InfoQ Homepage News
-
AI in Production: Panellists Highlight Silent Failures, Harness Engineering, and Agent Governance
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.
-
Grafana Applies SLOs and Error Budgets to AI Agent Behaviour
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.
-
Helidon 27 Introduces Restructured Programming Models and New Messaging and Data Modules
The release of Helidon 27 is the first release that follows the Oracle Tip & Tail Model of Library Development by which the Tip adopts the latest Java technology while the Tail provides a more stable and secure baseline. Concurrent with the release of JDK 27, new features in Helidon 27 include: an introduction to new major modules, Helidon Messaging and Helidon Data JDBC.
-
AWS Introduces Strands Decider 2B and Strands Box for AI Agent Development
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.
-
Chainguard Launches Secure Workspaces and Checks for AI Coding Agents
Software supply chain security company Chainguard has announced two beta products for running and testing code written by developers and AI agents. Chainguard Workspaces provides remote development environments based on hardened microVMs, while Chainguard Checks moves continuous integration into the development loop. The company announced both products at its Assemble London event.
-
Microsoft Commits Maia to Multi-Gigawatt Inference, and Its Efficiency Metric Draws Questions
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.
-
Instagram Modernized its UI with an AI-Native Architecture, Cutting Token Costs by 33%
Instagram Direct migrated its Android UI from the legacy Android View system to Jetpack Compose, creating an AI-native UI codebase that is easier for AI coding agents to understand, modify, and maintain. According to Instagram engineers, the migration reduced UI code volume by 50% and token costs per AI agent session by 33%.
-
Optimizing Software Workflow: Exploring Fundamental Impacts in Technology
Software only has value when shipped; faster release cadence matters. Development, deployment, and operations require different thinking, metrics, and investments. There are four impacts in tech: product success, compute capacity, engineering capacity, and strategic innovation. The biggest expense is people. AI shifts engineers toward deeper problem understanding, not fewer engineers.
-
Grafana Tempo 3.1 Adds Query-Based Trace Redaction and Sampling-Aware TraceQL Metrics
Grafana Labs has released Tempo 3.1, the first minor update to the 3.0 architecture. It adds TLS and additional SASL mechanisms to the Kafka client, lets operators redact traces with a TraceQL query instead of a list of trace IDs, and introduces an experimental query-time hint that corrects TraceQL metrics for sampled data.
-
Meta Extends Confidential Computing to AI Glasses with Private Processing
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.
-
Google Antigravity SDK Adds Local Model Support for Greater Token Efficiency and Code Privacy
Google has introduced support for local models in the Antigravity SDK, enabling developers to build and execute agentic workflows directly on their own machines, while retaining the flexibility to mix in cloud-based models for higher-level tasks. This approach gives developers greater control over data privacy, inference costs, network dependencies, and computational workload distribution.
-
Cloudflares Newly Acquired Vite+ Reaches 1.0 with GitLab CI Support, Hooks, and tsup Migration
VoidZero has launched Vite+ 1.0, the first stable version of its JavaScript toolchain. It features a command line tool for managing Node.js, package management, and frontend development from a single configuration file. Enhancements include CI integration for GitLab and Docker support. Future updates are planned, focusing on stability and diagnostics.
-
Backstage 1.55 Adds Scaffolder Task Recovery and Removes Deprecated Catalog APIs
Backstage 1.55 adds opt-in recovery for Software Template tasks, resuming crashed or timed-out runs from the last completed step. The release also carries breaking changes to the catalog, search and TechDocs, so teams should review their configuration before upgrading to the current 1.55.3 patch.
-
ZCS Command Injection via SNMP Handlers Enables Unauthenticated Remote Code Execution
A critical remote command execution vulnerability in the Zimbra Collaboration Suite, identified as CVE-2026-73570, poses risks by allowing unauthorized access to mailbox data and credentials. This flaw, stemming from improper input sanitization, has been actively exploited. Organizations are advised to upgrade to version 10.1.20 or disable susceptible SNMP services to mitigate risks.
-
Production Patterns for Agents, Evals, and LLM Costs: QCon AI New York 2026
Once AI is in production, code arrives faster than it can be reviewed, token costs rise, evals have to be good enough to act on, and agents need permissions and guardrails. QCon AI New York 2026 (December 15-16) has confirmed sessions from engineers sharing how they handle these constraints.