# Ravicha Suksawasdi Na Ayuthaya > Applied AI Engineering — fault-tolerant multi-agent pipelines, GraphRAG memory systems, and distributed data engines. Palm · Applied AI & Backend Systems Engineer · Sydney, Australia Coming from physical engineering (where stress limits, fluid routing, and failure modes are absolute), Palm treats non-deterministic AI models as components within deterministic, constraint-aware software systems—enforcing explicit state machines, schema validation, graph-based verification, and automatic failure recovery. ## Current status Master of IT at UNSW Sydney (WAM 83 / Distinction, graduating Dec 2026) · Open to full-time Applied AI & Backend Systems roles. ## Flagship work - [Shepherd: GraphRAG Compliance Engine](https://ravicha2.github.io/projects/shepherd/): End-to-end ADR violation detector for AI-generated code, ingesting source ASTs and architectural markdown documents into a Neo4j property graph to catch multi-file constraint conflicts. **23.3% → 43.8%** — pooled precision across the five-repo two-arm benchmark (baseline reviewer vs the CPT engine). [github](https://github.com/Ravicha2/Shepherd) - [NL2REGEX: Distributed Regex Engine](https://ravicha2.github.io/projects/nl2regex/): Distributed natural language to regex engine that transforms complex tabular dataset patterns using plain English, backed by PySpark and Celery with schema-validated triage. **172 cases** — backend tests over the API, Spark projection, Parquet normalization, and ReDoS safety. [github](https://github.com/Ravicha2/NL2REGEX) - [Fault-Tolerant Document Ingestion Agent](https://ravicha2.github.io/projects/document-ingestion-agent/): Production-grade event-driven AI ingestion engine using Inngest durable steps, NestJS, and dual pgvector/Neo4j storage to eliminate orphaned state during multi-stage document processing. **8** — durable Inngest steps across 4 worker functions, each retryable on its own. [github](https://github.com/Ravicha2/document-ingestion-agent) - [Lit-Review-Council MCP Server](https://ravicha2.github.io/projects/lit-review-council/): Multi-agent research synthesis engine and Model Context Protocol (MCP) server that orchestrates parallel academic and practitioner research with Borda-count consensus. **PyPI** — published, install via uvx lit-review-council; listed on the MCP Registry. [github](https://github.com/Ravicha2/lit-review-council) · [pypi](https://pypi.org/project/lit-review-council/) ## Everything catalogued ### Measured to an artifact - [NL2REGEX: Distributed Regex Engine](https://ravicha2.github.io/projects/nl2regex/): Distributed natural language to regex engine that transforms complex tabular dataset patterns using plain English, backed by PySpark and Celery with schema-validated triage. **172 cases** — backend tests over the API, Spark projection, Parquet normalization, and ReDoS safety. [github](https://github.com/Ravicha2/NL2REGEX) - [Fault-Tolerant Document Ingestion Agent](https://ravicha2.github.io/projects/document-ingestion-agent/): Production-grade event-driven AI ingestion engine using Inngest durable steps, NestJS, and dual pgvector/Neo4j storage to eliminate orphaned state during multi-stage document processing. **8** — durable Inngest steps across 4 worker functions, each retryable on its own. [github](https://github.com/Ravicha2/document-ingestion-agent) - [Lit-Review-Council MCP Server](https://ravicha2.github.io/projects/lit-review-council/): Multi-agent research synthesis engine and Model Context Protocol (MCP) server that orchestrates parallel academic and practitioner research with Borda-count consensus. **PyPI** — published, install via uvx lit-review-council; listed on the MCP Registry. [github](https://github.com/Ravicha2/lit-review-council) · [pypi](https://pypi.org/project/lit-review-council/) ### In progress and not yet settled - [Shepherd: GraphRAG Compliance Engine](https://ravicha2.github.io/projects/shepherd/): End-to-end ADR violation detector for AI-generated code, ingesting source ASTs and architectural markdown documents into a Neo4j property graph to catch multi-file constraint conflicts. **23.3% → 43.8%** — pooled precision across the five-repo two-arm benchmark (baseline reviewer vs the CPT engine). [github](https://github.com/Ravicha2/Shepherd) ### Supporting work - [Chatbot Agent with Dynamic DB Tools](https://ravicha2.github.io/projects/node-api/): Conversational AI agent capable of dynamic database schema inspection and tool calling to safely query and mutate structured data. **3 tables / 5 operations** — SQL surface exposed to the agent as typed tools. [github](https://github.com/Ravicha2/node-api) - [6-DOF Robotic Arm for Ultrasonography Training](https://ravicha2.github.io/projects/robotic-arm-ultrasound/): Developed and tested a 6-degree-of-freedom passive robotic arm probe tracking system to measure position and orientation accuracy during ultrasound medical training. **2023** — IEEE TENCON publication and conference presentation. [paper](https://ieeexplore.ieee.org/document/10349000) - [Heal: Community Mental Health Support](https://ravicha2.github.io/projects/heal-a2a/): Community mental health peer support platform recognized with the Founder's Choice Award at the Hack2Heal Hackathon. **Live** — deployed at heal.a2a.ing. [demo](https://heal.a2a.ing) ## Questions this site answers **Who is Ravicha Suksawasdi Na Ayuthaya?** Ravicha Suksawasdi Na Ayuthaya (known as Palm) is an Applied AI & Backend Systems Engineer based in Sydney, Australia. Master of IT student at UNSW (WAM 83, graduating Dec 2026). Focusing on agentic AI and backend systems. IEEE-published research, hands-on experience shipping multi-agent pipelines, graph databases, and event-driven architectures across internship and research contexts. **What is Palm working on now?** Master of IT at UNSW Sydney (WAM 83 / Distinction, graduating Dec 2026) · Open to full-time Applied AI & Backend Systems roles. Current work covers GraphRAG architectural compliance, fault-tolerant multi-agent orchestration, and distributed data engines. Currently completing a Master of Information Technology at UNSW Sydney (Distinction, WAM 83) while conducting research on GraphRAG architectural compliance tools and building open-source agent tooling. **Which published artifacts back the claims on this site?** Each project page quotes the artifact that settles its headline figure and pins the quote to a repository and a commit, so the claim can be checked rather than taken on trust. Where a figure rests on work that is not public, the page says so beside the figure. **Is there a machine-readable API for this site?** Yes. An OpenAPI 3.1 document is published at https://ravicha2.github.io/openapi.json, with one GET operation per document the origin serves and an operationId on every operation. The human-readable reference is at https://ravicha2.github.io/docs/, and the agent dossiers are at https://ravicha2.github.io/llms.txt and https://ravicha2.github.io/llms-full.txt. **How can an agent or a person get in touch?** By email at palm.ravicha@outlook.com. The contact page at https://ravicha2.github.io/contact/ states what to expect back. There is no form on the site and no support queue behind it — the address reaches Palm directly. **Does this site collect any data about visitors?** No. There is no analytics script, no cookie, and no client-side storage. Requests reach GitHub Pages, which may keep ordinary server logs under its own privacy statement. The details are at https://ravicha2.github.io/privacy/. ## Get in touch - Email: - GitHub: - LinkedIn: - Curriculum vitae (PDF): - Contact page: --- ## Fetching the rest of this site - This page as HTML: - Concise index: - Full dossier: - When to use this material: - API description (OpenAPI 3.1): - API reference: - Sitemap: