InfoQ - Agents

Google Antigravity SDK Adds Local Model Support for Greater Token Efficiency and Code Privacy

Sergio De Simone — Wed, 14 Oct 2026 09:00:00 GMT

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.

By Sergio De Simone

Production Patterns for Agents, Evals, and LLM Costs: QCon AI New York 2026

Artenisa Chatziou — Tue, 13 Oct 2026 12:00:00 GMT

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.

By Artenisa Chatziou

Xcode 27.2 Introduces an Agent- and Merge-Friendly JSON Format for Project Configuration

Sergio De Simone — Mon, 12 Oct 2026 09:00:00 GMT

Apple is introducing a new JSON-based format for Xcode project configuration files, replacing the traditional property-list-based format. Available in Xcode 27.2, the new format aims to improve readability, simplify maintenance, and make project configuration easier for AI coding agents to understand and modify.

By Sergio De Simone

Presentation: Multi-Agent Patterns from Spotify’s AI Powered Advertising Platform

Pratik Rasam — Thu, 08 Oct 2026 11:00:00 GMT

Pratik Rasam discusses how Spotify Ads Manager runs production-grade multi-agent systems at scale using Google ADK Java. He shares key architectural patterns, domain ownership models, deterministic guardrails, and tracing-based evaluation strategies, detailing hard-learned lessons on drawing agent boundaries, optimizing tool schemas, and managing costs while avoiding monolithic agent pitfalls.

By Pratik Rasam

Survey Finds AI-Generated Code Increases Debugging and Failure Rates and Creates a Comprehension Gap

Sergio De Simone — Wed, 07 Oct 2026 18:00:00 GMT

A survey conducted by independent research firm Coleman Parkes on behalf of Undo, a company focused on scaling AI-powered root-cause analysis, found that while AI coding agents have accelerated code generation, they have shifted the primary bottleneck to debugging, code comprehension, and maintenance.

By Sergio De Simone

Spanner Omni Reaches GA, Replacing Google's Atomic Clocks and File System with Software

Steef-Jan Wiggers — Wed, 07 Oct 2026 04:43:00 GMT

Google has made Spanner Omni generally available, running its distributed SQL database on-premises, across clouds or on a laptop. Doing so meant replacing Colossus with a Colossus-like abstraction layer and TrueTime with software-based time synchronization. There is no availability SLA, and practitioners are pricing the move in tail latency and operational toil.

By Steef-Jan Wiggers

Cloudflare Introduces CLI for AI Agents, Sunsetting Wrangler

Renato Losio — Tue, 06 Oct 2026 04:59:00 GMT

Cloudflare recently launched the open beta of cf, a new open-source, agent-focused command-line interface for interacting with Cloudflare services through a unified CLI. Written in TypeScript, it provides structured output and command discovery to make Cloudflare’s APIs easier for both developers and AI agents.

By Renato Losio

Presentation: Building Reusable Evaluation Frameworks for Agentic AI Products

Susan Chang — Mon, 05 Oct 2026 11:19:00 GMT

Susan Chang explains how Elastic transitioned from siloed, ad-hoc AI agent evaluations to a unified, production-grade framework. She discusses balancing LLM-as-a-judge with deterministic rules, bridging Python data science evals with TypeScript production code, and implementing deep tracing to catch regressions across complex RAG and cybersecurity workloads while preserving domain context.

By Susan Chang

Article: The Platform Engineering Playbook for Production LLMs

Aditya Mulik — Mon, 05 Oct 2026 11:00:00 GMT

In this article, author discusses his experience with AI agent hallucinations in an inventory recommendation system and how this problem was solved by treating the LLM stack as a platform infrastructure concern instead of as an application one. He makes a case for a shared LLM platform with common services like prompt registry & versioning, schema enforcement and token cost attribution by request.

By Aditya Mulik

Pizza Bot: Open-Source Inbox for Background AI Agents

Renato Losio — Sun, 04 Oct 2026 06:34:00 GMT

A team of developers working at AWS recently open-sourced Pizza Bot, a self-hosted application designed to let AI agents run tasks in the background and return results through an inbox-style interface. Agents can perform scheduled or webhook-triggered work, delegate tasks to specialized workers, and pause for human approval when needed.

By Renato Losio