In this issue, November 17, 2026 View it in your browser.

Agent Distraction, LLM Reliability, LinkedIn GitOps, OpenTelemetry, Compute Engine, Cloudflare Basin, Angular, Tokio Topcoat, Siri AI, iOS Crash, Post-Quantum CA, Agentic AI, Tech Debt, Influence

QCon London 2027 (Apr 13-15): What does AI change about the decisions that define your architecture?

Hien Luu hosts the Architecture in the Age of AI track on April 15, covering patterns for integrating AI into production systems and the trade-offs that come with it. April 13-15 at the QEII Centre, Westminster, with a certification day on April 16. See the tracks.

 

Sponsored by Equal Experts

When Code Is Cheap: Leading Software Teams in the AI Era - Sponsored by Equal Experts

When Code Is Cheap: Leading Software Teams in the AI Era

AI is writing more of the code, but deciding what to build, keeping systems healthy and growing engineers still sit with engineering leaders. Join Equal Experts and Francisco Trindade, VP of Engineering at Braze and author of Leading Effective Software Teams, for a fireside chat and dinner on night one of QCon AI New York, Tuesday, December 15. Every guest will leave with a signed copy of the book. Invite-only dinner. Request your seat.

https://res.infoq.com/podcasts/distributed-llm-inference-kubernetes/en/smallimage/infoq-podcast-500-1793797932006.jpg

Distributed LLM Inference on Kubernetes with llm-d, Wasm, & TornadoVM

In this episode, Edoardo Vacchi discusses the evolving landscape of WebAssembly on the backend, running Java workloads on GPUs using TornadoVM, and optimizing distributed AI inference using llm-d and vLLM on Kubernetes. Edoardo explains how llm-d manages cache locality (KV and prefix caches), request routing, and batch inference across Kubernetes clusters to maximize expensive GPU utilization. (Podcast)

https://res.infoq.com/podcasts/accountability-age-ai-coding-summary/en/smallimage/engineering-culture-500-1794303925695.jpg

Doing The Right Thing: Accountability In The Age Of AI Coding Summary

In this podcast, Shane Hastie, Lead Editor for Culture & Methods, spoke to Hugo Venturini about who is accountable when AI writes the code, how AI is reshaping code review and traditional engineering roles, and how leaders build a culture of transparency and psychological safety. (Podcast)

TOP AI, ML & Data Engineering NEWS HEADLINES

  1. Open Source DocumentDB 1.0 Reaches General Availability

  2. Google Open-Sources TPU Sync for KV Cache and Weight Transfer on TPUs

  3. Google Finds That Technical Debt Can Derail Coding Agents through "Agent Distraction"

  4. Google Releases Gemini 4 Argon for Robotics Control, Simulation, and Policy Improvement

  5. AWS Launches TorchNeuron to Run PyTorch Models on AWS Trainium without Modifications

LLM Reliability Layers Under Test: Accuracy, Yield, and the Limits of Verification

Verification layers sort outputs by trust rather than fixing errors. In a benchmark of six reliability layers, voting and self-correction failed to recover accuracy - they only withheld doubtful records. Production systems gain more reliability by replacing generation with deterministic lookups, tracking yield over raw accuracy, and resolving extraction bottlenecks before stacking checks. (Article)

Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector

Hannes Hapke shares how Dataiku's open-source Kiji Inspector applies Sparse Autoencoders (SAEs) directly to decision tokens to expose why agents pick specific tools. Moving past superficial chain-of-thought narratives, he discusses causal ablation, layer activation extraction via patched vLLM engines, and production monitoring workflows for software architects and senior engineering leaders. (Presentation with transcript included)

Batch Intelligence at Scale: Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience

Aditya Mulik explains how Walmart Global Tech deployed multi-agent LLM workflows across 4,700 stores for nightly batch inventory forecasting. He discusses tackling production hurdles - schema violations, cross-department data mismatches, and network drops - via MCP grounding and loop agents, while slashing cloud inference costs from $100k+ to $10k per month shifting from PTUs to pay-as-you-go. (Presentation with transcript included)

Sponsored by Hi3D

Hi3D Open-Sources V1.0 AI 3D Model - Sponsored by Hi3D

Hi3D Open-Sources V1.0 AI 3D Model

Hi3D V1.0 is now open-source with code & weights available. Engineered for 1536³ resolution & enterprise workflows. Integrate via MCP or try the new AI-powered Hi3D Agent to automate end-to-end 3D generation. Access demo now!

TOP DevOps NEWS HEADLINES

  1. Netflix Turns Operational Data Into a Knowledge Graph for AI-Driven Observability

  2. LinkedIn Replaces Argo CD with a Custom GitOps Engine for Kubernetes Deployments

  3. GitHub Makes Agentic Workflows Generally Available with Isolation and Budget Controls

  4. Pinterest and Intel Take Open-Source Profiling to Internet Scale

Uncorking Queueing Bottlenecks with OpenTelemetry

Oli Lane and Julian Wreford share how Gearset replaced guesswork in distributed asynchronous queues with OpenTelemetry tracing. They explain why traditional metrics fall short, how to implement user-centric SLOs based on latency distributions, and share practical debugging tips to help senior developers, software architects, and engineering leaders improve system reliability and team culture. (Presentation with transcript included)

Sponsored by Azul

The Agentic AI Threat - Sponsored by Azul

The Agentic AI Threat

AI agents are opening new attack paths into enterprise systems. Read the white paper to understand the threat and how to prepare.

TOP Cloud NEWS HEADLINES

  1. Azure Logic Apps Standard Gets a Local CLI in Preview

  2. Cloudflare Makes Basin Serverless Analytics Generally Available

  3. Google Cloud Spend Caps Reach General Availability with API and Monthly Resets

Google Cloud Moves the Compute Engine API to Immutable Date-Based Versions

Google Cloud has made date-based versioning of the Compute Engine API generally available, replacing the single mutable /v1 surface with immutable quarterly snapshots such as 2026-09-01, selected per request with a header or query parameter. New versions can change defaults, error formats, and IAM checks without touching /v1 callers, a model Azure Resource Manager and Stripe have used for years. (News)

Tokio Releases Topcoat: a Batteries-Included Full-Stack Rust Framework

Topcoat is an open-source, server-rendered full-stack web framework for Rust from the Tokio team, now public at version 0.9. It uses Rust expressions translated to JavaScript for reactivity instead of WebAssembly. It targets typical database-driven apps. Releases are unstable, and authentication and background jobs remain on the roadmap. (News)

Java News Roundup: TornadoVM, A2A Java, Open Liberty, Open J Proxy, Gradle, EclipseStore

This week's Java roundup for November 2nd, 2026, features news highlighting: point releases of TornadoVM, TornadoInsight, A2A for Java, Gradle and EclipseStore; the November 2026 edition of Open Liberty; the third release candidate of Open J Proxy; the second release candidates of Micrometer Metrics and Micrometer Tracing; and the third beta release of Quarkus 4.0. (News)

Sponsored by Microsoft

Microsoft Ignite 2026 - Sponsored by Microsoft

Microsoft Ignite 2026 starts today! Tune in live for the free broadcast and see what’s next in software

Join our very own Wesley Reisz live at the Microsoft Ignite anchor desk for a breakdown of news you can use, and technical analysis. It starts with a keynote at 10am PST from Satya Nadella and Judson Althoff, followed by three full days of customer interviews, live demos, and access to the top engineering minds across Microsoft.

TOP Web Development NEWS HEADLINES

  1. Node.js Brings Debounce, Throttle, and PKCS#12 Parsing Into Core Modules

  2. Dropbox Shares How Its In-House Cookie Auditor Tests Consent Behaviour Across 200+ Web Surfaces

  3. Author Q+A: finprim is a Case for One Financial Validation Library in TypeScript

  4. Effect 4.0 Ships: Dependency-Free Rewrite with 5x Smaller Bundles and Long-Term Support

Angular's TypeScript 7-Powered Compiler Enters Beta with Rust-Based Preprocessor

The Angular team has introduced ngp, a compiler preprocessor that rewrites the analysis stage in Rust using Oxc. It replaces ngc's dependence on the Transformer API, which TypeScript 7.0 removed. An early benchmark showed 2x to 3x faster cold builds. Adoption is expected in an Angular 22 minor release; production builds should stay on ngc until then. (News)

TOP Mobile and IoT NEWS HEADLINES

  1. Siri AI Developer Preview Lets iOS, iPadOS, and macOS Apps Integrate with Siri

The iOS Crash We Could Not Reproduce

This article describes the investigation to find the root cause of a production crash in a large-scale iOS consumer app that had no clean stack trace. The crash occurred intermittently and resisted every local reproduction attempt. The final code change was small, but identifying the root cause required turning a vague SIGBUS report into a controlled set of experiments. (Article)

TOP Architecture & Design NEWS HEADLINES

  1. Google Open Sources Ambient Quality Agent (AQuA) to Diagnose Production AI Agent Failures

  2. JioHotstar Benchmarks Knowledge Bases for AI Coding Agents

  3. Cloudflare Develops Public Certificate Authority for Post-Quantum Web Security

  4. Pinterest Replaces Journey Clustering with 4B Qwen3 LLM, Reports Improved Engagement

Agentic AI Architecture: Current Challenges and Future Opportunities

Agentic AI architecture extends microservices and cloud-native architectures with AI agents that work with context, memory, and protocols such as MCP and A2A. The article covers bounded-context integration, task-dependent coordination strategies, new security risks, and observability needs. It expects gradual adoption alongside existing architectures, with platforms absorbing common components. (Article)

TOP Culture & Methods NEWS HEADLINES

  1. Technical Debt is Social; it is the Price of Learning by Doing

The Influence Toolkit

Henry Wilson shares actionable tools from the BBC Sounds re-architecture to help senior engineering leaders drive technical strategy. He discusses building buy-in, navigating active resistors, using RFCs and ADRs, and balancing tradeoffs - showing that effective software architecture is fundamentally about communication, relationship-building, and organizational influence. (Presentation with transcript included)

SPONSORED CONTENT

Latest Sponsored Resources

document AI Agents in Production: What It Takes to Move Beyond the Demo

document Next-Gen Architecture Playbook: Insights and Patterns for the AI Era

document Understanding Postgres Performance Limits for Analytics on Live Data