Production AI

Production AI

Cloud Security Challenges in the AI Era: Analyzing the Impact of Containers and Inference on System Safety

Overview Marina Moore — security researcher and co-chair of the CNCF Security and Compliance TAG — shares her concerns about security vulnerabilities inherent in container-based architectures. She outlines: * Origins of the issues * Potential solutions * Alternatives such as micro‑VMs instead of traditional containers * Special risks around AI inference workloads --- 🔑 Key Takeaways

Production AI

Enhancing Software Delivery Efficiency with AI and Lean Methods: A QCon Case Study

Transcript – AI, Lean Thinking & Building the Right Product Opening Story: Zappos & Lean Experimentation Back in 1999, 28‑year‑old Nick Swinmurn had an idea: people would buy shoes online. It sounds obvious today but at the time it was novel — and odd — because he had no inventory, factories,

Production AI

Dev Proxy v1.3.0: HAR File Generation, LLM Usage Tracking, Enhanced API Testing

Dev Proxy v1.3.0 — Key Updates from Microsoft 365 Development Team The Microsoft 365 development team has released Dev Proxy v1.3.0, delivering major upgrades for debugging, testing, and API monitoring. This version features: * Two new plugins: * HAR File Generation — standardized network tracing * OpenAI Usage Tracking — monitor AI

Production AI

Building and Applying a Large Model System Integrated with Risk Control Knowledge

# Practical Implementation of Intelligent Risk Control Driven by Large Models ## Overview In recent years, China’s **domestic consumer credit market** has grown rapidly, approaching saturation. Financial institutions have shifted from acquiring **new customers** to **deep-mining existing customer bases**. To manage risk and improve acquisition efficiency for the **middle segment** customers,

Production AI

How Shopify Handles 30TB of Data per Minute with a Monolithic Architecture

Shopify’s Billion-User Monolith: How Simplicity Scales If you’ve ever worked on a web application that slows down with just a few thousand users, imagine handling billions—and doing it with a single, elegantly designed monolith, not hundreds of microservices or annual rewrites. This is the real story of

AI news

The AI World Is on Edge: How Many Years Can a GPU Last?

How Long Can a Single GPU Last — 2, 5, or Even 6 Years? Over the past three years, the AI industry has been in overdrive — models grow larger, data centers multiply, and Nvidia’s stock keeps soaring. Now, as global tech giants prepare to invest $1 trillion in AI data

Production AI

Race Conditions in the DynamoDB DNS System: Analyzing the AWS US-EAST-1 Outage

AWS DynamoDB Outage — Analysis and Lessons Learned On October 19–20, AWS suffered a major outage in its most popular region, Northern Virginia (US-EAST-1). The disruption arose from an Amazon DynamoDB failure that cascaded to multiple AWS services. The incident report published by AWS (full analysis) has prompted renewed debates

Production AI

Reducing False Positives in RAG Semantic Caching: A Banking Case Study

## Key Takeaways - **Semantic caching** — a **Retrieval-Augmented Generation (RAG)** technique — stores queries and responses as **vector embeddings** for reuse. - Improves **efficiency** by avoiding repeated large language model (LLM) calls. - Case study: failure ➡ production success through **7 bi-encoder models**, **4 setups**, **1,000 banking queries**. - **Three model types*

AI news

The Rise of AI Agents: Is AI+Software Development at a New Turning Point?

# 🚀 The LLM Native Development Era Large Language Models (LLMs) are **profoundly transforming R&D**, evolving from mere auxiliary assistants to **core productivity drivers**. From assisted programming to autonomous *Coding Agents*, we’re witnessing AI’s shift toward being native to the software development process. Has the **native AI-based development

Production AI

KubeCon NA 2025 - Salesforce’s AIOps and Intelligent Agent Approach to Self-Healing Practices

AIOps & Agentic AI for Self-Healing Kubernetes Platforms AIOps and Agentic AI technologies enable intelligent assessment of Kubernetes cluster health, automatic issue diagnosis, and orchestrated resolutions with minimal human intervention. At KubeCon + CloudNativeCon North America 2025, Vikram Venkataraman (AWS) and Srikanth Rajan (Salesforce) presented Salesforce’s approach to building a

Production AI

AI Transformation in Game Development: NetEase’s Multi-Agent System and Knowledge Engineering Practices

# Practical Implementation of Large Language Models in Game Development In recent years, **AI coding tools** have rapidly emerged, yet their adoption in *large-scale game engineering* remains limited. The main constraints are **LLM context length** and the **complex, highly flexible nature of game logic**. This article is based on my talk

Production AI

BigQuery: Efficient Vector Search Integration in Columnar Storage

# Integrating Vector Search into BigQuery’s Distributed Architecture In today’s AI-driven world, **vector search** has become a standard requirement for content retrieval, recommendation systems, and semantic matching. When Google announced **general availability of vector search in BigQuery** in early 2024, it joined the growing ranks of mature databases offering