Find all our past blog articles here. Filter by series, author, publication window, or keywords.
Latest articles
No articles match those filters.
Evals are all the rage in the AI space recently, especially with news of GPT-6 Astra saturating long-standing difficult benchmarks like ARC-AGI-3 and FrontierMath (Tier 4). In this article, we too are sharing our latest work on benchmarking — but with a unique Public Sector twist!
On observability as the layer agentic AI deployments may miss, and it's importance in deciding whether you can trust anything else you build
By Ng Shangru
Reflections on building reusable capabilities, empowering teams and staying relevant in a fast-moving field
By Tan Tai Kia
How we used agentic AI to proactively test and strengthen chatbot safeguards for chat.gov.sg
A closer look at the new paradigm of frontier models, and how we explored Jev and adapted its open-source interpretation - Kev, for Singapore-context moderation.
By Leanne Tan, Jia Yi Goh
We built VEILED-SH to evaluate indirect self-harm/suicide language in the Singapore context, shaped by local language, privacy safeguards and practitioner insight.
Balancing real-time performance, model cost and structured multi-agent workflows
By Ryan Lin
How we build custom policy guardrails and balance safety with helpfulness for chat.gov.sg
By Jia Yi Goh
No Forward-Deployed Team really starts from zero, every achievement begins with a foundation laid by someone before us. Looking back on my journey, I realise what I inherited matters just as much as what I've accomplished.
By Lois Ji
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.
Operationalising MLOps with production feedback to continuously evaluate, retrain, and improve our guardrails.
By Jia Yi Goh, Hugh Le
An experiment reveals how different layers shape what a model understands, retrieves and ultimately generates.
By Ryan Lin
“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.”
By Sumiko Teng
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.
GovTech's MOM team built it to unify AI tools for analysing data, drafting slides and checking compliance
On shared memory systems for organisations and the complexities around them
By Ng Shangru
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.
By Shaun Ang
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
By Rohan Jaggi
How we built Kaleidoscope: A structured workflow for realistic, scalable, and human-aligned contextual AI evaluations.
By Leanne Tan
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.
By Ng Shangru
Engineering Multi-Agent Architectures for Autonomous Penetration Testing.
By Watson Chua
On building your own multi-agent orchestrator, and why owning the infrastructure around AI matters.
By Ng Shangru
We tested 2026 SOTA models and found a "usability gap".
By Sumiko Teng
Ever spoken to an AI and felt like it was responding with insincere praise?
By Leanne Tan
The "hype" of robots ignore the unstructured environment problem.
By Jia Yi Goh