How far can I go with only Google AI Pro?

This was an experiment in designing an agentic workflow around Google tools. I deliberately limited the available services.

How did this begin?

At the end of 2025, I subscribed to Google AI Pro. I did not initially plan to use only the Google ecosystem. I also subscribed to ChatGPT and Cursor, knew them well, and found both useful.

After spending a lot of time with Antigravity, Gemini CLI, and Jules CLI, a question emerged: if I deliberately limited myself to Google AI Pro and stopped using ChatGPT and Cursor, how far could I actually go?

This was not an experiment in saving money. I wanted to find the real limit of Google's toolchain.

The real Antigravity problem was not product quality

To be clear, I do not think Antigravity is a bad product. I think it is still in beta. The practical limit was specific: the Antigravity quota for Gemini subscribers reset every five hours.

Light use barely touched the limit. Heavy use could still exhaust it during an afternoon of planning, revising requirements, and iterating. The constraint came from beta-stage IDE and agent-platform quotas, not from model capability.

Why not simply use Cursor or Claude Code?

I could, and I still do. But this experiment imposed a deliberate premise: if Google AI Pro were my only subscription, could I design a workflow that did not keep stopping at a quota wall? That constraint forced me to define the problem more clearly.

The problem was role assignment, not the tools

At first I made several predictable mistakes. I expected Antigravity IDE to do too much, asked Gemini CLI to write code and generate images, and wanted one agent to own the entire job.

The result was predictable too: quota disappeared quickly, the workflow became a black box, and failures had no obvious stopping point. The role boundaries had never been defined.

The design I chose

I redesigned the system as an IDE-first, repository-centered, closed-loop agent workflow and published it as the open-source starter repository keeponfirst-agentic-workflow-starter. It has one central rule: the IDE is for people; the CLI is for the system.

The actual workflow

1. The entry point is always the human-friendly Antigravity IDE. I describe a plan or task in natural language; the IDE is responsible only for planning and producing artifacts.

2. The repository is the central hub. Jules tasks, Gemini image prompts, records, logs, and notes all become files, making the process auditable, replayable, and resumable.

3. Jules handles heavy work, while Gemini CLI handles images only. Jules performs heavier development work in the cloud; Gemini CLI invokes Gemini's image-generation model. Clear roles reduce quota pressure.

4. Sidecar and agy form the automated handoff. Sidecar Watcher monitors Jules output and calls agy, the Antigravity CLI, after validation succeeds. If a result is ambiguous or risky, the flow stops and returns control to the IDE for a human decision.

What did the experiment show?

I would not claim that Gemini Pro alone can completely replace Claude Code. I can say that a deliberately designed workflow takes Google AI Pro much farther than I expected, while making it clearer which tasks are suitable for automation and which decisions must remain human.

What is still missing?

The workflow is one step short of a fully automated chain. I already have Sidecar Watcher monitoring Jules results, validating output format and completeness, and calling agy automatically.

The remaining limitation is that agy cannot yet inject the Jules result directly into an Antigravity conversation and execute the next step. It can launch Antigravity successfully, but the next instruction still has to be pasted or confirmed manually in the IDE.