TechTouch Asia

By Shahid Nizami, VP APAC & GCC, Braze AI is now at the forefront of consumer engagement, increasingly used by consumers and brands alike to shape the customer experience. Across the world, especially in Asia and Singapore, AI is becoming the engine behind acquisition, retention, and engagement. That shift raises new expectations - not just to have customer preferences understood to the letter, but to have clarity, consent, and transparency in how data is used across touchpoints. However, customer confidence is not keeping pace as AI adoption accelerates. Braze’s 2026 Global Customer Engagement Review found that while 93% of surveyed marketing leaders globally believe AI helps them understand customers more accurately, only 53% of surveyed consumers feel brands are accurately predicting their wants and needs. Relevance is not the only issue. A study by IDC and Microsoft also showed that fewer than one in four Singapore consumers trust organisations that provide digital services ...

Source: NVIDIA. See an up-to-3.5x increase in large language model (LLM) inference performance on NVIDIA GPUs with llama.cpp . All configurations measured using Q4_K_M quantizations BS = 1, ISL = 1024 and OSL = 128 on NVIDIA RTX 5090 and Mac M3 Ultra desktops. Token generation throughput measured on llama.cpp b7789 , using the llama-bench tool. The next generation of local AI models have larger context windows, delivering the intelligence to run agents on PC. Combined with richer user context and powerful local tools, these advances are unlocking new possibilities on AI PCs. - Nemotron 3 Super , released last week, is a 120‑billion‑parameter open model with 12 billion active parameters, designed to run complex agentic AI systems. Nemotron 3 Super is optimal for powering agents on the DGX Spark or NVIDIA RTX PRO workstations.  On PinchBench — a new benchmark for determining how well large language models perform with OpenClaw — Nemotron 3 Super scored 85.6%, making it the ...

Dataiku has launched The 575 Lab, Dataiku’s Open Source Office. The 575 Lab turns Dataiku’s decade of enterprise AI experience into open source tools that help enterprises see what AI is doing and stay in control.  The lab will focus on delivering deployable tools that strengthen explainability, privacy, and governance across modern AI and agentic systems. Two new open-source toolkits designed to help enterprises make AI systems more transparent, governable, and fit for real-world use will be launched:  - Agent Explainability Tools to help teams trace and understand decision-making across multistep agent workflows, making agent decisions transparent for data scientists, compliance teams, and end users.  - Privacy-Preserving Proxies  to enable safer use of closed-source models by protecting sensitive data end-to-end, and that teams will be able to run locally.   Both projects will be designed to support responsible enterprise AI, with a focus on rel...

Singtel Digital InfraCo’s sovereign AI cloud, RE:AI , has partnered with Cohesity, the AI-powered data security provider, to provide an intelligent, sovereign AI data security and management service.  This service addresses a limitation that enterprises face with their backup data, enabling them to transform their archives into a searchable knowledge base. According to Singtel, many enterprises have years’ worth of important information such as old documents, emails, reports and system records stored away in backup systems.  While the backups are essential for recovery, today’s large language models and AI applications find it difficult to search or learn from the data as they are built to work only with current active data. The new offering from RE:AI and Cohesity empowers enterprises and government agencies to catalogue and organise vast amounts of historical data so it can be searched and queried in real time. This will help them to generate more accurate, data-driven respo...

Source: NVIDIA. Seven different chips are part of the NVIDIA Vera Rubin platform. AI infrastructure is evolving from discrete chips and standalone servers to fully-integrated rack-scale systems,  pod-scale deployments, AI factories and sovereign AI, according to NVIDIA. These advances are driving dramatic gains in performance, improving cost efficiency for organisations of all sizes and across industries, while helping democratise access to AI and improve energy efficiency to power the world’s most demanding workloads.  AI labs and frontier model developers including Anthropic, Meta, Mistral AI and OpenAI are looking to use the NVIDIA Vera Rubin platform to train larger, more capable models and to serve long-context, multimodal systems at lower latency and cost than with prior GPU generations. New are: NVIDIA Vera Rubin NVL72 rack Integrating 72 Rubin GPUs and 36 Vera CPUs connected by NVLink 6, along with ConnectX-9 SuperNICs and BlueField-4 DPUs, Vera Rubin NVL72...

Source: NVIDIA. Concept visual for an AI grid. At NVIDIA GTC 2026 , leading operators announced that they are leveraging their network footprint to power and monetise new AI services across the distributed edge. Telcos and distributed cloud providers are using AI grids — geographically-distributed and interconnected AI infrastructure — to facilitate a new class of AI‑native applications that are real‑time, hyperpersonalised, concurrent and token-intensive, NVIDIA has said. - Personal AI is using NVIDIA Riva to power human‑grade conversational agents on the AI grid. By running small language models closer to users, it achieves sub-500 millisecond end-to-end latency and over 50% lower cost-per-token, enabling voice experiences that feel natural while remaining economically viable at scale. Riva is a software development kit for building speech-related AI apps. - Linker Vision is transforming city operations by running real‑time vision AI on the AI grid. By processing thousands of came...