Case Studies & R&D
Selected Work
Explore shipped systems and clearly labeled R&D prototypes across AI automation, agents, and data intelligence.
AI/MLNLPRAG
Batch Disclosure — Price-Moving Catalyst Detection
An AI-powered system that scans ASX and SEC filings for forward-looking disclosures — contracts, M&A, guidance — that move micro-cap prices before the market catches on.
Read Case Study
AI/MLMulti-AgentGraphRAG
WikiGen — Autonomous, Bias-Aware Knowledge Synthesis
A multi-agent GraphRAG system that autonomously writes reliable, bias-aware Wikipedia-style articles with verifiable provenance on every claim.
Read Case Study
AI/MLLLMQLORA
Llama2 QLoRA Healthcare — Medical LLM on One GPU
A fine-tuned LLaMA-2-7B medical assistant trained with QLoRA on a single GPU — production-quality LLM fine-tuning without an expensive compute cluster.
Read Case Study
Computer VisionOCRPython
ERP Screen Change Detector
An AI-powered computer vision system that automatically detects meaningful screen changes in ERP demo recordings, captures key screenshots, extracts OCR text, and generates structured JSON, CSV, and HTML outputs for business process documentation and SOP automation.
Read Case Study
ETLBigQueryn8n
Shoprenter to BigQuery ETL Sync Pipeline
A production-grade n8n ETL automation that synchronizes 80K+ Shoprenter products with Google BigQuery using scalable batch processing, staging tables, MERGE/UPSERT operations, soft delete reconciliation, metadata enrichment, and fault-tolerant workflows for reliable ecommerce data synchronization.
Read Case Study
Computer VisionPrivacyPython
Real-Time Person Redaction — Privacy-First Computer Vision
A real-time computer vision system that keeps the primary subject in sharp focus while automatically redacting (blurring) anyone who enters the frame behind them — privacy-preserving masking applied live to a camera feed.
Read Case Study
R&D PrototypeHealthcare AIPharmacovigilanceMulti-Agent
SafeSignal AI — Human-Governed Pharmacovigilance Automation
A multi-agent pharmacovigilance workflow that transforms unstructured adverse-event information into traceable, reviewer-ready safety cases with duplicate detection and E2B(R3)-aligned output.
Read Case Study
Let's Work Together
Want Results Like These?
Every project starts with a clear problem, a bounded delivery plan, and evidence that the system works.