Field notes from SSG services and building Agentic AI applications and native mobile apps.
AI Agents, LMS and TMS case studies from the Tertiary Infotech Academy.
Mixture of Experts: How MoE Architecture Scales LLMs
Mixture of experts (MoE) architectures let large language models grow to trillions of parameters without paying the full compute bill on every token. Here is how the routing works, why enterprise AI leads should care, and what it changes for your inference budget. Book a consult.
TPQA New Requirements 2026: The Full Checklist
SSG's TPQA Self-Assessment Checklist v1.1 (Dec 2025) tightened marketing controls and closed-loop feedback. Here is every criterion, the evidence that passes, and how to prepare.
Hermes Agent Kanban: Our Daily AI Video Team of Four Agents
Inside our Hermes Agent Kanban setup: one scheduled daily card fans out to research, script, video-generation and publishing agents that ship a finished YouTube video end to end. Exact board design and CLI included.
Claude in Chrome Extension: Anthropic's Browser Agent for Teams
Anthropic's Claude in Chrome extension turns the chat assistant into a browser agent that clicks, navigates and tests your live web apps. Here is how enterprise AI leads in Singapore should pilot it — book a consult.
How to Claim Your UTAP AI Tool Subscription (2026 Guide)
NTUC's UTAP now reimburses 50% of eligible AI tool subscriptions, capped at S$250 a year (S$500 if you are 40 and above). Here is the eight-step claim flow and the deadlines that catch people out.
Vibe Coding SG Tutors: Web App + iOS App in Under 5 Hours
We built SG Tutors — a full-stack tutor marketplace and a native iOS app — from an empty folder to a live site and an App Store submission in under five hours with Claude Fable. Here's what shipped, the workflow, and how to learn it.
Loop Engineering: Beyond Prompting to Autonomous AI Workflows
Prompt engineering optimised the one instruction you type. Loop engineering designs the autonomous system that decides what to prompt, verifies the result and self-corrects — the plan-execute-verify loop, and how to master it with Claude Code.
GLM 5.2: Open-Source AI Rivalling Claude Opus 4.8
Z.ai's open-weight GLM 5.2 lands within a point of Claude Opus 4.8 on the hardest benchmarks at five to seven times less cost. The benchmarks, the price, and when to pick which.
AI Digital Human for Business: 24/7 Avatars on MiniMax M3
What an AI digital human is, how it works, and where it pays off: a branded 24/7 avatar built on MiniMax M3, voiced with cloned multilingual speech and grounded in your own content.
Vibe Coding Mobile Apps: 6 Months to 3 Days with Claude Code
Traditional native app builds take six months or more. With Claude Code vibe coding we take a real iOS or Android app from blank repo to App Store review in under three days — here's the workflow and our shipped portfolio.
Potluckhub: A Home-Chef Marketplace on Web, iOS & Android
How we built Potluckhub, a Singapore home-chef marketplace, across a full-stack web app and native iOS and Android clients on one shared REST API — a bespoke marketplace build case study.
Claude Fable 5: What Anthropic's New AI Model Means in 2026
Anthropic's Claude Fable 5 launched on 9 June 2026 — a frontier model for multi-day autonomous coding and research. What it does, what it costs versus Opus 4.8, and how Singapore teams should decide whether to use it.