# Google Developers Blog Updates on changes and additions to the Google Developers Blog. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Agent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform DevFeed: [Agent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform]() Original publisher: [Read original article]() Author: Achuth Narayan Rajagopal Published: 2026-09-17T01:25:27.608736Z Content type: release Language: en Sources: [Google Developers Blog]() Topics: [agent observability](), [OpenTelemetry](), [Security](), [Traces](), [API]() Tags: [agent](), [anomaly-detection](), [api](), [autonomous-agents](), [gemini](), [opentelemetry](), [security]() ### AI overview Google announces Agent Anomaly Detection in private preview on the Gemini Enterprise Agent Platform. The feature analyzes agents' reasoning traces, tool calls, logs, and execution flows to identify behavioral anomalies, suspicious intent, and policy violations. ### Source excerpt 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 a multi-tiered detection pipeline--combining lightweight statistical scanning with deep LLM-based reasoning--to identify logical anomalies and policy violations grounded in the OWASP Agentic Top 10. Developers can triage these automated findings within Security Command Center or leverage the exposed API to programmatically block subsequent tool calls when an agent breaches defined risk thresholds. ## Build zero-trust AI agents that judge intent, not just syntax DevFeed: [Build zero-trust AI agents that judge intent, not just syntax]() Original publisher: [Read original article]() Author: Eric Dong; Shubham Saboo Published: 2026-09-16T01:23:36.799575Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Artificial Intelligence](), [Security](), [Zero Trust]() Tags: [agents](), [ai](), [ai-agents](), [gemini](), [model-context-protocol](), [python](), [security](), [zero-trust]() ### AI overview This blog post explains how to move AI-agent security from static, build-time controls to dynamic runtime governance on the Gemini Enterprise Agent Platform. It covers Model Armor, Semantic Governance Policies, and Agent Anomaly Detection with Closed-Loop Remediation for evaluating intent, enforcing business rules, and detecting multi-turn attacks. ### Source excerpt 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 edge prompts, Semantic Governance Policies for evaluating tool intent against business rules, and Agent Anomaly Detection for catching multi-turn exploits. By shifting these capabilities to the platform level, security administrators can dynamically enforce policies and neutralize complex attacks without needing to modify or redeploy the agent's underlying code. ## Scaling AI Agent Infrastructure with the MCP Stateless updates DevFeed: [Scaling AI Agent Infrastructure with the MCP Stateless updates]() Original publisher: [Read original article]() Author: Kurtis Van Gent; Alan Blount Published: 2026-09-12T11:04:33.891311Z Content type: release Language: en Sources: [Google Developers Blog]() Topics: [networking](), [SDKs]() Tags: [agentic](), [ai-agent](), [c-sharp](), [go](), [http](), [infrastructure](), [mcp](), [python](), [routing](), [sdks](), [serverless](), [typescript](), [updates]() ### AI overview The MCP release candidate replaces transport-level session management with a stateless core for HTTP load balancing, cloud-native scaling, and serverless deployments. It also introduces routing headers, caching controls, MRTR, and beta SDKs for Python, TypeScript, Go, and C#. ### Source excerpt The 2026-07-28 Model Context Protocol (MCP) specification replaces legacy stateful constraints with a fully stateless core, enabling cloud-native horizontal scaling, serverless deployments, and standard round-robin load balancing. This architectural shift introduces standardized HTTP headers for efficient routing without deep packet inspection, caching controls, and Multi Round-Trip Requests (MRTR) to handle interactive and long-running tasks without blocking connections. Developers can immediately begin migrating their agentic applications to this highly scalable infrastructure using the newly available beta SDKs for Python, TypeScript, Go, and C#. ## HeyGen x Google Cloud: Bringing Avatar IV to TPUs DevFeed: [HeyGen x Google Cloud: Bringing Avatar IV to TPUs]() Original publisher: [Read original article]() Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Google](), [Cloud](), [Artificial Intelligence](), [Optimization](), [AI Infrastructure](), [Transformer](), [PyTorch](), [Compiler](), [Streaming](), [real-time](), [Hardware](), [API]() Tags: [ai](), [ai-infrastructure](), [api](), [cloud](), [code](), [compiler](), [engineering](), [generation](), [google](), [hardware](), [model](), [optimization](), [performance](), [pytorch](), [real-time](), [streaming](), [time](), [tpu](), [transformers](), [video]() ### AI overview HeyGen and Google Cloud describe porting the 18B+ parameter Avatar IV talking-head video generation pipeline to an eight-chip Trillium TPU host. Using torchax, JAX, XLA, FSDP sharding, Ulysses sequence parallelism, and custom Pallas kernels, the team improved performance by 1.86x for real-time chunked streaming while preserving output quality through strict quality gates. ### Source excerpt 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-time streaming, the engineering team pipelined exposed all-to-all collectives, aligned sparse attention block sizes to eliminate mask padding, and bypassed softmax serial dependencies using a precomputed Cauchy-Schwarz upper bound. These custom Pallas kernel and compiler optimizations were deployed only after passing rigorous two-tier quality gates to guarantee byte-identical or mathematically equivalent pixel outputs. ## Why Go is an Ideal Language for AI-Assisted Software Engineering DevFeed: [Why Go is an Ideal Language for AI-Assisted Software Engineering]() Original publisher: [Read original article]() Author: Cameron Balahan; Richard Seroter Published: 2026-09-12T11:04:33.891311Z Content type: opinion Language: en Sources: [Google Developers Blog]() Topics: [Go Language](), [Software Engineering](), [AI Development](), [Architecture & Design](), [Tooling]() Tags: [ai](), [ai-coding](), [compatibility](), [developer-tools](), [engineering](), [go](), [software-development](), [software-engineering]() ### AI overview The article argues that AI-assisted software engineering shifts developers' work from writing boilerplate toward reviewing, verifying, maintaining, and architecting systems. It presents Go as well suited to this model because its simplicity, readability, tooling, compatibility guarantees, and team-oriented design provide consistency and guardrails for AI-generated code. ### Source excerpt 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 utilizing its strict compiler, integrated toolchain, and uncompromising readability to provide deterministic guardrails that help AI models self-correct and generate highly standardized code. By enforcing ecosystem-wide consistency and strict backward compatibility, the Go platform empowers engineering teams to efficiently verify, optimize, and maintain high-velocity, AI-generated output in production environments. ## Model routing with Google Cloud API Gateway DevFeed: [Model routing with Google Cloud API Gateway]() Original publisher: [Read original article]() Author: Mak Ahmad; Sanjay Pujare Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Amazon API Gateway](), [Model Routing](), [Google](), [Cloud](), [OpenAPI Specification](), [Serverless](), [Claude](), [OpenAI]() Tags: [ai-gateway](), [api-gateway](), [claude](), [cloud](), [google](), [model-routing](), [models](), [openai](), [openapi](), [serverless]() ### AI overview Google Cloud API Gateway adds model routing in Public Preview, providing a serverless, OpenAI-compatible endpoint that dynamically routes requests to Gemini, Claude, or OpenAI OSS-GPT. Developers can configure routing in OpenAPI specifications, centralize model changes, and separate application authentication from backend model credentials. ### Source excerpt Google Cloud API Gateway now offers a model routing feature in Public Preview, allowing developers to dynamically route traffic to models like Gemini, Claude, or OpenAI OSS-GPT without hardcoding endpoints or managing open-source proxies. Developers can easily configure these routing rules directly within their OpenAPI 3.x specifications by mapping virtual model names to specific backend targets on a shared host. Once deployed, the Gateway acts as a serverless ingress layer that accepts standard OpenAI-compatible requests, automatically transcodes the payload to the native schema of the target model, and routes the traffic on the fly. ## Enterprise-Grade Precision for Long-Context Multimodal Embedding Inference on Cloud TPU DevFeed: [Enterprise-Grade Precision for Long-Context Multimodal Embedding Inference on Cloud TPU]() Original publisher: [Read original article]() Author: Anthony Su; Injae Kwak Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Embeddings](), [vllm](), [Inference](), [long-context](), [autoscaling](), [Kubernetes](), [Cloud](), [Google](), [Artificial Intelligence](), [model-deployment](), [Open Source]() Tags: [autoscaling](), [embedding](), [github](), [gpu](), [inference](), [kubernetes](), [long-context](), [multimodal](), [open-source](), [retrieval](), [tpu](), [vllm]() ### AI overview This article explains how Google Cloud integrated native TPU support into vLLM to serve long-context, multimodal embedding models at production scale. It describes elastic TPU provisioning with Google Kubernetes Engine, autoscaling across accelerator types, and TPU-specific optimizations for long sequences and chunked prefill. The resulting setup is designed to preserve numerical parity with GPU reference baselines while supporting high-throughput semantic retrieval applications. ### Source excerpt 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 like Qwen3-Embedding-8B, the engineering team implemented TPU-specific optimizations such as hardware-safe tensor alignment, JAX/XLA compilation pre-warming, and a hybrid StepPool architecture for chunked prefill management. These enhancements achieve near-perfect numerical parity with reference GPU baselines, and developers can immediately leverage the open-sourced setup recipes on the AI-Hypercomputer GitHub to build their own high-throughput semantic retrieval applications. ## 4 engineering patterns behind the strongest AI Agents Challenge submissions DevFeed: [4 engineering patterns behind the strongest AI Agents Challenge submissions]() Original publisher: [Read original article]() Author: Sergio Villani Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [AI Bots](), [MSP MCP]() Tags: [agents](), [ai-agents](), [cost](), [engineering](), [event](), [inference](), [latency](), [mcp](), [mcp-server](), [routing](), [validation]() ### AI overview An article on engineering patterns found in leading AI Agents Challenge submissions. It highlights bidirectional MCP, asynchronous event buses, unified validation for model fallbacks, and tiered routing to make agentic workflows more resilient, faster, and less costly. ### Source excerpt 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 bidirectional MCP for seamless inter-agent communication, async event buses for parallel execution, strict unified validation for model fallbacks, and tiered routing to minimize expensive inference calls. By prioritizing these structural practices over simple linear prompt chains, developers can build more resilient, low-latency, and cost-effective agentic workflows. ## Build zero-trust AI agents with Google's Agent Development Kit DevFeed: [Build zero-trust AI agents with Google's Agent Development Kit]() Original publisher: [Read original article]() Author: Shubham Saboo; Eric Dong Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [AI Agent](), [Security](), [Zero Trust](), [Google](), [prompt injection](), [Architecture & Design](), [Code](), [Python](), [Open Source]() Tags: [agent](), [agents](), [ai](), [architecture](), [code](), [google](), [open-source](), [prompt-injection](), [python](), [sandboxes](), [security](), [zero-trust]() ### AI overview This article explains how to build zero-trust AI agents with Google's Agent Development Kit (ADK). It presents an autonomous customer support and returns agent as an example and recommends hard infrastructure-level controls: cryptographic signatures for database writes, kernel-level sandboxing with gVisor for dynamic code execution, and deterministic gateways for validating I/O, business logic, and data leakage. These controls address prompt injection, unauthorized state changes, credential leakage, and host compromise. ### Source excerpt 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 execution, developers must implement hardware-backed cryptographic signatures for database writes, kernel-level sandboxing with gVisor for dynamic code, and deterministic semantic gateways for I/O validation. By enforcing these hard security boundaries at the infrastructure level, you can safely deploy multi-tool AI agents without risking unauthorized data manipulation or server compromise. ## Autonomous LLM post-training with Tunix on TPUs DevFeed: [Autonomous LLM post-training with Tunix on TPUs]() Original publisher: [Read original article]() Author: Wei Wei Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [post-training](), [AI Agent](), [Fine-tuning](), [Large Language Model](), [grpo](), [lora](), [gemma](), [Google](), [Reinforcement learning](), [dataset](), [Command-line interface]() Tags: [autonomous](), [cli](), [fine-tuning](), [gemma](), [git](), [google](), [grpo](), [llm](), [lora](), [post-training](), [reinforcement-learning](), [training]() ### AI overview This article presents autofinetune, an autonomous research loop for LLM post-training. Using AI agents and Google's AI stack, including Tunix, Gemma, Cloud TPUs, Antigravity CLI, and Gemini Flash 3.7, it automates supervised fine-tuning and reinforcement learning with GRPO, exploring hyperparameters such as LoRA configurations, learning rates, batch sizes, and rollout settings. ### Source excerpt Imagine going to sleep after writing a single Markdown specification and waking up to find that an A... ## Agent Plugins package your skills, tools, and more DevFeed: [Agent Plugins package your skills, tools, and more]() Original publisher: [Read original article]() Author: Kevin Hou; Haoyu Wang; Alan Blount Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Agent Skills](), [Model Context Protocol (MCP)](), [MCP Server](), [Google](), [amazon](), [Microsoft](), [OpenAI](), [Vercel]() Tags: [agent-skills](), [amazon](), [google](), [maintainers](), [manifest](), [mcp](), [mcp-server](), [microsoft](), [openai](), [plugin](), [portable](), [skills](), [vercel]() ### AI overview The article introduces Agent Plugins 1.0.0, a vendor-neutral specification for packaging Agent Skills and MCP servers into portable plugins. It standardizes the manifest and directory layout so developers can distribute one package across clients while preserving client-specific flexibility. Google is joining the Core Maintainers and beginning support in its products. ### Source excerpt Agent Plugins 1.0.0 is a new, vendor-neutral directory specification--backed by Google, Amazon, Microsoft, and others--for packaging Agent Skills and MCP servers into a single portable unit. By standardizing the manifest (plugin.json) and utilizing a fixed directory layout, it eliminates the need for developers to maintain separate wrappers or configurations to support different AI coding agents and IDEs. Google has officially joined as a Core Maintainer and already rolled out support in the Agents CLI and Data Agent Kit, allowing developers to start building and distributing interoperable plugins today. ## How to Evaluate Live & Voice Agents in ADK DevFeed: [How to Evaluate Live & Voice Agents in ADK]() Original publisher: [Read original article]() Author: Stephen Allen Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [AI Bots](), [CI/CD]() Tags: [agents](), [audio](), [ci-cd](), [cli](), [evaluation](), [gemini](), [how-to](), [json](), [llm](), [production](), [testing](), [tool](), [tools](), [transcripts](), [voice](), [workflows]() ### AI overview The article explains how to evaluate live voice agents in ADK with simulated audio conversations, automated scoring, and recorded results. It covers scenario-based and fixed-conversation test cases, multi-agent workflows, and running evaluations in CI/CD. ### Source excerpt 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 workflows against LLM-driven simulated users that generate actual audio via Gemini TTS. By defining evaluation scenarios and natural-language rubrics, you can automatically score audio responses and tool executions, inspect the resulting transcripts in ADK Web, or run the CLI directly in your CI/CD pipeline. ## Enable on-demand expertise with Agent Skills in Genkit Go DevFeed: [Enable on-demand expertise with Agent Skills in Genkit Go]() Original publisher: [Read original article]() Author: Daniela Petruzalek Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [Agent Skills](), [Agent Harness](), [context window](), [Go](), [Script]() Tags: [agent](), [agent-skills](), [architecture](), [context-window](), [developers](), [go](), [skills](), [workflows]() ### AI overview This article explains how Agent Skills in Genkit Go provide on-demand specialized expertise through progressive disclosure. Skills package instructions, references, and scripts in modular SKILL.md bundles, exposing only metadata initially and loading full content when a task requires it. ### Source excerpt To prevent context window bloat and reduce token consumption, Genkit Go introduces Agent Skills based on a progressive disclosure architecture. Developers can package specialized instructions, scripts, and references into modular SKILL.md bundles where only the frontmatter metadata is initially exposed to the agent's system prompt. When a task matches the skill's description, Genkit's middleware dynamically loads the full instruction body and associated assets, ensuring the model accesses precise workflows exactly when needed. ## Mastering Edge AI on Raspberry Pi with LiteRT and Gemma DevFeed: [Mastering Edge AI on Raspberry Pi with LiteRT and Gemma]() Original publisher: [Read original article]() Author: Lu Wang; Terry Heo; Naushir Patuck; José María Casanova Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [LiteRT](), [On-device AI](), [Local AI](), [AI, ML & Data Engineering](), [Google AI](), [cpu](), [Security, Privacy and Abuse Prevention]() Tags: [cli](), [cpu](), [edge](), [gemma](), [gpu](), [inference](), [litert](), [offline](), [on-device](), [real-time](), [robotics]() ### AI overview The article explains how to deploy Gemma models with LiteRT on a Raspberry Pi for local, real-time edge AI applications such as robotics. It highlights LiteRT-LM, CPU and GPU optimization, and reported performance figures for Gemma 4 E2B on Raspberry Pi 5. ### Source excerpt Deploying secure, real-time Edge AI on Raspberry Pi is now simplified using LiteRT and lightweight Gemma open models. LiteRT optimizes CPU and GPU performance, delivering fast token speeds for models like Gemma4, enabling real-time local reasoning for robotics. Developers can quickly convert, quantize, and run these models using the lightweight LiteRT CLI tool. Support for Hailo AI accelerators is also coming very soon. ## Introducing Credentio: Open Source C++ Library for C2PA Content Credentials from Google DevFeed: [Introducing Credentio: Open Source C++ Library for C2PA Content Credentials from Google]() Original publisher: [Read original article]() Author: Sherif Hanna Published: 2026-09-12T11:04:33.891311Z Content type: news Language: en Sources: [Google Developers Blog]() Topics: [C++](), [Google](), [Open Source](), [Local-First](), [API](), [data]() Tags: [api](), [c-plus-plus](), [data-privacy](), [google](), [local-first](), [open-source](), [performance](), [provenance](), [validation]() ### AI overview Google introduces Credentio, an open-source C++ library for validating C2PA Content Credentials locally within client applications, server pipelines, and edge software. It is designed for high-performance validation of large media assets with lower memory usage, configurable trust lists, and no need to transmit files to cloud or external validation services. Future plans include generating and embedding Content Credentials. ### Source excerpt Credentio is a newly released, open-source C++ library from Google that allows developers to integrate high-performance, local-first validation of C2PA Content Credentials into their client and server applications. By processing assets entirely locally with a highly optimized memory footprint, the library delivers instant validation verdicts for multi-gigabyte media files without incurring cloud latency, bandwidth costs, or data privacy risks. The library currently features deep manifest parsing alongside configurable trust list integration, and is available now on Google Source with future plans to support full credential generation and embedding. ## How to use Google microbenchmarks for evaluating TPU performance DevFeed: [How to use Google microbenchmarks for evaluating TPU performance]() Original publisher: [Read original article]() Author: Junjie Qian; Chi Shuen Lee; Yu-Hsuan (Amy) Lin; Haixiong (Sean) Wang Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [Google AI](), [Inference Performance]() Tags: [architecture](), [benchmarks](), [compute](), [developers](), [google](), [guides](), [hardware](), [how-to](), [kernel](), [machine-learning](), [memory](), [mesh](), [metrics](), [model](), [open](), [open-source](), [performance](), [scale](), [software](), [tpu]() ### AI overview A tutorial on using Google's TPU microbenchmark suite to measure network, compute, memory, host-transfer, and attention performance. The results can establish a Roofline baseline and guide workload-specific optimization. ### Source excerpt Google's open-source TPU microbenchmark suite provides developers with granular performance metrics across Network, Compute, HBM, Host Transfer, and Attention components to validate real-world hardware capabilities. By leveraging these benchmarks to establish a Roofline model, engineers can accurately diagnose whether their machine learning workloads are compute-, memory-, or network-bound. This empirical baseline directly guides targeted software optimizations--such as kernel tuning, mesh sharding, and rematerialization--to maximize hardware utilization for large-scale model deployments. ## Driving Developer Excellence: Inside the Program Sprints DevFeed: [Driving Developer Excellence: Inside the Program Sprints]() Original publisher: [Read original article]() Author: Anant Nawalgaria; Eric Schmidt; Sokratis Kartakis; Aman Khan Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [AI Bots]() Tags: [agents](), [ai](), [ai-governance](), [developer-experience](), [devex](), [documentation](), [google-cloud](), [policy]() ### AI overview Google Cloud's Gemini Enterprise DevEx program tests developer workflows without internal shortcuts to find and resolve friction. This sprint focused on governed AI-agent deployment, covering identity provisioning, registry enrollment, gateway routing, policy enforcement, content safety, and auditable request verification. ### Source excerpt 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 on optimizing enterprise AI governance, including refining setup prerequisites, securing extension configurations, and clarifying policy enforcement mechanics to ensure a smoother, more reliable deployment. Developers can now leverage updated documentation and standardized code samples to improve their experience with Agent Gateway and Semantic Governance configurations. ## Decoding cosmic signals with deep learning and Keras DevFeed: [Decoding cosmic signals with deep learning and Keras]() Original publisher: [Read original article]() Author: Yufeng Guo; Jonas Glombitza, PhD Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Deep learning](), [Keras](), [data]() Tags: [analysis](), [blog-post](), [data](), [deep-learning](), [keras](), [particle-physics](), [physics](), [research]() ### AI overview The article explains how deep learning and Keras can help analyze the enormous, complex datasets produced by astroparticle-physics observatories. These methods may improve instrument sensitivity, reveal hidden patterns, and identify anomalies in signals from cosmic messengers such as photons, neutrinos, and cosmic rays. ### Source excerpt Astroparticle physics sits at the exciting intersection of astrophysics and particle physics and stu... ## The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents DevFeed: [The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents]() Original publisher: [Read original article]() Author: Taylor Mullen; Christian Gunderman Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [AI-assisted coding](), [ai observability]() Tags: [ai-agents](), [ai-coding](), [benchmarks](), [engineering](), [evaluation]() ### AI overview The article recommends behavioral evaluations for AI coding agents: fast checks of discrete actions that complement broad end-to-end benchmarks. These evaluations help teams diagnose changes, iterate on prompts and tools, and prevent regressions during model upgrades. ### Source excerpt 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, developers should adopt behavioral evaluations--fast, local, unit-style tests that assert on discrete intermediate actions, such as verifying specific tool calls or file modifications rather than final string equality. By building these inexpensive micro-checks alongside macro benchmarks, engineering teams can confidently iterate on system prompts and upgrade models without the risk of regressions. ## Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA DevFeed: [Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA]() Original publisher: [Read original article]() Author: Alex Martin; Dima Melnyk Published: 2026-09-12T11:04:33.891311Z Content type: release Language: en Sources: [Google Developers Blog]() Topics: [ai observability](), [SDKs](), [ci]() Tags: [agent](), [agents](), [ci](), [cli](), [development](), [enterprise](), [evaluation](), [experiments](), [gemini](), [llm](), [metrics](), [model](), [platform](), [production](), [telemetry](), [testing](), [traces]() ### AI overview Gemini Enterprise Agent Platform's evaluation service is generally available. It provides consistent evaluation of agents and models across local experiments and production traffic, with pre-built metrics, adaptive rubrics, custom metrics, simulators, and workflow integrations. ### Source excerpt Agent Platform's evaluation service is now generally available, providing developers with a unified engine to measure agent quality consistently across local development experiments and live production traffic. You can evaluate agents using over 20 pre-built metrics, DeepMind-backed adaptive rubrics, or custom code-based and LLM-as-a-judge metrics stored in a centralized, versioned registry. The service integrates directly into existing workflows via the Agent Platform SDK, agents-cli, and ADK, offering built-in user and environment simulators to automate complex multi-turn testing and streamline CI pipelines. ## Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond DevFeed: [Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond]() Original publisher: [Read original article]() Author: Guillaume Laforge Published: 2026-09-12T11:04:33.891311Z Content type: release Language: en Sources: [Google Developers Blog]() Topics: [Artificial Intelligence](), [Kotlin](), [AI Development](), [Android](), [Kotlin Multiplatform](), [multiplatform](), [Orchestration](), [Google](), [Persistence](), [Agent Skill](), [LiteRT](), [Cloud]() Tags: [agent-skill](), [agents](), [ai](), [ai-agent](), [ai-agents](), [android](), [building](), [database](), [development-kit](), [firebase](), [incident](), [kotlin](), [multiplatform](), [orchestration](), [persistence](), [production]() ### AI overview Google announces the 1.0 general availability release of the Agent Development Kit (ADK) for Kotlin, a production-ready toolkit for building multi-agent applications with Kotlin, Java, and Android. Built on Kotlin Multiplatform, it provides feature parity with the ADK 1.0 Core and adds Android-first extensions for on-device agents with LiteRT-LM and ML Kit, hybrid cloud workflows through Firebase AI Logic, and state persistence with Room and AppSearch. The release also includes type-safe, compile-time function calling through KSP and declarative agent skills. ### Source excerpt 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), the framework leverages Kotlin Symbol Processing (KSP) for zero-reflection, type-safe function calling, alongside advanced orchestration capabilities like human-in-the-loop workflows and context compaction. Additionally, the release introduces a robust suite of Android-first extensions, allowing mobile developers to integrate local models via LiteRT-LM, cloud reasoning through Firebase AI, session persistence using Room, and semantic memory powered by AppSearch. ## Scaling real-time AI agents with session-aware load balancing DevFeed: [Scaling real-time AI agents with session-aware load balancing]() Original publisher: [Read original article]() Author: Simerus Mahesh Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [real-time](), [Artificial Intelligence](), [Streaming](), [Server](), [gRPC](), [WebSocket](), [cpu](), [Concurrent Programming]() Tags: [ai-agents](), [concurrent](), [cpu](), [real-time](), [routing](), [server](), [streaming]() ### AI overview This article explains why real-time AI agents require session-aware load balancing. Long-lived, stateful bidirectional streams make request rates and CPU utilization insufficient measures of backend capacity. The proposed approach tracks active sessions at the application level and combines session counts with CPU metrics to distribute traffic and avoid bottlenecks. ### Source excerpt Real-time AI agents break traditional request-response load balancing paradigms because they rely on long-lived, stateful bidirectional streams that obscure true server capacity. To solve this, developers must implement application-level session tracking directly within the runtime to accurately measure the committed concurrent workload of active conversations. By feeding these precise session counts alongside standard CPU utilization metrics into a hybrid routing algorithm, infrastructure can effectively distribute stateful AI traffic and prevent individual backend bottlenecks.