Harnessing the harness
On building your own multi-agent orchestrator, and why owning the infrastructure around AI matters.
AI Practice
Video Generation Landscape Analysis: The Road to Informative Video
We tested 2026 SOTA models and found a "usability gap".
Yes, you’re absolutely right… Right? A mini survey on LLM sycophancy
Ever spoken to an AI and felt like it was responding with insincere praise?
The Realities of Robot Deployment: What It Takes for Embodied AI to Succeed
The "hype" of robots ignore the unstructured environment problem.
MetaEvaluator: Systematically Evaluate Your LLM Judges
Measure how well your app is performing and more importantly where it's failing.
MLOps Transformation: Moving from Stage 0 to Stage 3 (Part II)
A maturity roadmap and a cultural shift.
Building for Agentic AI - Agent SDKs & Design Patterns
The true value of AI agents lies in loops and self-correction rather than raw reasoning power.
A deeper look into using MCP in the enterprise
A universal "USB-C" for AI?
Building MLOps Bridges: Our Journey in Uplifting Agencies
A practical guide to MLOps adoption across Government teams.
Building a Better RAG Pipeline for HR Policy Q&A: What Worked and What Didn’t
We tested the most effective approaches.
Benchmarking GPT-5 & GPT-OSS: A Responsible AI Approach
Evaluating dimensions often overlooked by traditional benchmarks.
“The Bots Are Here. Now What?” How Knowledge Management Became the Key to Powering GenAI Solutions
Available LLMs are powerful enough. What we are missing is the knowledge to fuel them.
Introducing LionGuard 2: Multilingual LLM Guardrail for Singapore
We improved its coverage and robustness.
RabakBench: Multilingual AI Safety Evaluation Made Local
Global safety guardrails are often blind to local dialects and sensitivities.
Validating Annotation Agreement between Humans and LLMs
Who Judges the Judge?
At GovTech’s AI Practice, we’ve been embracing what’s known as “LLM-as-a-judge” — essentially employing LLMs as evaluators across our AI workflows. This approach has become one powerful approach in our evaluation toolkit.
We use LLMs extensively across multiple areas: judging other LLM outputs (e.
Does your LLM know when to say “I don’t know”?
Refusal by a model to answer may sometimes be more valuable.
Fine-Tuning Language Models for Long-Context Data: Automated Stance Analysis of Citizen Discussions
Addressing technical challenges of processing high-volume public feedback for policy-making
MLOps Transformation: Moving from Stage 0 to Stage 3 (Part I)
Much a cultural shift as a technical one.
Evaluating MOE’s SLS Learning Assistant: Using Synthetic Data and LLMs to Benchmark Faithfulness and Factuality
Safer, faster testing of student-facing AI before real-world deployment.
From Infrastructure to Intelligence (Part 1): Strategic Foundations for AI Model Hosting and Agent-Based Architectures on the Cloud
What began as simple chatbot prototypes has evolved into full-fledged agent architectures.
The other side of Agentic AI
An agent's utility is capped by its environment interface rather than just its reasoning capabilities.
Securing Guardrails with Automated Red Teaming
Manual testing is no longer scalable.
(Part 2) LLM Safety Alignment for the Singapore Context using Supervised Fine-tuning and RLHF-based Methods
Safety must be "baked in".
(Part 1) LLM Safety Alignment for the Singapore Context using Supervised Fine-tuning and RLHF-based Methods
The process of "teaching" models to be safe
Eliciting Toxic Singlish from r1
A red-teaming exercise that proves even "reasoning" models can be coaxed.