Join the Data Recovery Summit on Wednesday, January 21 to show you:

All attendees will be entered for a chance to win a Theragun Prime Plus!

Sponsored

Welcome toDataPro162 ✨
Wishing you a warm and thoughtful start to the New Year.

As we step into the year ahead, one thing is clear: the data stack is moving faster, getting smarter, and demanding sharper decisions from teams building with it. This issue is about solving that tension. How do we ship intelligence that is real-time, reliable, and production-ready, without adding fragility, cost blowouts, or trust gaps?

Across this edition, we look at how vendors and practitioners are addressing practical bottlenecks: latency in AI systems, brittle agent workflows, rising infrastructure complexity, and models that perform well in theory but falter in the real world. The common thread is quiet progress. Less hype, moresystemsthinking. Fewer dashboards, more decisions thatactually holdup in production.

You’llsee how frontier models are becoming faster and cheaper to deploy, how agents are gaining memory and governance, why evaluation matters more than accuracy scores, and how teams are modernizing code and infrastructure without grinding engineering velocity to a halt.

Here are thetop highlightsshaping this issue:

Gemini 3 Flash for Enterprises– Faster, lower-latency frontier intelligence designed for real-time, high-frequency workloads.

Gemini Live API on Vertex AI– Multimodal, human-like AI agents that handle voice, vision, and context in real time.

Amazon Nova Forge– A new path to building domain-specific frontier models without catastrophic forgetting.

BigQueryMCP Server– Secure, low-friction access to analytics data for data-aware AI agents.

Microsoft Fabric Dataflows Gen2– A meaningful shift in performance and cost that brings low-code ETL back into contention.

Why ML Fails in Production– A sobering look at time, data assumptions, and why strong offline metricsaren’tenough.

From Research to Reality– Lightweight, open models for video, speech, translation, and on-device AI thatactually ship.

Thank you for starting the year with us. Ifthere’sone takeaway from this edition,it’sthis: progress in data is no longer about adding morelayers, butabout removing the friction that stopsgood ideasfrom surviving contact with reality.

Here’stoa thoughtful, steady, and impact-driven year ahead!

Cheers,

Merlyn Shelley

Growth Lead, Packt

Subscribe|Submit a tip|Advertise with Us

🔆Gemini 3 Flash for EnterprisesGemini 3 Flashexpands Google’s Gemini 3 family with a fast, cost-efficient frontier model built for high-frequency, real-time workloads. It combines Pro-level reasoning with Flash-level latency, enabling responsive agentic apps, multimodal analysis, and large-scale automation.Key takeaways:low latency, strong multimodal intelligence, and significantly better price–performance for production systems.

🔆Gemini Live API available on Vertex AI:Gemini Live API, now generally available on Vertex AI, enables real-time multimodal AI agents powered by the Gemini 2.5 Flash Native Audio model. It blends voice, vision, and text with ultra-low latency, handling interruptions, tone, and visual context naturally.Key takeaways:human-like conversations, enterprise-grade reliability, and production-ready voice and video agents at scale.

🔆Amazon Nova Forge: Build your own frontier models using Nova.Amazon Nova Forgelets organizations build custom frontier models using early Nova checkpoints, blending proprietary data with Amazon-curated datasets to avoid catastrophic forgetting. It enables deep domain customization across pre-, mid-, and post-training, with RL support and safety controls.Key takeaways:deeper model steering, lower cost than training from scratch, and seamless deployment via SageMaker and Amazon Bedrock.

🔆New Enhanced Tool Governance in Vertex AI Agent Builder:Vertex AI Agent Buildernow adds stronger governance, faster development, and scalable production capabilities with Cloud API Registry integration. Teams can centrally manage approved tools, build agents faster using enhanced ADK and Gemini 3 models, and scale reliably with GA memory and sessions.Key takeaways:enterprise-grade control, faster agent development, and production-ready scaling with lower costs.

🔆Using the fully managed remote BigQuery MCP server to build data AI agents:BigQueryMCP Servergives AI agents secure, direct access to enterprise analytics data using a standard protocol. With fully managed remote MCP servers, teams can connect agents toBigQuerywithout custom integrations.Key takeaways:faster agent development, native support across ADK and popular tools, and secure, low-overhead access to real-time analytics data.

🔆From ‘Dataslows’ to Dataflows: The Gen2 Performance Revolution in Microsoft Fabric:This blog breaks down the latestDataflows Gen2 performance and pricing improvements in Microsoft Fabric.It explains how the new pricing model, Modern Evaluator, and Partitioned Compute significantly reduce execution time and Capacity Unit (CU) costs, showing through real benchmarks how Dataflows Gen2 are becominga viable, cost-efficient alternative to code-first ETL approaches.

🔆Why Your ML Model Works in Training But Fails in Production:Unpack why machine learning models that shine in training often fail in production. The article exposes real-world failure modes like time leakage, misleading default values, and silent population shifts that dashboards miss. It argues that most ML breakdowns stem from data timing and system assumptions, not model choice, and shows how production reality quietly invalidates offline success.

🔆How to Maximize Claude Code Effectiveness:Explore how to get the most out of Claude Code, a terminal-based agentic coding tool. The article shares hands-on techniques like plan mode, memory usage, slash commands, and automation-first workflows, showing when CLI-based agents outperform IDEs. It also covers practical limitations, helping engineers decide when Claude Code is the right fit for fast, low-review development.

🔆Why 90% Accuracy in Text-to-SQL is 100% Useless:Examine why Text-to-SQL systems must meet a binary accuracy bar in enterprise analytics. The article explores the limits of RAG pipelines, highlightsBigQuery’snative GenAI integration, and argues that rigorous evaluation, not model novelty, is the missing piece. It explains why modern benchmarks like Spider 2.0 are essential to earning user trust and avoiding costly analytical errors.

🔆Build durable AI agents with LangGraph and Amazon DynamoDB:Explorehow production-ready AI agents canmaintaindurable memory usingLangGraphand Amazon DynamoDB. The article introducesDynamoDBSaver, a persistence layer that stores agent state across failures, long-running workflows, and distributed systems, enabling scalable, reliable agents with support for recovery and human-in-the-loop processes.

🔆Provision Oracle Database@AWS stack using AWS CloudFormation:Understand howOracleDatabase@AWSbrings Oracle Exadata infrastructure into AWS data centers with native integration to AWS services. The article outlines themulticloudarchitecture, key components, and regional availability, then explains how to provision and manage OracleDatabase@AWSresources using AWS CloudFormation to standardize, automate, and scale deployments.

🔆How Salesforce migrated from Cluster Autoscaler to Karpenter across their fleet of 1,000 EKS clusters:Discover how Salesforce migrated over 1,000 Amazon EKS clusters from ClusterAutoscalertoKarpenter. The article breaks down the migration strategy, automation tooling, and operational lessons learned, showing howKarpenterenabled faster scaling, simpler infrastructure management, and meaningful cost and performance improvements at enterprise scale.

🔆AWS Transform custom: Crush tech debt with AI-powered code modernization.Get to know howAWS Transform customrethinks large-scale code modernization by automating repetitive upgrades across enterprise codebases. The article explains how organizations can define reusable transformation patterns for runtimes, frameworks, SDKs, and infrastructure, apply them consistently across thousands of repositories, and dramatically reduce the time spent paying down technical debt.

🔆Lightricks/LTX-2:MeetLTX-2, an open-source audio-video foundation model that generates synchronized video and sound in a single diffusion-based system. Built byLightricks, it combines modern video generation blocks with open weights, local execution, and multiple checkpoints for full, distilled, and upscaled outputs. LTX-2 targets practical, high-quality multimodal creation without relying on closed APIs.

🔆fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA:DiscoverQwen-Image-Edit-2511 Multiple AnglesLoRA, a camera-control add-on that gives precise viewpoint control for image generation. Trained on 3,000+ Gaussian Splattingrenders, it enables 96 distinct camera poses across angles and distances. TheLoRAimproves 3D consistency, supports true low-angle shots, and allows creators to animate orrenderimages with reliable, repeatable camera positioning.

🔆tencent/HY-MT1.5-1.8B:Learn aboutHunyuanTranslation Model v1.5, a new open-source multilingual translation system with 1.8B and 7B variants. The models support translation across 33 languages and dialects, handle mixed-language and formatted text, and allow terminology control. The smaller 1.8B model delivers near-7B quality with low latency, enabling real-time and edge deployments.

🔆nvidia/nemotron-speech-streaming-en-0.6b:NemotronSpeech ASR, NVIDIA’s new streaming-first speech-to-text model built for low-latency, real-time applications. The 0.6B model deliversaccurateEnglish transcription with native punctuation and capitalization, supports flexible chunk sizes, and scales efficiently across parallel streams. Its cache-aware architecture enables faster, cheaper voice agents, live captioning, and conversational AI without retraining.

🔆LiquidAI/LFM2.5-1.2B-Instruct:IntroducingLFM2.5-1.2B-Instruct, a lightweight hybrid language model built for fast, on-device AI. Despite its small size, it rivals much larger models, delivering strong instruction-following with low memory use and high edge performance. Designed for agentic tasks, data extraction, and RAG, it runs efficiently across CPUs, mobile NPUs, and local inference frameworks.

See you next time!