PROJECTS.
Side projects and open-source work. Each one is live — explore the app, then see how it was designed.
AI Workflow Automation Platform
A self-hosted, multi-tenant platform that connects to business systems — email, CRM, helpdesk, accounting — and processes inbound events through configurable AI pipelines. Features a visual drag-and-drop workflow builder, 10 preset templates, and triple-provider LLM architecture with automatic fallback.
◆ ARCHITECTURE
Ingest
Events arrive from 10 built-in connectors — Gmail, Slack, Zendesk, Xero, and more — normalised into a universal WorkItem model.
Classify & Retrieve
AI classifies intent, urgency, and category. Hybrid RAG retrieves relevant context from knowledge bases via semantic + keyword search.
Reason & Safeguard
LLM drafts a response using classification and retrieved context. Guardrails check for PII, prohibited content, and bias.
Route & Act
Confidence-based routing: high-confidence items auto-resolve, uncertain ones go to human review. Replies sent, tickets updated, full audit trail logged.
CouncilMate AI
A RAG-powered AI assistant that helps Melbourne residents navigate city council services — from waste management and parking permits to pet registration and community events. Scrapes and processes real council data, then answers questions with grounded, cited responses.
◆ ARCHITECTURE
Scrape
Scrapy + Playwright crawl City of Melbourne pages and PDFs, extracting structured content.
Process & Index
Documents are chunked, embedded, and stored in ChromaDB with metadata for fast retrieval.
Route & Retrieve
User queries are routed to the right domain. Top-k relevant chunks are retrieved from the vector store.
Generate
Retrieved context is injected into the prompt. The LLM produces a grounded answer scoped to council services.
Sakura — Autonomous ML Agent
A local-first, multi-agent AI system that autonomously completes the full ML lifecycle — from data ingestion and exploratory analysis through feature engineering, model training, evaluation, and artifact delivery. 10 specialist agents coordinate through an orchestrator, with sandboxed code execution and support for 11 LLM providers.
◆ AGENT WORKFLOW
Ingest & Profile
Upload raw data with a business goal. The Data Analyst agent profiles types, distributions, and quality issues.
Research & Engineer
Web Researcher gathers domain context. Preprocessor cleans data. Feature Engineer creates and selects features.
Design & Train
Model Architect selects algorithms. Trainer runs training loops with hyperparameter tuning in a sandboxed environment.
Evaluate & Deliver
Evaluator runs cross-validation and metrics. Explainer generates SHAP analysis, model cards, and a final delivery report.