When Agent Skills Evolve: The Need for a Layer of Control
What we learnt from building Rhizomatic, a human-in-the-loop proof of concept for reviewing, versioning and rolling back changes to reusable agent skills.
How we build AI for public good
A technical blog for AI science and engineering
Guardrails in the Wild: Closing the Retraining Loop for LionGuard 2
Operationalising MLOps with production feedback to continuously evaluate, retrain, and improve our guardrails.
What is a Mixture-of-Experts model, really?
An experiment reveals how different layers shape what a model understands, retrieves and ultimately generates.
One Year in Multimodal AI at GovTech
“I came here expecting to build models for people who already knew what they wanted. I discovered that the harder work is figuring out what should be built, who it is for, and whether it solves a real problem.”
ORCA Part 2: Under the Hood
How ORCA works under the hood: routing each request to the right agent, running generated code in an isolated sandbox, and turning repeat chat tasks into reusable workflows.
ORCA: one platform, many agents, working together
GovTech's MOM team built it to unify AI tools for analysing data, drafting slides and checking compliance
Agent Wars, Episode 2: The Brain Wars
On shared memory systems for organisations and the complexities around them
Stress-Testing Government Communications with AI Personas Grounded in Real Voices
Government communications can misfire in ways their authors never intended. We built an app that lets officers stress-test drafts against AI personas grounded in real Singapore voices, so they can catch what they missed in minutes rather than weeks.
My 6 Months Interning Responsibly at AI Practice
Tell us about yourself- what did you expect from this internship?
I’m Rohan, a penultimate year Business Analytics student at the National University of Singapore (NUS) who spent the first half of 2026 as an applied AI Data Scientist Intern at GovTech’s Responsible AI team.
Going in, I
Building an automated Evals workflow that works (and open-sourcing it)
How we built Kaleidoscope: A structured workflow for realistic, scalable, and human-aligned contextual AI evaluations.
The Road Under the Harness
Previously I wrote about building a harness for yourself. This one is about the environment you're building in, and why at enterprise scale, if the platform underneath doesn't exist, individual wins have nowhere to accumulate.
Scaling the Pentesting Team with AI
Engineering Multi-Agent Architectures for Autonomous Penetration Testing.