InfoQ - AI, ML & Data Engineering

Anthropic Introduces Managed Agents to Simplify AI Agent Deployment

Leela Kumili — Tue, 21 Apr 2026 14:36:00 GMT

Anthropic introduces Managed Agents on Claude, a managed execution layer for agent-based workflows. It separates agent logic from runtime concerns like orchestration, sandboxing, state management, and credentials. The system supports long-running multi-step workflows with external tools, error recovery, and session continuity via a meta-harness architecture.

By Leela Kumili

GitHub Acknowledges Recent Outages, Cites Scaling Challenges and Architectural Weaknesses

Craig Risi — Tue, 21 Apr 2026 12:00:00 GMT

GitHub has publicly addressed a series of recent availability and performance issues that disrupted services across its platform, attributing the incidents to rapid growth, architectural coupling, and limitations in handling system load.

By Craig Risi

Presentation: Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash

Sudeep Das, Pradeep Muthukrishnan — Tue, 21 Apr 2026 10:35:00 GMT

Sudeep Das and Pradeep Muthukrishnan explain the shift from static merchandising to dynamic, moment-aware personalization at DoorDash. They share how LLMs generate natural-language "consumer profiles" and content blueprints, while traditional deep learning handles last-mile ranking. This hybrid approach allows the platform to adapt to short-lived user intent and massive catalog abundance.

By Sudeep Das, Pradeep Muthukrishnan

Designing Memory for AI Agents: Inside Linkedin’s Cognitive Memory Agent

Leela Kumili — Mon, 20 Apr 2026 14:59:00 GMT

LinkedIn introduces Cognitive Memory Agent (CMA), generative AI infrastructure layer enabling stateful, context-aware systems. It provides persistent memory across episodic, semantic, and procedural layers, supporting multi-agent coordination, retrieval, and lifecycle management. CMA addresses LLM statelessness and enables production-grade personalization and long-term context in AI applications.

By Leela Kumili

Subagents in Gemini CLI Enable Task Delegation and Parallel Agent Workflows

Robert Krzaczyński — Mon, 20 Apr 2026 12:26:00 GMT

Google has introduced subagents in Gemini CLI, a new capability designed to help developers delegate complex or repetitive tasks to specialized AI agents operating alongside a primary session.

By Robert Krzaczyński

Google ADK for Java 1.0 Introduces New App and Plugin Architecture, External Tools Support, and More

Sergio De Simone — Mon, 20 Apr 2026 10:00:00 GMT

Google's Agent Development Kit for Java reached 1.0, introducing integrations with new external tools, a new app and plugin architecture, advanced context engineering, human-in-the-loop workflows, and more.

By Sergio De Simone

Google’s Aletheia Advances the State of the Art of Fully Autonomous Agentic Math Research

Bruno Couriol — Sun, 19 Apr 2026 04:38:00 GMT

Google announced Aletheia, an AI using Gemini 3 Deep Think that solved 6/10 novel math problems in the FirstProof challenge. Aletheia also scored ~91.9% on IMO-ProofBench, signaling a significant shift in automated research-level proof discovery without human intervention.

By Bruno Couriol

AWS Announces General Availability of DevOps Agent for Automated Incident Investigation

Renato Losio — Sat, 18 Apr 2026 11:31:00 GMT

AWS has announced the general availability of DevOps Agent, a generative AI–powered assistant designed to help developers and operators troubleshoot issues, analyze deployments, and automate operational tasks across AWS environments.

By Renato Losio

Meta Reports 4x Higher Bug Detection with Just-in-Time Testing

Leela Kumili — Fri, 17 Apr 2026 14:49:00 GMT

Meta introduces Just-in-Time (JiT) testing, a dynamic approach that generates tests during code review instead of relying on static test suites. The system improves bug detection by ~4x in AI-assisted development using LLMs, mutation testing, and intent-aware workflows like Dodgy Diff. It reflects a shift toward change-aware, AI-driven software testing in agentic development environments.

By Leela Kumili

CNCF Warns Kubernetes Alone Is Not Enough to Secure LLM Workloads

Craig Risi — Fri, 17 Apr 2026 12:00:00 GMT

A new blog from the Cloud Native Computing Foundation highlights a critical gap in how organizations are deploying large language models (LLMs) on Kubernetes: while Kubernetes excels at orchestrating and isolating workloads, it does not inherently understand or control the behavior of AI systems, creating a fundamentally different and more complex threat model.

By Craig Risi

Anthropic Introduces Agent-Based Code Review for Claude Code

Daniel Dominguez — Fri, 17 Apr 2026 10:16:00 GMT

Anthropic has introduced a new Code Review feature for Claude Code, adding an agent-based pull request review system that analyzes code changes using multiple AI reviewers.

By Daniel Dominguez

Article: Lakehouse Tower of Babel: Handling Identifier Resolution Rules across Database Engines

Maninder Parmar — Fri, 17 Apr 2026 09:00:00 GMT

Lakehouse architectures enable multiple engines to operate on shared data using open table formats such as Apache Iceberg. However, differences in SQL identifier resolution and catalog naming rules create interoperability failures. This article examines these behaviors and explains why enforcing consistent naming conventions and cross-engine validation is critical.

By Maninder Parmar

AWS Launches Agent Registry in Preview to Govern AI Agent Sprawl across Enterprises

Steef-Jan Wiggers — Fri, 17 Apr 2026 06:54:00 GMT

AWS released Agent Registry in preview as part of Amazon Bedrock AgentCore, providing a centralized catalog for discovering, governing, and reusing AI agents, tools, and MCP servers across organizations. The registry indexes agents regardless of where they run and supports both MCP and A2A protocols natively. Microsoft, Google Cloud, and the ACP Registry offer competing solutions.

By Steef-Jan Wiggers

Google Opens Gemma 4 Under Apache 2.0 with Multimodal and Agentic Capabilities

Hien Luu — Thu, 16 Apr 2026 17:05:00 GMT

Google has announced the release of Gemma 4, a series of open-weight AI models, including variants with 2B, 4B, 26B, and 31B parameters, under the Apache 2.0 license. Key features include enhanced video and image processing, audio input on smaller models, and extended context windows up to 256K tokens.

By Hien Luu

Cloudflare Launches Code Mode MCP Server to Optimize Token Usage for AI Agents

Leela Kumili — Thu, 16 Apr 2026 14:17:00 GMT

Cloudflare has launched a new Model Context Protocol (MCP) server powered by Code Mode, enabling AI agents to interact with large APIs with minimal token usage. The server reduces context footprint across 2,500+ endpoints, improves multi-API orchestration, and provides a secure, code-centric execution environment for LLM agents.

By Leela Kumili