InfoQ - AI, ML & Data Engineering

Presentation: Beyond the Prototype: Scaling Framework Agnostic AI Agent Infrastructure with Ray

Deepak Mohanakumar Chandramouli, Bhumik Vinodkumar Thakkar — Tue, 20 Oct 2026 11:00:00 GMT

The speakers discuss transitioning AI agents from local FastAPI prototypes to resilient production systems on Kubernetes using Ray. They share operational insights on RayCluster topology, stateful memory handling, auto-scaling on dynamic traffic, and robust control plane designs, while highlighting critical guardrails, multi-region setups, and LLM-as-a-judge evaluation pipelines.

By Deepak Mohanakumar Chandramouli, Bhumik Vinodkumar Thakkar

Article: From Microservices to Agents: the Next Evolution of Distributed Systems

Mallika Rao — Mon, 19 Oct 2026 11:00:00 GMT

The article examines the transition from microservices to agentic AI architecture in distributed systems. Microservices allow for functional decomposition, while agentic systems focus on decision decomposition. This shift introduces new complexities in observability, reliability, and system design, highlighting the need for updated architectural patterns and practices.

By Mallika Rao

Podcast: The Future of Web Apps: Will AI Agents Generate UIs on the Fly?

Rachel Lee Nabors — Mon, 19 Oct 2026 11:00:00 GMT

Rachel Lee Nabors, former React core team member, dives into the architecture and philosophy behind local-first applications, exploring how small language models (SLMs) running directly on-device can deliver privacy-focused, low-latency, and cost-effective alternatives to cloud-hosted LLM wrappers.

By Rachel Lee Nabors

EmbeddingGemma 2 Expands beyond Text to Support Code, Images, Video, and Audio

Sergio De Simone — Mon, 19 Oct 2026 10:00:00 GMT

Based on Gemma 4 and released under the Apache 2.0 license, Google's EmbeddingGemma 2 is a compact, open-weight, multimodal embedding model designed to make semantic search and retrieval-augmented generation (RAG) more efficient while optimizing performance for on-device deployment.

By Sergio De Simone

Reverse Engineer Anything Project Brings AI Agents to Binary Analysis

Renato Losio — Sat, 17 Oct 2026 06:28:00 GMT

Reverse Engineer Anything (REA) is an open-source project with over 200K GitHub stars that connects coding agents such as Claude Code and Codex to reverse-engineering tools like Ghidra, Hopper, and IDA. The project lets developers inspect compiled binaries, trace function calls, and investigate how applications implement specific features.

By Renato Losio

Amazon Acquires DuckLabs and Integrates DuckDB in Amazon Aurora PostgreSQL

Gianmarco Nalin — Sat, 17 Oct 2026 06:00:00 GMT

Amazon has acquired DuckLabs, the company behind the analytical database DuckDB. Co-founders Hannes Mühleisen and Mark Raasveldt will continue to lead the team under AWS. The acquisition aims to enhance the development and reach of DuckDB while maintaining its open-source status. Amazon Aurora PostgreSQL gets its first DuckDB-powered feature following the acquisition.

By Gianmarco Nalin

Google EnvHarness Enables Self-Evolving Agents to Learn in Dynamics Environments

Sergio De Simone — Fri, 16 Oct 2026 19:00:00 GMT

Google researchers open sourced EnvHarness, a framework that dynamically adapts agent-training environments to an agent's weaknesses without modifying the agent, environment, or evaluation system. According to the researchers, this approach can improve both learning effectiveness and efficiency while helping agents overcome their weaknesses.

By Sergio De Simone

AI in Production: Panellists Highlight Silent Failures, Harness Engineering, and Agent Governance

Olimpiu Pop — Fri, 16 Oct 2026 14:14:00 GMT

A recent InfoQ webinar examined operational challenges in deploying agentic systems. Key points included issues like semantic and embedding drift, which can lead to significant errors. Experts discussed the need for automated code reviews, continuous evaluation of models, and enhanced privacy measures. The session emphasised a strategic approach to deployment and security management.

By Olimpiu Pop

Grafana Applies SLOs and Error Budgets to AI Agent Behaviour

Craig Risi — Fri, 16 Oct 2026 12:00:00 GMT

Grafana Labs is proposing a familiar reliability engineering approach for one of the less familiar problems in modern software: how to measure whether an AI agent is actually behaving well.

By Craig Risi

Mini book: Evolutionary Architecture in Practice

InfoQ — Fri, 16 Oct 2026 11:30:00 GMT

Discover how to keep software evolvable as systems, technology, and teams shift. This edition explores agentic fitness functions for semantic drift, treating human comprehension as a core design metric, cross-cloud guardrails for regional autonomy, and aligning technical boundaries with Conway’s Law. Move beyond static diagrams to continuous feedback systems that keep change safe and intentional.

By InfoQ

Presentation: Exploding GPUs and the AI Infrastructure Challenge

Andrew Martin — Fri, 16 Oct 2026 11:00:00 GMT

Andrew Martin discusses why AI security is fundamentally tied to Kubernetes security. He shares insights into the evolving AI threat landscape, covering non-deterministic agent behavior, GPU supply chain vulnerabilities, shared compute risks, and practical defense strategies - from prompt firewalling to agentic identity - to help secure cloud-native AI workloads in production environments.

By Andrew Martin

AWS Introduces Strands Decider 2B and Strands Box for AI Agent Development

Daniel Dominguez — Fri, 16 Oct 2026 10:47:00 GMT

AWS has introduced two open-source projects for AI agent development: Strands Decider 2B, a small model designed to make decisions within agent workflows, and Strands Box, a sandbox for controlling agent execution. Both projects address different aspects of building agents that use tools, execute code, and interact with external systems.

By Daniel Dominguez

Microsoft Commits Maia to Multi-Gigawatt Inference, and its Efficiency Metric Draws Questions

Steef-Jan Wiggers — Fri, 16 Oct 2026 06:02:00 GMT

Microsoft will scale its Maia accelerator family to multi-gigawatt deployments from 2027, making it the primary inference system for its own products. Maia 300 collapses scale-up and scale-out onto one Ethernet fabric and moves KV state between prefill and decode workers without leaving it. Practitioners have questioned the tokens-per-watt claim that leads the announcement.

By Steef-Jan Wiggers

Presentation: What 25 Trillion Tokens Reveal about How Developers Actually Adopt AI Agents

Brendan O’Leary — Thu, 15 Oct 2026 11:00:00 GMT

Brendan O'Leary discusses how real-world AI adoption depends on building trust rather than chasing model benchmarks. Drawing from 40 trillion tokens of usage data, he explains the four rungs of the AI adoption ladder and analyzes key failure points in context construction, multi-model routing, and feedback loops to help engineering leaders successfully scale agentic workflows.

By Brendan O’Leary

Meta Extends Confidential Computing to AI Glasses with Private Processing

Leela Kumili — Wed, 14 Oct 2026 13:57:00 GMT

Meta has extended Private Processing to AI glasses, using confidential VMs, trusted execution environments, remote attestation, anonymous credentials, OHTTP routing, and TEE-based storage to process AI workloads and persistent user context in the cloud.

By Leela Kumili