AI
110 briefings in the desk
The Day the Model Answered “Billing.” With a Period
Why an LLM returning “Billing.” can break an otherwise sensible classifier—and how typed outputs, validation, and failure-aware routing make the boundary reliable.
When Company Names Are All You Have: Exploring LLM-Based Entity Matching
Can an LLM determine whether “ING BANK N.V.” and “ING Bank” refer to the same company when names are the only available signal?
Small models are becoming the default edge runtime
The useful question is no longer whether a model fits on-device, but which parts of a product should never leave it.
Turn your REST APIs into MCP tools with Google Cloud API Gateway
Google Cloud API Gateway now acts as a native remote Model Context Protocol (MCP) server, eliminating the need to build and maintain custom middleware to expose REST APIs to AI agents. By simply adding specific annotations (like x-google-ap
Reproducing OLMo 3 7B Pre-training in MaxText: case study of large scale training on TPUs
The MaxText team successfully reproduced AI2’s OLMo 3 7B language model from scratch on Google Cloud TPUs using JAX/XLA, precisely matching the original PyTorch-on-GPU reference across pre-training and mid-training stages on all held-out ev
Spotlight on SIG Apps
As Kubernetes adoption has grown, the conversation has shifted beyond running containers to managing increasingly complex application lifecycles. Modern platforms support stateless web services, stateful databases, batch processing, AI…
Introducing Support for Local AI Models in the Antigravity SDK
The Google Antigravity SDK now empowers developers to execute offline, agentic workflows locally using models like Gemma 4 26B A4B via LiteRT. This update facilitates powerful hybrid orchestration architectures, allowing a cloud model to ac
What coding agents change about code review
When code gets cheaper to produce, attention—not typing—becomes the scarce engineering resource.
Why client SDK generation belongs in the open
Google has partnered with Speakeasy to open-source their OpenAPI code generation suite under the AGPLv3 license, a strategic move prompted by the sudden shutdown of Google's previous proprietary SDK provider. The newly open-sourced suite eq
Agent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform
Agent Anomaly Detection is a new, out-of-band oversight layer for the Gemini Enterprise Agent Platform that analyzes OpenTelemetry traces and tool calls to catch behavioral risks without adding runtime latency to live requests. It utilizes
Build zero-trust AI agents that judge intent, not just syntax
This blog post explores how to transition AI agents from static, build-time security controls to dynamic runtime governance using the Gemini Enterprise Agent Platform. It highlights three primary managed defenses: Model Armor for screening
Autonomous LLM post-training with Tunix on TPUs
The "autofinetune" project introduces an autonomous research loop that fully automates LLM post-training workflows, including Supervised Fine-Tuning (SFT) and Reinforcement Learning via GRPO. By defining boundary conditions and evaluation m
Kubernetes v1.37: Advancing Workload-Aware Scheduling
AI/ML and complex batch workloads continue to push the boundaries of Kubernetes scheduling. Following the foundational workload-centric enhancements introduced in previous releases, Kubernetes v1.37 delivers the next major milestone in the…
The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents
While end-to-end benchmarks like SWE-bench provide broad performance scores for AI agents, they are often expensive, slow, and lack the root-cause diagnostics needed to explain exactly where an agent's logic broke down. To solve this, devel
Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond
Google has officially released version 1.0 of the Agent Development Kit (ADK) for Kotlin, achieving full feature parity with the Python and Java ADK cores to enable idiomatic, multi-agent AI development. Built on Kotlin Multiplatform (KMP),
Kubernetes v1.37: DRA Updates
Kubernetes 1.37 is here and Dynamic Resource Allocation (DRA) keeps pushing past where it started! This release brings DRA Extended Resource support to GA, a milestone the team has been building toward for three straight releases. Several…
Driving Developer Excellence: Inside the Program Sprints
The Gemini Enterprise Developer Experience (DevEx) program conducts ongoing sprint testing of end-to-end developer workflows to identify and rapidly resolve friction points without relying on internal shortcuts. This recent sprint focused o
Kubernetes v1.37: Scale Workloads to Zero with HorizontalPodAutoscaler
Kubernetes v1.37 includes API support for horizontal autoscaling of workloads down to zero replicas. This feature is now Beta and enabled by default. A HorizontalPodAutoscaler (HPA) that uses a suitable object metric or external metric can…
4 engineering patterns behind the strongest AI Agents Challenge submissions
The recent Google for Startups AI Agents Challenge revealed that the most successful multi-agent systems rely on foundational software engineering patterns rather than just raw model power. Winning architectures consistently implemented bid
Enterprise-Grade Precision for Long-Context Multimodal Embedding Inference on Cloud TPU
Google Cloud has natively integrated TPU support into the vLLM serving engine, allowing developers to elastically scale high-demand embedding pipelines using Google Kubernetes Engine (GKE). To handle massive 15K+ token contexts for models l
How to Evaluate Live & Voice Agents in ADK
Moving live voice agents from demo to production requires rigorous, automated testing to handle the unpredictability of real multi-turn conversations. ADK now provides native live evaluation, allowing developers to test graph-based agent wo
Build zero-trust AI agents with Google's Agent Development Kit
Building autonomous AI agents that mutate production state requires moving beyond soft system prompts to a robust zero-trust architecture. To secure Google Agent Development Kit (ADK) workflows against prompt injections and malicious execut
HeyGen x Google Cloud: Bringing Avatar IV to TPUs
HeyGen ported their 18B+ parameter Avatar IV video generation model to Google Cloud's Trillium (v6e) TPUs via torchax and XLA, utilizing FSDP and Ulysses sequence parallelism across an eight-chip mesh. To achieve a 1.86x speedup for real-ti
Why Go is an Ideal Language for AI-Assisted Software Engineering
As AI coding assistants shift the developer's primary role from writing boilerplate to reviewing and maintaining systems, language choice becomes critical for long-term architectural integrity. Go directly addresses this new paradigm by uti