agency

An end-to-end AI editorial pipeline — from trend monitoring to multi-platform publishing, with no manual intervention on generation.

Context

LuxenCrest is a digital content agency publishing on Instagram, LinkedIn and Twitter/X. The content — copy, visuals, carousels — is entirely produced by a system of agents, not an editorial team.

What was built

LangGraph agentic backend (7 agents: trend analyst, editorial direction, strategist, writing, image generation, QA, publishing), FastAPI + PostgreSQL + Redis, deployed on a VPS with observability (Arize Phoenix).

Result

20+ campaigns produced, blending copy and images
Under 2 minutes to get an Instagram campaign ready to approve or iterate on
Rigorous token-consumption tracking, in the client's own hands

Full case study →

LuxenInvest — AI financial advisory agents

Multi-agent wealth advisory with regulatory guardrails built in from day one (MiFID II, audit trail).

Context

A wealth advisory firm needs to assist its advisors on client profiling and asset allocation, without ever risking a regulatory breach.

What was built

React + FastAPI application orchestrating specialized agents (KYC, market, allocation, tax, risk, coaching, simulation), with a full audit trail of recommendations.

Result

7 agents orchestrated
[TO COMPLETE] KYC profile processing time
[TO COMPLETE] number of recommendations generated

Full case study →

Coming soon

Luxen Immo

AI-assisted property sourcing, location scoring and valuation — turning months of on-the-ground research into minutes.

Context

A future decision-support tool for real estate investment — property and location selection against investor criteria, automated on-the-ground analysis.

What was built

Not yet launched — in scoping.