- RAG
- LLM
- FASTAPI
- DOCKER
- +1
AI Insight Assistant
An assistant that combines RAG and a SQL agent over your data: it retrieves from a document corpus and queries a database, served with FastAPI and Streamlit and packaged in Docker. Code at github.com/delcenjo/ai-insight-assistant.
This case study went into production combining art direction, UX/UI design, motion design and creative development in a single pipeline. The goal: make navigating the product feel like a small cinematic experience, not another catalogue.
Tech stack: React, Three.js, GSAP + ScrollTrigger, custom GLSL shaders and Lenis for smooth scroll. 3D models compressed with DRACO and textures in KTX2 to hold 60 fps on mid-range mobile.
Phase 1
Concept
Workshops with the client, visual reference exploration, defining the narrative rhythm and the scroll-driven beats.
Phase 2
Design
Figma mockups with a component system, variable type, an oklch-based palette and a full motion specification.
Phase 3
Build
React + Three.js implementation, asset optimisation, headless CMS integration, cross-device QA and a documented handoff.
Work with JMWEB
Let's build something that reaches production.
It all starts with a conversation. Bring a dataset, a goal or a model that is stuck; I will take care of the rest.
Start a project
Next projects:
Credit Risk Platform
End-to-end MLOps platform for credit-default scoring: reproducible training with a versioned model registry, a FastAPI inference API with input validation, PSI drift monitoring and a Prometheus and Grafana observability stack, all containerised with CI. Code at github.com/delcenjo/credit-risk-platform.
Transformer from scratch
A GPT-style language model implemented from scratch in PyTorch: multi-head attention, causal masking and residual blocks written by hand, plus a byte-pair tokenizer and an ablation study. Code at github.com/delcenjo/transformer-from-scratch.
Crafted with
