Uploaded July 2026 | Updated September 2026, 2 weeks ago
*Download Google Antigravity here.* → https://goo.gle/4fdw536
Are AI coding agents writing your features, or just writing your bugs?
A common complaint about AI development tools is that while they generate code quickly, they also create a massive amount of technical debt. Developers tend to over-rely on AI to write code, but don't use it enough to maintain, review, or test it.
In this video, YK Sugi walks through how to apply agentic workflows to an entire Software Development Lifecycle (SDLC) using *Google Antigravity*. Whether orchestrating multiple local agents in parallel through the Antigravity 2.0 command center, managing background subagents from the terminal-first Antigravity CLI, or prototyping custom behavior with the SDK, this platform is designed to help you build in the agent-first era.
Using real open source examples—like customizing a GitHub profile card—YK demonstrates how to speed up workflows and let agents do the heavy lifting, without losing control of your codebase.
*What we cover:*
* *Step 1:* Identifying and summarizing complex GitHub issues autonomously.
* *Step 2:* Collaborating with coding agents on system design and architecture.
* *Step 3:* Live implementation and flexible feature customization.
* *Step 4:* Deep, line-by-line PR reviews and automated testing.
Chapters:
00:00 - The problem: More AI code = more tech debt
00:44 - The agent-powered SDLC explained
01:23 - Step 1: Identifying & understanding issues
04:32 - Step 2: Designing the solution
06:53 - Step 3: Implementation & live demo
16:03 - Step 4: PR reviews & testing with Google Antigravity
🔗 *Resources Mentioned:*
* Google Antigravity: Experience liftoff with the next-gen agent platform (IDE, CLI, and SDK). Download it here. → https://goo.gle/4fdw536
Speaker: YK Sugi
Products Mentioned: Antigravity
*Download Google Antigravity here.* → https://goo.gle/4fdw536
Are AI coding agents writing your features, or just writing your bugs?
A common complaint about AI development tools is that while they generate code quickly, they also create a massive amount of technical debt. Developers tend to over-rely on AI to write code, but don't use it enough to maintain, review, or test it.
In this video, YK Sugi walks through how to apply agentic workflows to an entire Software Development Lifecycle (SDLC) using *Google Antigravity*. Whether orchestrating multiple local agents in parallel through the Antigravity 2.0 command center, managing background subagents from the terminal-first Antigravity CLI, or prototyping custom behavior with the SDK, this platform is designed to help you build in the agent-first era.
Using real open source examples—like customizing a GitHub profile card—YK demonstrates how to speed up workflows and let agents do the heavy lifting, without losing control of your codebase.
*What we cover:*
* *Step 1:* Identifying and summarizing complex GitHub issues autonomously.
* *Step 2:* Collaborating with coding agents on system design and architecture.
* *Step 3:* Live implementation and flexible feature customization.
* *Step 4:* Deep, line-by-line PR reviews and automated testing.
Chapters:
00:00 - The problem: More AI code = more tech debt
00:44 - The agent-powered SDLC explained
01:23 - Step 1: Identifying & understanding issues
04:32 - Step 2: Designing the solution
06:53 - Step 3: Implementation & live demo
16:03 - Step 4: PR reviews & testing with Google Antigravity
🔗 *Resources Mentioned:*
* Google Antigravity: Experience liftoff with the next-gen agent platform (IDE, CLI, and SDK). Download it here. → https://goo.gle/4fdw536
Speaker: YK Sugi
Products Mentioned: Antigravity
