Mike Ng
Engineer (Cloud & Systems) exploring how AI fits into production systems
Hong Kong
Actions
Mike is an engineer working on production systems where governance, reliability, and auditability are non-negotiable. His experience spans fintech, cloud platforms, and decentralized systems, with a focus on designing boundaries that keep complex systems operable under real-world constraints.
He has been trained through competition-based systems engineering and has spent years building and operating systems where decisions are difficult to reverse. He now applies the same engineering discipline to AI-assisted workflows, focusing on how agents can be governed once they interact with code, infrastructure, and delivery pipelines. His current work explores how individual engineering disciplines can be transformed into organizational governance.
Area of Expertise
Governing AI Agents in Production: From Experiment to Engineering System
Most AI governance discussions assume AI will "do the right thing" with proper
guidelines. This talk takes a different approach: assume drift, error, and
misalignment by default, then design mechanical structures that make bad
behavior expensive.
The core idea: systems are defined by what they refuse to do, not what they
can do. For AI in production, governance means explicit rejection zones,
constitutional constraints that cannot be bypassed, and separation between
decision-making and execution.
Five governance patterns: constitutional constraints (forbidden states and
behaviors), rejection zones (where AI cannot operate), separation of powers
(decision ≠ execution ≠ validation), retrieval-led reasoning (grounding over
pre-training), and mechanical enforcement (architecture over policy).
Developed while preparing experimental multi-agent systems for production
deployment in FinTech, where mistakes are irreversible and governance is
survival, not choice.
Mike Ng
Engineer (Cloud & Systems) exploring how AI fits into production systems
Hong Kong
Actions
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