InfoQ Homepage AI Development Content on InfoQ
-
AWS Releases aws-bench to Evaluate Agents on Cloud Tasks
AWS has released aws-bench, an open-source benchmark for evaluating AI agents on real AWS tasks such as misconfigurations and infrastructure provisioning. Unlike traditional benchmarks, it uses real resources in disposable AWS accounts, scoring agent performance through automated verifiers.
-
Cloudflare Turns Engineering Standards into an AI-Enforced Control System
Cloudflare has recently detailed how it is using AI to transform internal engineering standards from passive documentation into an actively enforced control system across the software development lifecycle.
-
GitHub Brings Stacked Pull Requests to Public Preview
GitHub has announced that Stacked Pull Requests are now available in public preview, introducing native support for breaking large software changes into smaller, dependent pull requests that can be reviewed and merged independently.
-
Grab Cuts Mechanical Analytics Work from 44% to 30% with AI Agents
Grab is using AI agents to automate analytics workflows, cutting mechanical analyst work from 44% in February to 30% in June. Its approach combines agent autonomy, certified data, context management and human oversight, with self service analytics increasingly handling metric, data and SQL requests without analyst intervention.
-
shadcn Brings Conversational Primitives to shadcn/ui with New Chat Components
Shadcn, a design engineer at Vercel, has introduced new components for chat interfaces within the shadcn/ui project. This release includes components like MessageScroller and Message, focusing on conversation functionality. The approach emphasizes modular design, allowing developers to adapt elements without affecting underlying logic or styles. Support for headless components is also provided.
-
Embabel Agent Framework Reaches 1.0
Embabel has reached its 1.0 release, providing a framework for AI agents on Java It allows Java and Kotlin developers to define agents as typed domain objects. Built on Spring AI, Embabel supports multiple model providers and combines planning with predefined state machines, offering flexibility for agent workflows.
-
Stripe Benchmark Shows AI Agents Build Integrations but Struggle with Validation
Stripe introduces a benchmark suite to evaluate whether AI agents can build real-world Stripe integrations across backend, frontend, and browser-based checkout workflows. The study examines end-to-end software engineering capability, focusing on execution, testing, and validation gaps in agentic systems under production-like constraints.
-
AI Is Moving up the Software Lifecycle: from Code Review to PRD Governance
Technology companies are extending AI beyond code generation into earlier stages of the software lifecycle, including PRD validation, design inputs, and code review. Initiatives from Uber, DoorDash, and Cloudflare highlight a shift toward AI-driven governance layers that evaluate engineering artifacts before implementation while preserving human oversight across the development pipeline.
-
AI-Assisted Migration Tool Helps Teams Move from ingress-nginx to Higress in Minutes
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.
-
Pullfrog AI: Open-Source CodeRabbit Alternative Powered by GitHub Actions
Pullfrog is an open-source AI-powered GitHub bot by Colin McDonnell, designed for automation in GitHub Actions. It supports a model-agnostic approach, allowing integration with various LLM providers. Key features include orchestration for pull request reviews, issue triage, and CI remediation, all managed within GitHub's environment. The tool operates with a bring-your-own-key model for access.
-
Inside Claude Code Auto Mode: Anthropic’s Autonomous Coding System with Human Approval Gates
Anthropic has introduced auto mode in Claude Code, enabling multi-step software development workflows with reduced manual intervention. The feature combines automated execution with layered safety mechanisms, including input filtering, action evaluation, and two-stage classification, while maintaining human approval checkpoints for sensitive operations.
-
Uber Migrates 75,000+ Test Classes from Junit 4 to Junit 5 Using Automated Code Transformation
Uber engineers migrated over 75,000 test classes from JUnit 4 to JUnit 5 using automated code transformation with OpenRewrite and internal orchestration. By enabling the JUnit Platform for dual execution with Bazel and validating changes through CI, the team modernized testing infrastructure while maintaining correctness at monorepo scale.
-
Anthropic Introduces Managed Agents to Simplify AI Agent Deployment
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.
-
Designing Memory for AI Agents: inside Linkedin’s Cognitive Memory Agent
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.
-
Cursor 3 Introduces Agent-First Interface, Moving beyond the IDE Model
Anysphere released Cursor 3, a redesigned interface built from scratch that shifts the primary model from file editing to managing parallel coding agents. The new workspace supports local-to-cloud agent handoff, multi-repo parallel execution, and a plugin marketplace. Community reaction has been divided, with developers questioning cost overhead and the move away from Cursor's IDE-first identity.