---
title: "Google"
description: "Global technology leader developing innovative software, cloud services, and AI solutions across mobile, web, and enterprise platforms"
---

# Google
> Global technology leader developing innovative software, cloud services, and AI solutions across mobile, web, and enterprise platforms

## Articles

### [Announcing DPoP Support for Google OAuth: Securing Refresh Tokens](https://yomu.fyi/post/announcing-dpop-support-for-google-oauth-securing-refresh-tokens.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sergei Akulich, Brian Daugherty
- Published: Oct 15, 2026
- Type: Announcement

Google announced DPoP (RFC 9449) support for its OAuth platform, specifically binding refresh tokens to a client-generated asymmetric keypair to neutralize token theft and replay attacks from Infostealer malware and AiTM threats. Access tokens remain standard bearer tokens to avoid the per-request asymmetric cryptographic verification overhead on high-QPS APIs like Gmail and Drive, delivering a pragmatic tradeoff between security and performance. The implementation follows RFC 9700 best practices for sender-constrained refresh tokens and is recommended for Backend-for-Frontend (BFF) and Token-Mediating Backend architectures. DPoP operates at the HTTP header level, making it resilient in multi-hop environments such as Model Context Protocol (MCP) agent chains, though multi-agent delegation requires Google Cloud Secure Token Service (STS) to preserve key isolation. Complementary protections against cookie theft are offered by Device Bound Session Credentials (DBSC), which cryptographically binds browser session cookies to device hardware for a defense-in-depth strategy.


### [Three layers, one repo: a tour of google/adk-recipes](https://yomu.fyi/post/three-layers-one-repo-a-tour-of-google-adk-recipes.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Pier Paolo Ippolito, Shahin Saadati
- Published: Oct 15, 2026
- Type: Explainer

The google/adk-recipes repository serves as the single source of truth for ADK content across Google Cloud’s Agent Platform, including the Agents CLI, Agent Garden, and Gemini Enterprise app. It is organized into three top-level folders: core/ with reference patterns curated by the Agents CLI and DevRel teams, plugins/ with installable vertical skills packaged as Plugin Recipes conforming to the Agent Plugins v1.0.0 spec, and contrib/ with end-to-end deployable services in five languages. Every recipe ships a validated manifest.yaml and an AGENTS.md written primarily for AI coding assistants, and CI enforces the standards on every pull request. The core/ layer features Horizon, a reference harness for long-horizon memory agents that handles cross-session memory, per-user sandboxing, guardrails, and multi-step task orchestration. The retail Plugin Recipe includes product-search and virtual-tryon skills using Vector Search 2.0 and Gemini models, with deployable counterparts in contrib/ that can be surfaced on five deployment personas.


### [Evaluating AI agents: moving past the vibe check](https://yomu.fyi/post/evaluating-ai-agents-moving-past-the-vibe-check.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Hugo Selbie, Dani Zamora, Jesse Carah
- Published: Oct 15, 2026
- Type: Problem & solution

Manual vibe checks for AI agents miss silent failures like retry loops, token waste, and hallucinated parameters while plausible final answers mask them. The post outlines a structured evaluation pipeline using the open-source agent-eval toolkit, starting with critical user journeys (CUJs) that define success in concrete, testable clauses. Synthetic user simulations (via ADK) generate multi-turn scenarios for initial trace collection, which developers grade with a ‘red pen’ before automating checks. Four layers of verification are recommended: unit tests, deterministic metrics, LLM-as-a-judge with boolean rubrics (avoiding unreliable 1-to-5 scales), and integration tests, all standardized on OpenInference/OpenTelemetry traces. The rollout progresses from Day 0 manual review through Day 1 automated checks to Day 2 CI/CD gates and shared dashboards, with real production traces fed back into the golden dataset.


### [Optimizing a 200,000-line Python codebase overnight with Gemini 4 Argon](https://yomu.fyi/post/optimizing-a-200-000-line-python-codebase-overnight-with-gemini-4-argo.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: George Weale, Bo Yang, Andrew Biernat
- Published: Oct 13, 2026
- Type: Problem & solution

Google tested Gemini 4 Argon on google/adk-python, a 205,000-line Python framework with 800 source files and 17,000 unit tests. The model ran unattended for 11 hours, guided by a /goal prompt and .agents/skills rulefiles that encoded maintainer conventions. Argon first wrote a benchmark script, spent 70 minutes measuring before editing code, and proposed six optimizations across 32 files; two shipped after human code review. The shipped changes cut in-memory session prep time by about 40% in long sessions and sped up cold package imports by 21% by filtering events before copying and using lazy module accessors. The other four proposals were rejected for relying on fragile state, private library internals, or synthetic-only gains, illustrating a division of labor where the agent explores and the maintainer subtracts.


### [Gemini 4 Argon for Robotics](https://yomu.fyi/post/gemini-4-argon-for-robotics.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Kanishka Rao
- Published: Oct 13, 2026
- Type: Announcement

Gemini 4 Argon is a new model that achieves a step change in physical understanding, code generation, and visual-semantic reasoning for robotics. It scores 87% on the Embodied Reasoning (ERQA) benchmark using pure reasoning, outperforming other frontier models. The model can be applied across the entire robotics lifecycle, including robot control, Real2Sim reconstruction, physical understanding, and research self-improvement. Examples include controlling a Spot quadruped to practice foot-pedal trash bin disposal in MuJoCo before executing, zero-shot control of a robotic arm, steering a video world model to rearrange Scrabble tiles, reconstructing simulation twins from robot camera feeds or hand-drawn sketches, and reproducing robotics papers as self-contained MuJoCo WebAssembly browser labs with a single prompt. Argon also performs agentic multimodal hindsight labeling for dexterity understanding and dense value functions, and can self-improve by diagnosing failures and optimizing speed, bridging coding, visual perception, physics simulation, and embodied control toward physical AGI.


### [The Outer Loop, Insights First: An Ambient Quality Agent That Diagnoses Your Production Agent](https://yomu.fyi/post/the-outer-loop-insights-first-an-ambient-quality-agent-that-diagnoses.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Dima Melnyk, Elia Secchi
- Published: Oct 8, 2026
- Type: Announcement

AI agents in production often pass health checks while silently failing at real tasks, such as confirming a seat without checking availability. Google and ADK released AQuA (Ambient Quality Agent), a sidecar system that continuously sweeps production agent trajectories from Cloud Trace, Cloud Logging, or BigQuery outside the request path. AQuA samples up to 1,000 recent sessions, grades each against a developer-defined goal and a nine-point breakdown checklist using a single-pass judge (or optional Gemini AutoRaters), clusters failures by mechanism, verifies clusters with a second model, and tracks them in BigQuery. Developers can trigger root-cause analysis that reads failing trajectories alongside the immutable deploy-time source snapshot, citing exact code lines without auto-applying edits. The system runs unattended, sweeps after each deploy or on demand, and produces verified failure clusters to feed back into the inner development loop, solving quality degradation that standard health checks miss.


### [Supercharge your development with the Google Developer Knowledge API ecosystem](https://yomu.fyi/post/supercharge-your-development-with-the-google-developer-knowledge-api-e.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Christina Gonzalez
- Published: Oct 7, 2026
- Type: Announcement

The Developer Knowledge API is Google’s official, programmatic source for developer documentation across Google Cloud, Firebase, and Android. It replaces web-scraping with a structured API serving fresh Markdown-formatted documentation, offering semantic and keyword search, intelligent document chunking, and grounded Q&A. The ecosystem includes a gcloud CLI surface that integrates search and grounded Q&A into terminal environments without extra plugins. An agent skill uses the standard MCP integration to connect AI assistants such as Claude Code, Cursor, and GitHub Copilot to up-to-date documentation. Multi-language client libraries enable programmatic access with features like BatchGetDocuments for retrieving up to 20 documents in one call.


### [EmbeddingGemma 2: The Developer Guide](https://yomu.fyi/post/embeddinggemma-2-the-developer-guide.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Maarten Grootendorst, Ian Ballantyne
- Published: Oct 6, 2026
- Type: Tutorial

Modern search and RAG applications need to work across diverse content types, but finding models with strong retrieval accuracy and low latency without massive compute is challenging. EmbeddingGemma 2 is a compact open model under Apache 2.0, based on Gemma 4, that maps text, code, images, video, and audio into a unified 768-dimensional space with a modular architecture scaling from 270M to 740M parameters. Key capabilities include native multimodal retrieval, superior code understanding, modular memory footprint, and flexible vector storage via Matryoshka Representation Learning enabling dynamic truncation from 768 to 128 dimensions. Under the hood, it uses modular encoders—a text/code decoder, vision encoder, and audio encoder—that project into a shared space and can be loaded selectively to minimize memory. The developer guide demonstrates how to use sentence-transformers to load the model, embed with task prompts, handle media inputs, truncate dimensions, and choose configurations based on storage and recall needs.


### [Bring multimodal semantic search to the edge with EmbeddingGemma 2](https://yomu.fyi/post/bring-multimodal-semantic-search-to-the-edge-with-embeddinggemma-2.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Google AI Edge Team, Android ML Team
- Published: Oct 6, 2026
- Type: Announcement

Google DeepMind launched EmbeddingGemma 2, an open-weight multimodal embedding model that maps text, images, video frames, and audio into a single vector space. Designed for local, privacy-first applications, it runs on as little as ~191MB active RAM for text-only weights and ~567MB for the full multimodal model on a Google Pixel 11 Pro. The model powers two new interactive showcases in Google AI Edge Gallery: Instant Media Search, which retrieves local images and videos via natural language or example images, and Video Moments Finder, which locates specific visual moments in local video files without transcribing audio. Google AI Edge Foresight for Mac uses EmbeddingGemma 2 alongside Gemma 4 for local meeting note-taking, cross-modal retrieval, and live question answering. Optimizations include modular encoders, quantization-aware training to INT4/INT8, and Matryoshka Representation Learning slicing to reduce storage footprints by up to 8x.


### [Turn your REST APIs into MCP tools with Google Cloud API Gateway](https://yomu.fyi/post/turn-your-rest-apis-into-mcp-tools-with-google-cloud-api-gateway.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sanjay Pujare, Paul Howell
- Published: Sep 24, 2026
- Type: Announcement

Most enterprise REST APIs are invisible to AI agents, forcing teams to run separate MCP servers that duplicate their existing gateway logic. Google Cloud API Gateway in Public Preview solves this by acting as a remote MCP server — annotate the OpenAPI 3.0.x/3.1.x spec with x-google-api-management.mcp and deploy it with no extra infrastructure. The gateway accepts MCP JSON-RPC requests on a single /mcp endpoint, transcodes tools/call into the corresponding REST call, runs it through existing policies, and returns the response as an MCP result. Authentication via JWT or API key works unchanged for REST operations; tools/list is unauthenticated by default and requires JWT in production for security. With no separate server to operate, teams in Public Preview can expose up to 1,000 tools per gateway that support existing authentication and quota, and the MCP server is automatically discoverable via API hub and Agent Registry.


### [Reproducing OLMo 3 7B Pre-training in MaxText: case study of large scale training on TPUs](https://yomu.fyi/post/reproducing-olmo-3-7b-pre-training-in-maxtext-case-study-of-large-scal.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Gagik Amirkhanyan, Ran Ran, Aireen Mei, Matt Davidow, TPU Inference Software Engineering Team, Google Cloud, AI2 Team
- Published: Sep 24, 2026
- Type: Problem & solution

The post describes the reproduction of AI2’s OLMo 3 7B pre-training using MaxText on Google Cloud TPUs, covering both stages, matching the reference loss curve and held-out metrics. PyTorch weights were converted to JAX with logit parity, KL divergence 1.5e-3 and 98.75% top-1 agreement, and held-out evaluations caught a data loader bug that made incorrect gains appear. The run demonstrated reliability via exact checkpoint-resume with zero loss delta, resilience to a 75% capacity loss via resize with 1% throughput preservation, and seamless TPU generation change. Performance optimizations achieved 44.5% MFU on Ironwood, and head reshaping from 32 heads by 128 to 16 by 256 yielded 12.4% faster throughput at identical parameters and FLOPs. The post emphasizes that faithful reproduction requires verification on generalization metrics and provides instructions for readers to reproduce the run with open sourced code.


### [Introducing Support for Local AI Models in the Antigravity SDK](https://yomu.fyi/post/introducing-support-for-local-ai-models-in-the-antigravity-sdk.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sachin Kotwani, Taylor Mullen
- Published: Sep 23, 2026
- Type: Announcement

The Antigravity SDK now supports local AI models, starting with Gemma 4 26B A4B via Google AI Edge’s LiteRT, enabling offline agentic assistance on local GPU and RAM with a recommended machine of 24GB VRAM or unified memory. Local execution eliminates API costs and rate limits while keeping code and requests on-device, offering privacy and offline resiliency. The SDK supports hybrid workflows where a cloud model like Gemini 3.8 Flash plans while local Gemma 4 instances execute, as in a code auditing task where 97.2% of tokens (3,322 of 3,417) ran locally. A built-in example generates a live-updating CLI resource monitor using psutil and rich from a single prompt, with the agent autonomously writing the script, creating requirements.txt, and testing the code entirely offline. The SDK also supports any OpenAI-compatible server like Ollama, LM Studio, or vLLM via LocalOpenAIAgentConfig without changing agent orchestration.


### [Why client SDK generation belongs in the open](https://yomu.fyi/post/why-client-sdk-generation-belongs-in-the-open.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Amir Hardon, Philipp Schmid
- Published: Sep 17, 2026
- Type: Announcement

Google describes partnering with Speakeasy to open-source the OpenAPI code-generation suite used for new SDKs for its Interactions, Agents, and Webhooks APIs. The change follows the May 2026 shutdown of a proprietary SDK-generation provider, which exposed platform risk while Google was preparing the Interactions API for general availability; migration prioritized avoiding breaking changes and preserving type definitions, strict error hierarchies, and streaming behavior. The AGPLv3 suite generates statically typed libraries for Python, TypeScript, Go, Java, C#, PHP, and Ruby, plus standalone agent-native CLI binaries and documentation MCP servers built from OpenAPI specifications and Markdown. Google says a deterministic generator paired with Antigravity AI agents now supports its pipeline across six targets, including three released SDKs, with roughly one engineer maintaining it, while generated code can remain under a chosen license such as MIT or Apache 2.0.


### [Agent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform](https://yomu.fyi/post/agent-anomaly-detection-now-in-private-preview-on-the-gemini-enterpris.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Achuth Narayan Rajagopal
- Published: Sep 16, 2026
- Type: Announcement

Agent Anomaly Detection is a reasoning-based oversight and audit layer for autonomous agents on the Gemini Enterprise Agent Platform, now in Private Preview. It analyzes existing reasoning traces, tool calls, execution flow, logs, and OpenTelemetry traces asynchronously, using a lightweight statistical pass followed by deeper LLM-based examination of flagged sessions. Its initial detectors cover tool misuse, identity and privilege abuse, cascading failures, rogue agents, resource exhaustion, and token usage escalation, with findings assigned severity, probability, explanations, and recommended fixes and surfaced in Security Command Center. In the Inventory Agent example, repeated large-batch, offset-jumping list\_inventory calls are classified as systematic scraping and produce a Critical resource-exhaustion finding at 95% probability; an API can let ADK callbacks or plugins block later actions. Custom business logic detectors are described as coming soon.


### [Build zero-trust AI agents that judge intent, not just syntax](https://yomu.fyi/post/build-zero-trust-ai-agents-that-judge-intent-not-just-syntax.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Eric Dong, Shubham Saboo
- Published: Sep 15, 2026
- Type: Explainer

Part 2 of the Zero-trust Agents series addresses attacks that deterministic, build-time checks cannot recognize when syntax remains valid. It keeps the Customer Support and Returns Agent, which reads orders, calculates restocking fees in Agent Sandbox, and commits payouts through an issue\_refund tool signed with a hardware-backed Cloud KMS key, then moves enforcement to Gemini Enterprise Agent Platform. Agent Gateway applies three runtime controls: Model Armor screens prompts and responses, Semantic Governance Policies evaluates proposed tool calls against intent, history, and business rules, and Agent Anomaly Detection analyzes behavior across a session. The examples cover prompt injection, a non-refundable digital-license refund, and a multi-turn refund drain; detected anomalies can trigger a new policy that blocks subsequent calls without redeploying the agent.


### [Autonomous LLM post-training with Tunix on TPUs](https://yomu.fyi/post/autonomous-llm-post-training-with-tunix-on-tpus.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Wei Wei
- Published: Sep 11, 2026
- Type: Benchmark

autofinetune applies autonomous research loops to LLM post-training, covering supervised fine-tuning (SFT) and reinforcement learning with GRPO through Tunix, Gemma, Cloud TPUs, Antigravity CLI, and Gemini Flash 3.7. A human defines the arena in program.md and supplies a self-contained run.py, while an agent edits hyperparameters, launches jobs, evaluates a target metric, keeps winning Git commits, reverts regressions, and logs results in results.tsv. On FunctionGemma 270M with google/mobile-actions, 20 Cloud TPU v5e-1 experiments tested LoRA settings, optimization choices, schedules, batch size, and seeds without changing the dataset, epochs, or architecture. A second study used Gemma 3 1B, GSM8K, and Cloud TPU v6e-1 for 40 GRPO experiments over two to three days, improving the combined numerical-and-format reward by about 10%.


### [The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents](https://yomu.fyi/post/the-anatomy-of-harness-engineering-how-to-evaluate-iterate-and-guard-a.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Taylor Mullen, Christian Gunderman
- Published: Sep 9, 2026
- Type: Explainer

The post argues that end-to-end benchmarks such as Terminal-Bench and DeepSWE show overall agent performance but rarely explain why behavior changes. It presents behavioral evaluations as fast, deterministic, unit-style checks of observable intermediate actions, such as asking clarifying questions, running validators, or invoking web search instead of guessing. The proposed workflow starts with a recent failure, uses strict milestone assertions for simple tasks and flexible outcome-based or LLM-as-a-judge checks for complex tasks, then runs batch evaluations to track aggregate pass rates despite model nondeterminism. These evaluations are positioned for the second phase of development, after an agent can dogfood its codebase, and as complementary to macro benchmarks: behavioral tests enable prompt, tool-schema, and model iteration while guarding against regressions.


### [Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond](https://yomu.fyi/post/announcing-adk-for-kotlin-1-0-building-production-ready-ai-agents-in-k.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Guillaume Laforge
- Published: Sep 9, 2026
- Type: Announcement

ADK for Kotlin 1.0 is announced as a general availability release for building AI agents with Kotlin across Android, JVM server applications, and Java-integrated systems. The release targets a production-ready toolkit while preserving an idiomatic, lightweight, composable approach, and it reaches feature parity with ADK 1.0 Core, including hierarchical agents, context compaction, human-in-the-loop confirmation, resumable sessions, annotated tools, and Java interoperability. A Kotlin Multiplatform core stays agnostic to model backends, session providers, and memory systems, while Android extensions support LiteRT-LM, ML Kit (beta), Firebase AI Logic, Room, AppSearch, and file artifacts. The database incident example combines compile-time KSP-generated function schemas, suspend-capable @Tool functions, and dynamically loaded SKILL.md playbooks with progressive disclosure. The release provides 1.0.0 dependencies, documentation, a repository, and sample applications.


### [Driving Developer Excellence: Inside the Program Sprints](https://yomu.fyi/post/driving-developer-excellence-inside-the-program-sprints.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Anant Nawalgaria, Eric Schmidt, Sokratis Kartakis, Aman Khan
- Published: Sep 4, 2026
- Type: Announcement

Google Cloud’s Gemini Enterprise developer experience (DevEx) Program pressure-tests enterprise AI tooling by walking fixed developer workflows without internal credentials or shortcuts, logging friction, and working with engineering on fixes. This sprint focused on governance across five dependency-ordered workflows: provisioning an agent identity, registering it, binding it to an Agent Gateway, applying policies and content safety, and verifying an authorized request with auditable decisions. Changes included documenting the Identity-Aware Proxy API prerequisite, fail-closed Model Armor extension examples, automatic allowance for essential Google-managed APIs, Private Service Connect and private Cloud DNS guidance, corrected IAM CEL syntax, clearer bind-time versus runtime evaluation, and ready-made Logs Explorer queries. The program says fixes are rigorously re-verified through continued user-journey testing to improve reliability, security, and end-to-end usability.


### [4 engineering patterns behind the strongest AI Agents Challenge submissions](https://yomu.fyi/post/4-engineering-patterns-behind-the-strongest-ai-agents-challenge-submis.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sergio Villani
- Published: Sep 2, 2026
- Type: Explainer

The strongest submissions in the Google for Startups AI Agents Challenge repeatedly used four engineering patterns rather than merely labeling prompt chains as multi-agent systems. They exposed internally used tools through bidirectional MCP, used typed events and asyncio queues to let independent agents run concurrently, and routed fallback outputs through one shared validation function. They also reduced inference cost with tiered routing: regex or a cheap classifier handled simple intent before requests reached an expensive reasoning model, with one team reporting more than 40 percent handled before a real model call. The post argues these practices improve bounded data access, latency, resilience, and cost without requiring larger teams or newer models, and notes that Agent Development Kit and Agents CLI submissions showed them frequently.


[Older posts](https://yomu.fyi/company/google/page/2.md)