I have been experimenting with Claude Code and Google Antigravity extensively as part of my development workflow. I have used them to build an enterprise-grade tool. I would not credit the tools alone, though. There was plenty of human input involved throughout the process. Even so, working with them made me realize just how capable these tools have become.

That became even more apparent recently when I gave Claude Code and Google Antigravity an entire project. I wanted to build something useful, not just run another coding tool benchmark. The project was a resume builder microsite for a friend who was actively looking for a job. He already had a solid resume, but he needed a way to edit it properly and create versions tailored to different roles. A single resume rarely works across every application because each job requires a slightly different emphasis.

I wanted the microsite to provide templates, editable sections, and role-specific versions without turning the process into a manual copy-and-paste exercise. I ran Claude Code inside Google Antigravity through the terminal while also using Antigravity's agents to plan and structure the project. That combination finished the build almost twice as fast as my usual VS Code workflow.

Using Antigravity for planning

And Claude Code for execution

My plan was to use both Google Antigravity and Claude Code to my advantage. I started by giving Antigravity a prompt to begin project planning. The plan is for Antigravity to break the project into milestones, generate the architecture, and define the database schema. While this particular project did not require APIs, if yours does, you can create API specs and ask it to identify risks and edge cases. Finally, you can ask it to create implementation tasks.

This helped get things moving in minutes. I then asked Claude Code to start executing the plan. The best way is to give it executable tasks and milestones generated by Antigravity. For my resume builder, that meant tasks such as building the template system, creating editable sections, and implementing PDF exports. You ask Claude to start working on milestone one and complete the milestones generated by Antigravity. Claude Code performs much better when working on a specific task instead of a prompt like "build everything."

If you want real speed, let Claude Code operate on the repository. Claude Code can create files for you. It can edit existing files, run tests, fix lint errors, and search the entire repository. VS Code, on the other hand, asks you to jump between tabs manually. For example, while working on the resume builder, I could ask Claude Code to update every template to support a new field or modify the PDF export flow. It could work through dozens of files without opening them and get the task done.

Making use of both tools

Both tools have their own strengths

Once you have a reasonable output from Claude Code, you can use Antigravity as a second opinion. You can ask Claude Code to do something, then ask Antigravity to review it, and then feed the review back into Claude Code. Antigravity can identify edge cases, usability issues, or architectural problems. Once those issues are highlighted, you can prompt Claude Code to implement the changes.

While my resume builder project did not require both tools to work over time, if you are working on something much larger, you can also split the work into parallel streams. Instead of giving Claude Code a prompt to build the backend, waiting, then asking it to build the frontend, waiting again, and asking it to write documentation, you could run multiple sessions. In my case, Session A could focus on building authentication, while Session B could focus on the template editor. At the same time, Session C could handle PDF generation or documentation. The idea is to use multiple agents at once so that different parts of the project can move forward in parallel.

I have also found it useful to divide implementation and reasoning between the two tools. I have found Antigravity to be better with architecture planning, design decisions, and reviewing work in general. Claude Code is brilliant at writing code, refactoring code, running commands, and creating tests, so you could essentially divide these functions between the tools to get a much better output.

VS Code feels behind for agentic development

It’s lagging far behind at this point

VS Code still has a massive ecosystem, and I understand why developers use it. It gives you extensions, debugging, Git support, and almost every workflow a developer expects. Microsoft has also recently added AI features and Copilot-based agent workflows to VS Code.

But my issue with VS Code comes from how the workflow feels during a full project. You can add extensions, open terminals, install Copilot, configure tools, and build a decent setup. That setup still depends on you stitching the workflow together.

VS Code also carries baggage because the official product differs from the Code OSS repository. Microsoft develops Code OSS under the MIT license, but Visual Studio Code ships as a Microsoft product with Microsoft-specific customizations under a traditional Microsoft product license. It also explains why tools like VSCodium exist for people who want cleaner open-source binaries. Telemetry also adds to my frustration with VS Code.

Other tools now feel more aggressive about the future of coding. Cursor, Antigravity, Zed, Warp, and similar tools focus more directly on agent workflows. VS Code still gives you most features through extensions and integrations, but that does not automatically make it the fastest workflow.

Using multiple agents is the way to go

We have reached a point where using a single agent for everything is probably no longer the best approach. You can use multiple agents on the same project and get much more value out of them. I also found this to be cheaper than running everything through one agent. It lets you use cheaper models for simpler tasks while saving the more capable models for work that actually needs them.