Google Cloud Tech (@GoogleCloudTech)

Every software engineer knows how to write deterministic tests (assert add(2, 2) == 4). But traditional unit tests break down the moment an agent takes actions on our behalf....

Coding agents do heavy engineering work. The agent harness manages runtime state, sandbox execution, and prompt preparation. Providing static surrounding context on every turn creates a multi-turn scaling bottleneck, wastes tokens, and increases cost....

First came the LLM, then came the agent. And now we have the <b>harness</b>: essentially everything that surrounds an AI model, including the infrastructure and resources that increase its capabilities along with the guardrails to keep it from running amok. <b>by Roger Martinez, Cloud Developer Rel...

Every AI agent demo starts with a developer running raw generated code on their laptop, and every production deployment starts with a security team asking what happens when that code turns hostile....

How do you ship a software product with 0 lines of manually-written code?...

As smaller, cheaper models become more capable, striking the right balance between the costs, speed, and the desired outcomes is what <b><i>token engineering </i></b><i></i>is all about<b><i>. </i></b><i></i>Early on, token management was mostly about prompt compression, squeezing text to fit into t...

<a target="_blank" href="https://agent-plugins.org/" color="blue">Agent Plugins</a> is an open, vendor-neutral standard for packaging Agent Skills and the MCP servers they depend on into one portable folder that any compatible client can load. Google is joining the Technical Steering Committee as a ...

<b>By <a target="_blank" href="https://x.com/@Saboo_Shubham_" color="blue">@Saboo_Shubham_</a> and <a target="_blank" href="https://x.com/@secchi_elia" color="blue">@secchi_elia</a></b><a target="_blank" href="https://x.com/@secchi_elia" color="blue"></a>...