Projects

A portfolio of production-grade AI systems, from physics-informed energy platforms to agentic RAG chatbots, MLOps pipelines, and developer tools.


Ongoing: Enterprise AI Automation

Agentic ERP Automation Platform LIVE IN PRODUCTION

An agentic automation platform layered on a live commercial cloud ERP, running the full procure-to-pay chain for a multi-entity food manufacturing group. Automated reorder proposals and purchase orders, AI vision extraction of vendor invoices, statistical matching of invoices to their goods receipts, purchase invoice creation in the ERP, a three-gate payment approval flow with enforced separation of duties that executes real bank transfers, bank statement reconciliation, and guarded payment write-back into the ERP.

Built with no ERP sandbox and no test tenant, so every safety property had to be engineered: a GET-only nightly mirror for all reads, a seven-layer write-guard with idempotency and read-back verification, dry-run shadow mode by default, and per-capability feature flags canaried one document at a time.

Technologies: FastAPI, Next.js, PostgreSQL, Claude (headless CLI + vision), MCP, Docker Compose, Alembic, Nginx

Highlights: 4 operational pillars, 87 API endpoints, 43 read-only AI tools, 5 guarded ERP write capabilities, 15 containerized services, 34 tables, live and moving real money

View Project ->


Mobile & Kiosk Apps

Face-Attendance Android App + Outlet Kiosk FLUTTER PILOT

One Flutter codebase shipping as two products: an employee phone app where clocking in is a face verification inside a geofence, and the same binary running as a shared outlet kiosk tablet with no login and no session, bound to one work site.

Built for store floors rather than for a demo: a server-issued head-turn liveness challenge with a three-frame burst verified server-side (nothing the app claims about liveness is trusted), no face embedding ever computed on the device, a file-backed offline clock queue replayed with its original timestamp and flagged as late-synced, device binding through a fingerprint in secure storage, and self-updating outside the Play Store from a published manifest with a non-dismissible floor for releases nobody may skip.

Technologies: Flutter, Dart, Riverpod, go_router, dio, Google ML Kit face detection, camera, geolocator, drift/SQLite, flutter_secure_storage, wakelock_plus

Highlights: 2 run modes from one binary, ~4,000 lines of Dart, offline-first clock-in, roster-scoped kiosk matching with a NIK fallback, per-architecture release handling

View Project ->


Ongoing: Workforce Platforms

HR & Face-Attendance Platform STAGING, PILOT

A company-owned HR platform for a multi-entity food and beverage group of roughly 45 outlets, built on three surfaces over one backend: an Android app where employees clock in by face inside a geofence, the same app running as a shared kiosk tablet in each outlet, and an HR web dashboard for attendance, contracts, incidents, salary progression and payroll.

Face verification runs server-side on CPU (InsightFace ArcFace) with an active liveness challenge on the device, a review band instead of a guess between the accept and reject thresholds, and a kiosk that matches only against one outlet's roster for one day. Contract renewal recommendations come from a rule engine with the evidence shown next to them; the model writes the narrative and never produces a number. Biometric handling is designed against Indonesia's UU PDP No. 27/2022: encrypted templates, no export endpoint, explicit consent, and documented retention.

Technologies: FastAPI, PostgreSQL + PostGIS, Next.js, Flutter, InsightFace + onnxruntime, Claude (headless CLI), MCP, Docker Compose

Highlights: 3 surfaces, 136 API endpoints, 42 tables, 9 read-only AI tools, 326 employees and 45 work sites on staging, payroll engine pending a parallel run

View Project ->


Ongoing: AI-Native Applications

Two applications built on the same architectural idea: one shared live state edited by both a human and an AI agent, an MCP tool layer instead of code generation, and a headless Claude Code agent running on a subscription.

TransForce - AI-Native Particle Transport DEPLOYED

Chat-driven Monte Carlo radiation transport on OpenMC. Describe a reactor physics problem in plain language and an agent builds the CSG geometry, materials, source and tallies, runs the transport calculation, and reports k-eff with uncertainty. Ingests a paper from an arXiv id, DOI, URL or PDF, extracts a structured model spec, reproduces it, and reports the bias in pcm against the published values.

The agent never writes Python: it manipulates a typed, provider-agnostic ModelSpec, and a deterministic driver translates that into live OpenMC objects. Includes depletion, weight-window variance reduction, MGXS generation, and PDF reporting.

Technologies: Python, FastAPI, FastMCP, OpenMC, Pydantic, React, Vite, matplotlib, reportlab, Docker

Highlights: 27 simulation MCP tools, 4 benchmark presets including Godiva, 3 compute backends (local/VPS/GCP), C/E comparison in pcm, runs on a Claude subscription with no API key

View Project ->


CutForce - AI-Native Video Editor DEPLOYED

A browser video editor where a human and an AI agent edit the same timeline simultaneously, over 43 MCP tools and a live WebSocket-synced store, with an embedded terminal wired to the editor's own MCP endpoint. Undo works across both editors because every mutation funnels through one commit path.

The export engine compiles the timeline into a single ffmpeg filter_complex: keyframes become piecewise-linear ffmpeg expressions, speed changes chain atempo stages, and colour grades resolve from the same numbers in both the CSS preview and the ffmpeg render.

Technologies: TypeScript, Express, MCP SDK, React, Vite, zustand, xterm.js, ffmpeg, node-pty, Veo/Imagen/FLUX, Docker

Highlights: 43 MCP tools, 7 authored agent skills, 12 grade presets, cross-editor undo, generative clips with cost estimation, runs anywhere Node and ffmpeg run

View Project ->


Flagship — ForceX AI

ForceX AI — AI-for-Energy Platform

Indonesia's first AI-for-energy platform — 12 physics-informed AI products for nuclear, geothermal, oil & gas, and renewables. Multi-agent orchestration with LangGraph, CNN/PINN/GNN/LSTM models, and production deployment.

Technologies: PyTorch, LangGraph, PINNs, GNNs, CNN, LSTM, RL (PPO), FastAPI, React, Docker

Highlights: 12 products, 484 tests, GeoForce deployed (R²=0.997), published on HuggingFace

View Project → | Visit forcex-ai.com →


GeoForce — CNN Geothermal Reservoir Surrogate

Standalone production version of the GeoForce CNN surrogate model. Replaces hours of TOUGH2 geothermal simulation with sub-second inference at R²=0.997 accuracy.

Technologies: PyTorch, CNN, TOUGH2, FastAPI, HuggingFace Hub

Highlights: 57K params, R²=0.997, model + dataset published on HuggingFace

View Project →


LLM Fine-Tuning & Alignment

EnergyLM-7B — LLM Fine-Tuning & Alignment Pipeline IN PROGRESS

End-to-end LLM training pipeline for a domain-adapted energy model. Fine-tunes Qwen2.5-7B using QLoRA SFT on 20K synthetic instructions, compares DPO vs ORPO alignment, trains a reward model, and evaluates across 10 benchmarks. Multi-teacher data generation, dedup/filter pipeline, AWQ/GGUF quantization, vLLM serving. $0 budget — 100% free compute.

Technologies: PyTorch, Transformers, TRL, PEFT, QLoRA, DPO, ORPO, lm-eval-harness, vLLM, AutoAWQ, llama.cpp, Kaggle T4

Highlights: 20K synthetic dataset, DPO vs ORPO comparison, 10-benchmark evaluation, CoT distillation, reward modeling, AWQ + GGUF quantization, $0 compute cost

View Project → | ForceX-AI on HuggingFace →


GenAI & LLM Systems

Enterprise Agentic RAG Chatbot

Agentic RAG system with LangGraph multi-agent orchestration, self-reflective retrieval, hybrid search, and streaming responses. Deployed in production for enterprise documentation Q&A.

Technologies: LangGraph, LangChain, FastAPI, React, pgvector, Langfuse, Prometheus

Highlights: Self-reflection loop, 14 specialized agents, multilingual (ID + EN), production-deployed

View Project →


Agentic HR Intelligence Platform

Full-stack AI-powered HR platform that transforms raw employee and attendance data into workforce intelligence. Features an agentic AI chat with 5 specialized tools (Gemini 2.5 Flash), interactive analytics dashboards, turnover risk scoring, anomaly detection, and AI-driven contract renewal recommendations.

Technologies: Next.js 16, React 19, FastAPI, PostgreSQL, Google Gemini 2.5 Flash, Recharts, Tailwind CSS 4

Highlights: 5 agent tools with 10-iteration tool calling, 5-factor risk scoring (0-100), 5-type anomaly detection, bilingual (ID + EN), PDF report generation

View Project →


AI-Powered Help & QnA System

Production-ready RAG system with hybrid retrieval (dense + BM25 + RRF fusion), multi-provider LLM fallback chain (5 providers), cross-encoder reranking, and voice assistant.

Technologies: FastAPI, pgvector, BGE embeddings, Redis, React, Docker, Kubernetes

Highlights: 40K+ docs indexed, 75%+ cache hit rate, ≤5% hallucination rate, 100% free-tier LLMs

View Project →


Porto Agent — AI Content Marketing Platform

AI-powered platform that generates technical blog posts and LinkedIn content from git commit history. LangGraph orchestration with human-in-the-loop approval via dashboard and Telegram.

Technologies: Gemini 2.5 Flash, LangGraph, FastAPI, Next.js, PostgreSQL, Telegram Bot API

Highlights: Auto-generates blog + LinkedIn posts from commits, human-in-the-loop approval workflow

View Project →


Computer Vision & Video Analytics

Retail Video Analytics - Customer Behaviour from CCTV COMPLETED

An end-to-end pipeline that turns two retail CCTV cameras into behavioural metrics: store interest and walk-in conversion, per-shelf engagement events, and genuine staff-to-customer interaction sessions. YOLO11m detection with ByteTrack identity persistence, entirely on CPU, reproducible from one Docker command.

The engineering is in the layer above the detector. Perception is cached so that behavioural thresholds can be tuned interactively instead of at 80 CPU-minutes per iteration. Speeds and distances are normalised by body height so a single threshold holds across the depth of the frame. Shelf assignment uses the torso rather than the feet, after an audit showed browsing customers' feet stay in the aisle while their upper body leans into the fixture. An apron-colour staff classifier was built, measured, and rejected in favour of a spatial rule that actually separates the classes.

Technologies: Python, YOLO11m (Ultralytics), ByteTrack, PyTorch CPU, OpenCV, pandas, YAML, Docker

Highlights: 2 cameras, 3 behavioural metrics, 10 fps effective inference on CPU, zone geometry validated against plotted real tracks, interpolation guard that stopped a phantom interaction, documented misses

View Project ->


AI Applications

Deployable AI product builds, each a live, working demo grounded on Gemini 2.5 Flash (Vertex AI), built with Next.js and deployed on a VPS with automatic HTTPS.

AI Sales & Lead-Gen Chatbot (WhatsApp / Instagram)

A 24/7 sales assistant that answers pricing/schedule questions, handles objections, captures every lead, classifies status, and saves to a CRM with hot-lead alerts. Web chat plus WhatsApp/Instagram channels.

Technologies: Gemini 2.5 Flash, Next.js, JSON-mode extraction, file CRM, Telegram alerts

Highlights: Two-call architecture (reply + structured lead extraction), status classification, live admin dashboard

View Project →


Upload documents and a RAG pipeline writes a fresh 8-10 slide LinkedIn carousel grounded in the content, with a topic-dedup log, exportable as a LinkedIn-ready PDF.

Technologies: Gemini 2.5 Flash, Vertex text-embedding-004, vector retrieval, jsPDF + html-to-image, Next.js

Highlights: Grounded slide generation, topic dedup, native carousel rendering (no Canva API), isolated PDF parsing

View Project →


Self-Correcting Document Pipeline (LangGraph)

A supervisor-worker LangGraph agent that extracts invoice data, validates the arithmetic deterministically, self-corrects on mismatches (capped retries), and writes a report — with a live graph, streamed steps, and an eval panel.

Technologies: LangGraph (@langchain/langgraph), Gemini 2.5 Flash, React Flow, SSE, Next.js

Highlights: Real StateGraph with conditional self-correction loop, deterministic validation, per-run token/latency/loop evaluation

View Project →


AI Assistant Embedded on a Portfolio Site

A floating AI chatbot embedded on a personal site that answers visitors' free-form questions about skills, projects and availability, grounded in the site content so it never invents facts.

Technologies: Gemini 2.5 Flash, Next.js, knowledge-base grounding, embeddable widget

Highlights: Anti-hallucination grounding, hire-intent nudging, drops into any existing site

View Project →


WhatsApp Lead Bot with Photo-on-Demand (Real Estate)

An always-on WhatsApp assistant for studio rentals that answers questions, sends a property photo gallery on request, captures leads, and books viewings, with editable galleries.

Technologies: Gemini 2.5 Flash, Next.js, token-driven photo delivery, file CRM

Highlights: Text-plus-photos via model-emitted tokens, grounded answers, lead capture and status

View Project →


WhatsApp AI Chatbot with Product Compatibility (Automotive)

A WhatsApp chatbot for an automotive electronics business: KB-grounded answers, product compatibility by car model with upgrade suggestions, rule-based human handoff, and lead capture.

Technologies: Gemini 2.5 Flash, Next.js, compatibility rules + KB grounding, file CRM

Highlights: Model-aware product recommendation, deterministic premium-brand handoff, editable knowledge base and rules

View Project →


InsightFlow -- AI Analytics Workspace

Upload a CSV and the workspace auto-builds a dashboard: KPIs, anomaly detection across every metric, a trend chart, AI-written insights, and a natural-language layer to ask questions about the data. Deterministic stats in code, LLM for narration only.

Technologies: Gemini 2.5 Flash, Next.js, Recharts, PapaParse, TypeScript analytics engine

Highlights: IQR anomaly detection, grounded AI insights and Q&A (no hallucinated numbers), BI-style workspace UI

View Project →


MarketMind -- AI Crypto & Stock Market Intelligence

A market-intelligence SaaS: live crypto prices, technical indicators (SMA, RSI, volatility), a Bullish/Bearish/Neutral signal, AI-written analysis grounded on the indicators, and a chat to ask about any asset. Polished dark trading terminal.

Technologies: Gemini 2.5 Flash, Next.js, Recharts, CoinGecko, TypeScript indicators engine

Highlights: Live data, technical analysis in code, grounded AI analysis + Q&A (no hallucinated numbers), signal generation

View Project →


DataPilot -- Private AI Data Analyst

A self-hostable "code interpreter": describe an analysis in plain English, the AI writes the Python, runs it in a sandbox, and returns a report (charts + results + the code), refined by prompting. Privacy-first -- the model only sees the schema, and it runs on a local model (Ollama) so data never leaves the machine.

Technologies: Next.js, Gemini / local Ollama (Qwen2.5-Coder), Python sandbox (pandas, matplotlib, scikit-learn), Docker

Highlights: Live streaming code-gen, self-correction loop, switchable cloud/local model, sandboxed execution, fully on-premise/air-gappable

View Project →


HealthPredict -- Clinical Risk Prediction

A self-hostable web app that turns routine clinical values into an explained ML risk estimate for common conditions (diabetes, heart, kidney, liver, thyroid). Each condition is scored by a Logistic Regression + Random Forest ensemble, with the contributing factors ranked on every result.

Technologies: Python, Flask, scikit-learn (LogReg + Random Forest), SQLAlchemy (SQLite/MySQL), gunicorn + nginx

Highlights: Two-model ensemble per condition, explainable factor breakdown, history dashboard, admin console, light/dark, production-deployed

View Project →


Web & Business Systems

LeadFlow -- Sales & Lead Management System

A full-stack CRM: multi-source lead capture, a visual deal pipeline (New -> Contacted -> Quoted -> Won/Lost) with per-stage value totals, overdue follow-up reminders, and conversion analytics. REST API with a swappable data store.

Technologies: Next.js, TypeScript, Tailwind, Recharts, REST API, file/Airtable/Supabase/MySQL store

Highlights: Kanban pipeline, multi-source capture form, follow-up reminders, funnel + value-by-stage analytics

View Project →


MLOps & Infrastructure

Broadcast Analytics — MLOps Platform

Enterprise MLOps platform with 24 trained models (6 algorithms × 4 targets), LLM-powered analytics chat, genetic algorithm schedule optimization, and full monitoring stack.

Technologies: FastAPI, scikit-learn, XGBoost, CatBoost, LangChain, Redis, Prometheus, Grafana, Docker, Kubernetes, GitHub Actions

Highlights: 24 models, genetic algorithm optimizer, Prometheus + Grafana + Alertmanager + Loki monitoring, full CI/CD

View Project →


Media Platform — Ad Campaign Management

Comprehensive enterprise media platform with OTT streaming, broadcast management, media asset management, and multimodal AI (NLP + Vision + Audio). Microservices architecture deployed on Google Cloud Platform.

Technologies: NestJS, Next.js 14, Kafka, PostgreSQL + pgvector, MinIO, CLIP, Whisper, spaCy, Docker, Kubernetes, GCP (Cloud Run, Cloud SQL, Artifact Registry, Secret Manager)

Highlights: 5 Cloud Run microservices in production, managed PostgreSQL with private networking, MediaMTX streaming on Compute Engine, 350+ pages documentation

View Project →


GPU Computing

AI Service Migration: CPU to GPU (RTX 5060)

Migrated a multimodal AI inference pipeline (Whisper, CLIP, YOLO) from CPU-only VMs to a dedicated NVIDIA RTX 5060 GPU server. Solved Blackwell sm_120 compatibility issues, managed VRAM constraints on 8 GB, and achieved zero-downtime rolling cutover.

Technologies: NVIDIA CUDA, PyTorch 2.11.0+cu128, faster-whisper (CTranslate2), CLIP, YOLOv8, Docker + nvidia-container-toolkit, Bull/Redis

Highlights: 8.7x pipeline speedup, Blackwell sm_120 CUDA fix, VRAM budgeting (67% of 8 GB), zero-downtime rolling migration with instant rollback

View Project →


Developer Tools

Automation Testing Platform (ATP)

Playwright-like testing framework specialized for AI platforms — LLM APIs, AI chat UIs, and intelligent applications. Published on npm with full TypeScript support.

Technologies: TypeScript, Node.js, Playwright, Fastify, Next.js, pnpm + Turborepo

Highlights: Published on npm (@robi-atp/*), semantic similarity testing, hallucination detection, AI-aware browser selectors

View Project →


Research

Recommendation Systems Research

Comprehensive comparison of YouTube Two-Tower, Netflix Foundation, and Hybrid recommendation architectures with 108 hyperparameter configurations tested.

Technologies: PyTorch, FAISS, Transformers, Gradio

Highlights: 0.744 best combined score, 3 architectures, interactive Gradio apps

View Project →


Project Categories at a Glance

Category Projects Key Skills
Mobile & Kiosk Apps Face-Attendance App + Outlet Kiosk Flutter, Dart, ML Kit on-device liveness, camera, geolocation, offline sync queue, kiosk mode, out-of-store releases
Enterprise Automation Agentic ERP Platform, HR & Face-Attendance Platform FastAPI, Next.js, guarded ERP write-back, MCP tool servers, RBAC and audit, Docker Compose
LLM Fine-Tuning EnergyLM-7B QLoRA SFT, DPO, ORPO, CoT distillation, reward modeling, quantization
Physics-Informed ML ForceX AI, GeoForce PINNs, CNN surrogates, simulation, HuggingFace
GenAI & LLM Agentic RAG, HR Intelligence, Help QnA, Porto Agent LangGraph, RAG, multi-agent, agentic tool calling, LLM fallback chains
MLOps Broadcast Analytics, Media Platform ML pipelines, model registry, CI/CD, monitoring
GPU Computing AI Service Migration (CPU to GPU) NVIDIA CUDA, PyTorch cu128, Docker GPU, VRAM budgeting, Blackwell sm_120
Developer Tools ATP npm publishing, TypeScript frameworks, AI testing
Cloud & Infrastructure Media Platform GCP Cloud Run, Cloud SQL, Kubernetes, Terraform
Research Recommendation Systems PyTorch, FAISS, Transformers