GeezerVison

The World Wide Web, restored to 800 pixels of glory.

GeezerVison is showing google.github.io — Agents CLI: build AI agents on Google Cloud that meet your production standards

Build AI agents that meet your production standards.

Agents CLI teaches your coding agent how to ship them on Google Cloud.

Paste into your coding agent: Follow google.github.io/agents-cli/setup.md to build my first agent

Read the docs→

Works with & more

The whole lifecycle, one CLI

Your coding agent builds until evals pass, ships to Google Cloud, and learns from production.

A working agent with one toolDevelopment guide →
4.71 of 5, above your 4.5 barEvaluation guide →
One command for Agent Runtime, Cloud Run or GKEDeployment guide →
One lookup_order call in 125 msCloud Trace guide →
Traces become eval cases, back to Evaluate

You:

Build a support agent that looks up orders.

Using the scaffold skill

Terminal

$ agents-cli create support-agent --agent adk_python --prototype
✅ Success! Your agent project is ready.

app/agent.py

def lookup_order(order_id: str) -> dict:
    return {"order_id": order_id, "status": "shipped"}

root_agent = Agent(
    name="support_agent",
    instruction="You answer questions about orders.",
    tools=[lookup_order],
)

Coding agent:

I created the project and wrote a lookup_order tool.

Ask your coding agent

You:

Evaluate it before we ship. Aim for 4.5 out of 5.

Using the eval skill

Terminal

$ agents-cli eval run
Step 1/2: eval generate
Step 2/2: eval grade
RESULT: PASS (custom_response_quality 4.71 >= 4.50)

Eval results

Mean score4.71 / 5Above your 4.5 bar

7 cases, 0 errors

Coding agent:

I added 4 order cases, 7 in total, and ran the evals.

Ask your coding agent

You:

Looks good. Deploy it to Cloud Run.

Using the deploy skill

Terminal

$ agents-cli scaffold enhance . --deployment-target cloud_run
✅ Enhancement complete!
$ agents-cli deploy --project my-project
✅ Deployed to Cloud Run.

Deploy target

Agent Runtime
Cloud Run
GKE

support-agentLive

Region us-east1 Revision support-agent-00001-k7d

Traffic100%

support-agent-482910375521.us-east1.run.app

Coding agent:

I added Cloud Run to the project and deployed it.

Ask your coding agent

You:

Is it calling the tool in production?

Using the observability skill

Terminal

$ agents-cli run --url https://support-agent-482910375521.us-east1.run.app --mode a2a "Where is order 1042?"

Trace explorer

00.6 s1.2 s1.8 s2.4 s

invoke_workflow support_agent2.41 s
invoke_agent support_agent2.40 s
call_llm970 ms
execute_tool lookup_order125 ms
call_llm1.28 s

Coding agent:

I sent a test request and opened its trace.

Ask your coding agent

Your rules, as extensions

An extension adds your checks and skills to agents-cli. Everyone keeps running the same agents-cli deploy.

Enforce a policy. Run your checks before every deploy.
Teach your coding agent. Add skills that spell out your rules.

How extensions work

Team Aagents-cli deploy
Team Bagents-cli deploy
CIagents-cli deploy

agents-cli-extension.yaml

commands:
  override:
    deploy:
      run: ["bash", "policy.sh"]

built-in deployCloud Run

Build agents with any framework

Pick your framework. The commands stay the same.

ADK
Python or Go, built in.
LangGraph
First-party template, built with LangChain.
Claude Agent SDK
First-party template, Claude on Gemini platform.
Your framework
Bring your own template.

Agents CLI

create
run
eval
infra
deploy

Agent Runtime
Cloud Run
GKE

Explore the docs

Getting started
Install Agents CLI and build a first agent.
Evaluation guide
Check tool calls, response quality and edge cases.
CLI reference
Every command and flag.
Skills reference
What each skill teaches your coding agent.

You are visitor 01402520 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.