Look at any builder's prompt history and you'll see a collection of highly specific, sometimes chaotic, one-off prompts. We use AI to debug a single error message, refactor a messy email, or generate a quick boilerplate. If you sit down with people who consistently ship high-quality work, you'll find something interesting. They aren't just improvising. They have a set of…
#developers practitioners
5 posts
Yesterday
10 Jun
Choosing your surface: Antigravity 2.0, Antigravity CLI, Antigravity IDE, or Antigravity SDK
Google CloudTL;DR: Antigravity 2.0: A desktop app to orchestrate multiple autonomous agents working in parallel across independent projects. Antigravity CLI: A terminal interface designed for command-line workflows and headless execution. Antigravity IDE: An editor for developers who want to write code directly alongside an agent. Antigravity SDK: A Python library for building and deploying your own custom agents that use the…
4 Jun
While building AI agents locally using Google’s Agent Development Kit (ADK) is an excellent way to prototype, production-ready agents require a robust, scalable infrastructure. For developers looking to move beyond simple instances and into the world of managed container orchestration, Google Kubernetes Engine (GKE) Autopilot offers the perfect balance of flexibility and ease of use. In this tutorial, I will…
2 Jun
Google Cloud Storage (GCS) is a foundational component of the modern agentic tech stack and the preferred home for unstructured data at scale. As enterprises deploy agents in production, the critical focus has shifted to turning data into context and building secure, standardized integrations to access context. This is the core of smart storage: making unstructured data inherently agent-ready by…
What happens when your workload fails in one region but you need access to service? This is a common case for availability and uptime. With recent enhancement to the Kubernetes ecosystem and capabilities like Dynamic Resource Allocation (DRA) and Inference Gateway. I decided to experiment with these capabilities in Google Cloud for a simple test using an AI inference workload.…