AI in CI/CD

Google opens Gemini Enterprise Agent Ready as a free training path for agents in production

Google opens Gemini Enterprise Agent Ready as a free training path for agents in production

Google Cloud announced Gemini Enterprise Agent Ready (GEAR), a free training program, on August 6. Twelve skill badges and hands-on labs live on skills.google, and a companion contest called the All Things Agentic Hackathon runs on Devpost from August 3 to August 31 with $180,000 on offer in prizes, cash and credits. The launch post opens on the question, verbatim, "How do we actually get agents into production?".

For CI/CD teams the interesting choice is what Google decided to teach. Two named learning paths cover ground that pipeline owners tend to inherit once an agent leaves the notebook: "Build High-Performance Multi-Agent Systems" for orchestration, and "Govern and Secure Enterprise Agents" for the audit and blast-radius side. The material is delivered as skill badges rather than a proctored certification, so what a team walks away with is a checked box against a lab, not a graded exam.

The operator read

Free training is easy to like. It is also downstream of the harder problem, which is that the shape of "an agent in production" is not settled. A skill badge on securing enterprise agents does not decide whether your agent gets its own IAM identity or borrows the runner's, whether a tool call belongs behind a change window, or what a rollback looks like when the failing artifact is a prompt.

The courses will help engineers reason about those choices. They will not answer them. And because the material is Google-first, the reference model for orchestration and MCP integration reflects the Agent Development Kit's assumptions; teams running on Vertex-adjacent stacks will find the mapping straight, teams on other clouds less so.

The hackathon closes August 31. The badges stay up after.

Source: Google Cloud Blog (cloud.google.com)

Related
Security & supply chain

AlloyDB puts agents behind IAM groups so nobody has to share a database password again

Google's managed Postgres is adding IAM group authentication in preview, mapping Cloud Identity and Workforce Identity Federation groups to database roles. The point is not the passwordless slogan: it is that AI agents can finally carry a real end-user identity all the way to the row filter.

August 1, 2026
Platform engineering

Google's borderless lakehouse wires AWS, Databricks and Snowflake catalogs into one Iceberg REST surface

Google Cloud has pushed a preview of catalog federation that lets BigQuery and Managed Spark read AWS Glue, Databricks Unity Catalog and Snowflake Horizon through an Iceberg REST catalog, and shipped an open-source Data Agent Kit that hands the same tables to MCP-speaking agents. For pipeline teams the practical shift is that the protocol coding agents already talk now reaches a synchronised view of a multi-cloud data estate.

July 30, 2026
Platform engineering

Google's pitch: put Agent Substrate on top of GKE Agent Sandbox, and call it the AI-agent runtime

Two months after GKE Agent Sandbox went GA in May 2026, Google introduced a follow-up called Agent Substrate in the same post. The New Stack's read is that Google now wants Kubernetes to be the runtime for AI agents on the primitives GKE already uses for production services.

July 26, 2026

Turn this into your pipeline. Build it on Buddy.

Start free