Connie's Programming Journey

Reading Time: 11 minutesObservability at Scale: Mastering ADK Callbacks for Cost, Latency, and Auditability AI orchestrators receive significant attention; however, when deployments become latent and costly, developers often overlook a critical capability: ADK callback hooks. The design patterns and best practices of callback hooks enable developers to refactor logic from agents to callback hooks to add observability, reduce … Read more

Reading Time: 8 minutesIn the world of AI orchestration, it’s tempting to use a Large Language Model (LLM) for every step of a workflow. However, as applications scale, the “LLM-first” approach can introduce unnecessary latency, costs, and unpredictability. The Google Agent Development Kit (ADK) provides a powerful alternative: the BaseAgent. This post explores how to create a custom, … Read more

Reading Time: 12 minutesThe Use Case: Scaling Content to Global Tech Communities When content writers write English blog posts, they often want to distribute them to different tech communities to share knowledge, increase impact, and reach. However, many readers in these communities do not read, write, or speak English. When the blog post is posted in these localized, … Read more

Reading Time: 10 minutesThe Pain Point: The Invisible World of the “Granular” Masterpiece When a postcard miniaturizes a traditional Chinese painting, the reduced scale obscures details. Consider a standard postcard depicting workers and horses pulling wagons in a crowded street during the Qing dynasty. Adults and children walk on a busy bridge while shops on both sides sell … Read more

Reading Time: 14 minutesTechnical writers and ESL professionals often rely on complex prompts to polish our work. However, as prompts grow into monolithic walls of text, they become brittle, hard to debug, and expensive to run. Modularity addresses this challenge. In this post, I transition from a single Custom Command to a modular, portable Gemini CLI extension implemented … Read more

Reading Time: 13 minutesRetrieving accurate, up-to-date sports statistics with LLMs is notoriously difficult due to hallucinations and outdated training data. In this post, I will explore retrieving the Premier League 2025/2026 Player statistics using the Gemini 3 Flash Preview model, URL Context, Grounding with Google Search, and structured output. I will describe lessons learned and how I extracted … Read more

Reading Time: 8 minutesIn this blog post, I will explore the enhanced inputs in the Gemini API and how they simplify my Colab demo. I will outline the recent updates to the Gemini API, walk through the legacy implementation, and finally demonstrate how to replace a complex utility function with just two lines of code. Introduction As of … Read more

Reading Time: 5 minutesIn this project, I stepped out of my comfort zone to upgrade from Gemini 2.5 to Gemini 3 in Vertex AI. The goal was to build an intelligent Image Alt Text Generator that goes beyond simple description and hashtags. By leveraging Gemini 3.0 (Pro Preview), this application analyzes an image to generate alternate text, hashtags, … Read more

Reading Time: 5 minutesOn day 29, I add a loader (A 

) to show that the page is loading the data. It is incredibly easy in Angular 20 because it is a built-in functionality in httpResource. In Vue 3, I installed vueuse and applied the useFetch composable to initiate the network requests. In SvelteKit, a loader can be implemented with the navigating object in $app/state. It … Read more

Reading Time: 4 minutesOn day 28, I use the userId of a post to call the users endpoint to retrieve the user name. In Vue 3, I created another composable to return a user Object with a name property. In Angular 20, it is a User service that uses the experimental httpResource to retrieve a user when the post is updated. In SvelteKit, I … Read more