InfoQ - AI, ML & Data Engineering - News

Claude Code Adds Dynamic Workflows for Parallel Agent Coordination

Robert Krzaczyński — Mon, 01 Jun 2026 16:55:00 GMT

Anthropic introduced Dynamic Workflows, a new capability for Claude Code designed to handle complex software engineering tasks by coordinating large numbers of AI agents within a single workflow. The feature allows Claude to dynamically create orchestration scripts, break work into subtasks, run them in parallel, and validate results before presenting a final answer.

By Robert Krzaczyński

BadHost Vulnerability Exposes AI Agents, Evaluators, and LLM Gateways

Sergio De Simone — Mon, 01 Jun 2026 14:00:00 GMT

BadHost is a high-severity authentication bypass vulnerability in the widely used Python web framework Starlette, with 325 million weekly downloads. The flaw allows attackers to use malformed HTTP Host headers to bypass path-based access controls and access sensitive AI agent infrastructure, among other systems.

By Sergio De Simone

DuckDB Quack: Client/Server Protocol over HTTP for Multi-User Analytics

Renato Losio — Sun, 31 May 2026 11:17:00 GMT

DuckDB has recently announced Quack, a new remote protocol over HTTP that lets multiple DuckDB instances connect to and work with the same database over a network. The protocol introduces client-server capabilities to a database that was previously mostly local and embedded.

By Renato Losio

Arm Open-Sources Metis, an AI Security Framework Outperforming Traditional SAST Tools

Sergio De Simone — Sat, 30 May 2026 19:00:00 GMT

Arm has open-sourced Metis, an agentic AI security framework designed to autonomously uncover complex software vulnerabilities. Unlike traditional pattern-based tools, Metis applies semantic reasoning to analyze cross-component dependencies and provides clear, natural language explanations for its findings.

By Sergio De Simone

How Meta Rebuilt Data Ingestion for Petabyte-Scale Reliability

Renato Losio — Sat, 30 May 2026 06:01:00 GMT

The engineering team at Meta recently outlined how the company migrated a data ingestion platform that transfers several petabytes of MySQL social graph data daily to improve reliability and operational efficiency. The team used techniques like reverse shadowing and continuous checksum monitoring to ensure zero downtime during the transition.

By Renato Losio

AI-Assisted Migration Tool Helps Teams Move from ingress-nginx to Higress in Minutes

Craig Risi — Fri, 29 May 2026 12:00:00 GMT

The Cloud Native Computing Foundation has highlighted a new AI-assisted migration approach that enabled engineers to migrate 60 ingress-nginx resources to Higress in roughly 30 minutes, demonstrating how artificial intelligence is increasingly being applied to modernize Kubernetes networking and gateway infrastructure.

By Craig Risi

GitHub Slashes Agent Workflow Token Spend up to 62% with Daily Audits and MCP Pruning

Mark Silvester — Fri, 29 May 2026 08:30:00 GMT

GitHub reports cutting token costs in agentic CI workflows by up to 62% by pruning unused MCP tools, swapping some MCP calls for gh CLI, and running daily “auditor” and “optimizer” agents. A token-usage.jsonl artefact and an Effective Tokens metric help track spend across models and spot regressions.

By Mark Silvester

Cloudflare Adds Support for Claude Managed Agents

Renato Losio — Thu, 28 May 2026 06:23:00 GMT

Cloudflare recently added support for Claude Managed Agents, allowing developers to run and manage Claude agents within Cloudflare. Developers can connect agents to private systems, choose their runtime environment, and monitor agent activity using Cloudflare services.

By Renato Losio

Azure Logic Apps Adds Sandboxed Code Interpreters to Agent Workflows

Steef-Jan Wiggers — Wed, 27 May 2026 09:45:00 GMT

Microsoft added sandboxed code interpreters to Azure Logic Apps, enabling agents within integration workflows to generate and execute Python, JavaScript, C#, and PowerShell in Hyper-V isolated sessions. Architects get full control over model selection per workflow. The capability positions Logic Apps as an agent platform for integration alongside Foundry and Copilot Studio.

By Steef-Jan Wiggers

Sarang Kulkarni on Lessons from Building Deep Research Agents in Production

Srini Penchikala — Wed, 27 May 2026 07:45:00 GMT

Deep Research Agentic Systems are AI Agents designed to conduct multi-step research for complex tasks using dynamic reasoning, multi-hop information retrieval, and generate structured analytical reports. Sarang Kulkarni from Thoughtworks spoke at Arc of AI Conference 2026 on how to deploy multi-agent research systems for deep reasoning, and the lessons learned from developing Deep Research Agents.

By Srini Penchikala

InfoQ Online Certification Program: New AI Engineering and Organizational Architecture Cohorts

Artenisa Chatziou — Tue, 26 May 2026 10:00:00 GMT

InfoQ expands its online certification portfolio with new AI Engineering and Organizational Architecture cohorts, giving senior practitioners a confidential peer group to pressure-test production AI, platform, team design, and architecture decisions.

By Artenisa Chatziou

Google Expands SynthID Adoption for AI Watermarking, Previews Content Detection API

Sergio De Simone — Tue, 26 May 2026 09:00:00 GMT

Google's SynthID, designed to embed imperceptible signals into AI-generated content, is adding a new Content Detection API on Google Cloud's Gemini Enterprise Agent Platform, after gaining adoption by several industry players including Nvidia and OpenAI.

By Sergio De Simone

Microsoft Introduces MDASH for Large-Scale AI Vulnerability Research

Robert Krzaczyński — Mon, 25 May 2026 16:30:00 GMT

Microsoft has introduced a new AI-driven vulnerability discovery system called MDASH, a multi-model agentic security platform designed to automate large-scale code auditing across Windows and other Microsoft software environments. The system combines more than 100 specialized AI agents that work together to scan, validate, debate, and prove vulnerabilities across complex codebases.

By Robert Krzaczyński

Gemma 4 Multi-Token Prediction Delivers up to ~3x Faster Token Generation

Sergio De Simone — Mon, 25 May 2026 09:00:00 GMT

Gemma 4 can be paired with multi-token prediction (MTP) drafters that use speculative decoding to generate multiple tokens in parallel, allowing the model to verify them in a single pass and achieve up to ~3Ã— faster inference without quality loss.

By Sergio De Simone

Google Introduces Middleware Architecture for Genkit Applications

Robert Krzaczyński — Sun, 24 May 2026 17:55:00 GMT

Google has introduced Middleware for Genkit, its open-source framework for building AI-powered and agentic applications. The update adds a programmable interception layer around model calls, tool execution, and generation loops, giving developers more control over reliability, safety, and orchestration inside production AI systems.

By Robert Krzaczyński