Jia Huang

Jia Huang

Lead Research Engineer at A*STAR Singapore · Author

I write about agent architecture from inside the engineering trenches — what the harness actually does, why composing patterns matters more than picking models, and how the next decade of AI systems will be built.

The thesis I keep coming back to: agent architecture is the design of bounded resource allocation under uncertainty. The model spends; the harness budgets.

Designing AI Agents — Manning Publications, MEAP

Designing AI Agents — the design-pattern catalogue for production AI agents.

Two buckets, one carrier — every agent design decision is a balance.

Recent Writing

Books

Training Demos

I keep a small library of runnable Agent training cases. The current finance track includes LSEG workshop demos for regulatory document analysis, multi-agent ticket review, and Copilot-driven spec development.

Browse training demos →

About

I am a Lead Research Engineer at A*STAR Singapore, formerly senior consultant at Accenture Singapore, with twenty years across NLP, LLMs, and AI applications in MedTech and FinTech. I am also a certified counsellor with seven years volunteering on a Singapore counselling helpline, a background that quietly shapes how I write about agents: the most important thing the harness does is the same thing a phone counsellor does — read meaning out of a narrow channel, decide when to escalate, build trust call by call.

Read more →

Newsletter

I write a free newsletter, Agent Design Patterns, on Substack. One essay every 1–2 weeks. Structural observation, not hype.

Or read on Substack directly · LinkedIn.