Explore

To serve the 397B-parameter Qwen 3.5 Mixture-of-Experts (MoE) model on Ironwood TPUs, engineers developed a modular JAX/Pallas optimization stack that achieved up to a 4.7x inference speedup for prefill-heavy workloads. The team bypassed severe hardware sharding constraints by deploying a hybrid Data Parallelism and Expert Parallelism (DP+EP) topology, paired with custom low-level communication fusions like a hierarchical reduce-scatter to optimize cross-device token routing. Finally, by executing hardware-aware custom kernels—such as Batched Ragged Page Attention and a fully-fused Gated DeltaNet (GDN) block—they successfully saturated HBM bandwidth and TensorCore MXUs to push system throughput near its theoretical roofline limits.

Google DevelopersJuly 24, 20261 min read

TechnologyRelease

Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration

The Agent Development Kit (ADK) for Go 2.0 has been released, introducing a first-class, graph-based workflow engine to help developers compose complex, multi-agent applications. This update adds built-in primitives for human-in-the-loop (HITL) orchestration, dynamic execution using plain Go code, and automated resilience features like exponential backoff retries. By unifying the execution model, both single-agent applications and intricate graphs now run on the same runtime, simplifying telemetry and state persistence.

Google DevelopersJuly 24, 20261 min read

WorldNews

How A2A is Building a World of Collaborative Agents

Celebrating the first anniversary of the Agent-to-Agent (A2A) protocol, this blog post highlights how the framework enables autonomous AI agents to securely collaborate and hand off tasks without the rigidity of traditional APIs. By delegating complex workflows to specialized peer agents, A2A prevents context pollution, ensures data privacy, and simplifies application design through modularity. To demonstrate this ecosystem in action, the post spotlights FoldRun—an agentic interface for life sciences that orchestrates complex protein structure predictions—alongside diverse A2A use cases spanning commerce, data streaming, DevOps, and telecommunications.

Google DevelopersJuly 24, 20261 min read

AIRelease

ML Development in VS Code with Google Cloud Power: Workbench Extension Now Available

The Google Cloud Workbench Notebooks extension for VS Code has officially launched, allowing developers to connect their local IDE to scalable, cloud-based Jupyter environments. This integration streamlines the machine learning lifecycle by eliminating context switching and providing direct access to high-performance Google Cloud infrastructure. To support transparency and community-driven innovation, the newly released extension is fully open-sourced and available on GitHub and the VS Code Marketplace.

Google DevelopersJuly 24, 20261 min read

TechnologyNews

A2UI + MCP Apps: Combining the best of declarative and custom agentic UIs

This post introduces three architectural patterns designed to integrate Model Context Protocol (MCP) Apps and Agent-to-User Interface (A2UI) to solve the tradeoff between highly custom iframe environments and native, declarative rendering. By combining these approaches, developers can serve native-feeling UIs directly over MCP servers, embed complex and stateful iframe apps securely inside declarative views, or inject generative UI components into legacy systems. Ultimately, these hybrid frameworks empower engineering teams to deliver secure, performant, and brand-consistent agentic user experiences tailored to their specific project constraints.

Google DevelopersJuly 24, 20261 min read

AINews

Building scalable AI agents with modular prompt transpilation

To resolve the scaling bottlenecks and runtime errors caused by monolithic system prompts, engineering teams should treat prompts as build artifacts by modularizing instructions into reusable templates. By running these modular "skill files" through a transpiler, developers can enforce static validation, catch missing dependencies at build time, and integrate prompt generation directly into their CI/CD pipelines. This deterministic approach prevents code drift and ultimately establishes a safe framework where agents can propose updates to their own logic via standard pull requests.

Google DevelopersJuly 24, 20261 min read

TechnologyNews

Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search

Google Cloud has partnered with Parallel Web Systems to natively integrate Parallel's search infrastructure as a web grounding provider on the Gemini Enterprise Agent Platform. This integration enables developers to anchor their AI agents in verifiable, real-time web results, significantly improving factual accuracy for complex enterprise workflows. Additionally, the partnership offers expanded architectural flexibility, allowing users to programmatically extract, permanently cache, and process web data alongside other large language models.

Google DevelopersJuly 24, 20261 min read

TechnologyNews

Measuring What Matters with Jules

AI coding agents are rapidly shifting from reactive assistants that complete tasks when prompted to ...

Google DevelopersJuly 24, 20261 min read

TechnologyNews

Announcing the Agentic Resource Discovery specification

An open specification for finding and verifying tools, skills, and agents across the web.Agents are ...

Google DevelopersJuly 24, 20261 min read

ProgrammingNews

Driving the Agent Quality Flywheel from Your Coding Agent

Building AI agents often leaves developers uncertain if prompt tweaks to fix single errors will accidentally cause widespread regressions in production. To bridge this gap, Google has introduced a new developer skill for coding agents that automates a five-stage evaluation flywheel: preparing data, running inference, grading with adaptive AutoRaters, analyzing failure clusters, and executing targeted optimizations. Running continuously against production traffic or on-demand via synthetic scenarios, this tool allows developers to describe testing goals in plain language while an independent evaluation service safely validates and counts actual performance improvements.

Google DevelopersJuly 24, 20261 min read

TechnologyNews

We terminated a TPU mid-training and it recovered in seconds: Introduction to elastic training with MaxText

Distributed AI training is notoriously fragile because losing a single machine typically crashes the entire multi-node job, forcing a time-consuming, full-workload infrastructure restart. To address this, Google’s JAX ecosystem utilizes elastic training via Pathways, which converts a hardware failure into a catchable Python exception so the running process can survive. When an unplanned failure occurs, the system automatically replaces only the broken worker, restores the last viable checkpoint from Cloud Storage, and resumes training in place—minimizing total downtime to under two minutes without ever restarting the main controller process.

Google DevelopersJuly 24, 20261 min read

TechnologyRelease

Why we built ADK 2.0

Answering the questions of "why we built ADK 2.0". This explains the rationale, some of the features, and why a developer should consider upgrading. This will be published the day after ADK go 2.0 launches.

Google DevelopersJuly 24, 20261 min read

Most Read

Systems Engineering Playbook: Optimizing Qwen 3.5-397B MoE on Ironwood (TPU7x)

Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration

How A2A is Building a World of Collaborative Agents

ML Development in VS Code with Google Cloud Power: Workbench Extension Now Available

A2UI + MCP Apps: Combining the best of declarative and custom agentic UIs

Building scalable AI agents with modular prompt transpilation

Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search

Measuring What Matters with Jules

Announcing the Agentic Resource Discovery specification

Driving the Agent Quality Flywheel from Your Coding Agent

We terminated a TPU mid-training and it recovered in seconds: Introduction to elastic training with MaxText

Why we built ADK 2.0

Top Discussion

Filters