Stephen Mc Gowan
AI Architect. Graph Evangelist. 18 years of delivering business value into customers hands, now shipping software with AI agents, with the governance to prove it.
Sydney, Australia
Actions
I'm an AI Architect with 18 years in software engineering. I currently lead the rollout of AI tooling and an AI-enabled SDLC at a global insurance company, and I run TrolleyRelay, a production SaaS built by one human directing AI agents through a fully gated delivery process: hundreds of PRs, more test code than product code, and every rule in the process traceable to a real incident that produced it.
My current talk and article series, "You can't install an AI-SDLC", is about what it actually takes to run AI-driven delivery accountably: quality floors, review and judgment gates, agent identity and attribution, and infrastructure that keeps agents constrained, observable, and reviewable. Nothing in it is claimed practice; it is all demonstrated, dated, and public.
Before the AI wave I spent most of my career in LegalTech and HealthTech, and co-founded Realta Logic, an Australian startup digitising regulation and making it operational, built on two decades of CSIRO research. My earlier talks sit where those threads meet: domain-specific languages, graph databases, and turning complex regulation into something visual and computable.
Area of Expertise
Topics
Regulation can be fun! Building insightful knowledge graphs using domain-specific languages
Domain-specific languages have existed since the early days of computing. In particular, they can improve communication with domain experts, providing an essential tool for tackling one of the hardest problems in software development, clear communication. Stephen will explore the power of using domain-specific languages to create graphs and how a domain-specific language for encoding regulation can be used to create beautiful visualisations and rapidly deliver insights into complex topics.
Neo4j Graph DB. First presented at the May 2023 Graph DB Meetup Sydney Event, as part of Neo4j's Graph Summit
Using Generative AI and Knowledge Graphs to deliver trustworthy AI
Generative AI shows great promise, but hallucinations are a massive risk where factual responses are mission-critical. In this session we will show how to use Knowledge Graphs to provide a solid fact basis and Generative AI to query our data and deliver natural language responses, all while ensuring we can trust the output and how it was generated.
Neo4j + Open AI or Azure Open AI. Can also be adapted to use other common LLMs, such as Google Cloud Vertex AI. Minimum 30 mins to present, longer sessions also possible with additional theory around methodologies for combining the capabilities of Knowledge Graphs and Generative AI.
NODES 2024 Sessionize Event
NODES 2023 Sessionize Event
Graph DB Meetup Sydney / Neo4j Graph Summit
Regulation can be fun! Building insightful knowledge graphs using domain-specific languages
This event was run as part of the Neo4j Graph Summit. I organise these regular bi-monthly GraphDB Meetups, but I also spoke at this meetup in May.
Appian Europe
Delivering an Automated Real Time Compliance Solution using Appian
The most attended breakout session at Appian Europe - https://www.youtube.com/watch?v=wm9BNOcwDhg
Appian APJ
Realta Logic: Delivering Real-Time Compliance as an Advantage in Financial Services
https://appian.com/learn/events/event-videos/appian-apj-2022/delivering-real-time-compliance-as-an-advantage-in-financial-services.html
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top