A blog about software engineering, devops and web development
The Google Gemini LLM and the app have more features than you can see from the surface. In addition to generating images, audio, and music, you can also use Gemini for Deep Research, Guided Learning, and generating microapps on the fly with Gemini Canvas. In this post, you will learn how to use Deep Research, Guided Learning, and Canvas features in Gemini for software engineering tasks. Let's get…
Google Antigravity 2.0 has some very interesting features . One of them is the /goal command, which runs until the specified task is complete, without asking the user for intermediate input. The point here is to achieve the goal by iteratively and autonomously checking the output until it is accomplished. In this post, you will learn how to use /goal to build a last updated at feature on this blog…
Building a powerful AI agent locally with Google’s Agent Development Kit (ADK) is exciting, but how do you share it with the world or scale it for production? If you want to move beyond localhost without managing complex virtual machines or infrastructure, Google Cloud Run is the ultimate serverless solution with compelling reasons . In this step-by-step tutorial, you will learn how to deploy your…
Have you ever tried building an AI agent, only to get bogged down in massive, complex frameworks just to get a basic output? If you want a clean, code-first way to build and debug agents without the boilerplate, Google’s open-source Agent Development Kit (ADK) is what you need. In this post, you will learn how to set up the Python SDK, code your first Gemini-powered agent that checks facts, and…
After writing a couple of prompts to get a feature done with an LLM or a coding Agent like Claude Code (or Cursor), have you felt like there should be a more declarative way of doing this than taking turns with prompts? Instead of throwing prompts at a coding Agent, herding it/them to do the right job, and getting frustrated, wouldn’t it be better to have a plan of tasks to follow? This is where…
Google AI Studio has recently added an array of new features , calling it a new full-stack vibe-coding experience and vibe-coding-to-production. The new features include the ability to generate music, use Google Search data, use Google Maps data, add a database and auth, and add Gemini intelligence, to name a few. In this post, you will learn about adding a database and auth, which uses Google…
With AI doing some or most of the code writing (ahm! generation, if I may), being strong in the basics becomes even more crucial. If you have the word "engineer" in your job title, then knowing tools like Git and Docker has become inevitable. In this post, you will learn about the three main Git branching strategies and which one your team should choose for continuous delivery. This post will also…
You can run open models with other apps, such as Ollama . Docker Model Runner shines when you want to connect your application’s Docker container with an open model. It feels more native to Docker to define both the application and the model in a single Docker Compose file. You will learn to do so in this tutorial with a demo app built with Node.js that talks to Smollm2, defined in a Docker…
Docker has been the de facto containerization ecosystem for more than a decade now. It recently added a model runner that runs many open models locally via a docker model command. In this post, you will learn how to use the Docker model runner to run Smollm2 locally and interact with it. Let’s get started! Table of contents # Prerequisites Running Smollm2 with Docker Model Runner Pull a model with…
This will be the seventh year I have written a recap or “wrap” of the year that has passed. I started writing these in 2019 , and I have continued writing them since then. In this one, I will reflect on some of the crucial professional accomplishments I achieved in 2025. Fasten your seatbelts! Table of contents # Highlights Public speaking in 2025 Blog posts in 2025 Most viewed blog posts of 2025…
Wouldn’t it be great if you had an on-demand experienced software engineer interviewer who could take a technical interview whenever and wherever you wanted? Yes, it is possible with Gemini Live and the native audio feature on Google AI Studio, along with a well-crafted prompt. The best part is that it's free. Let’s get started! Table of contents # Gemini Multimodal capabilities Gemini Live Native…
You can make practical and fun apps using Gemini 3 on Google AI Studio for free. In this post, you will create a fun app fast. The app lets you change a person's hairstyle on any human picture you upload. It will work for both male and female photos. Let’s get started! Table of contents # Prerequisites Steps to generate a hair style changer app Navigate to Google AI Studio Go to Build Paste the…
Google’s NotebookLM is a hidden gem in the world of information processing. It is not just another chatbot; it is a personalized AI research assistant grounded in your own documents. If you have ever felt overwhelmed by the sheer amount of documentation, PDFs, or websites you need to read to get a job done, this tool is for you at no cost. In this post, you will learn how to use NotebookLM,…
Using Google AI Studio’s build feature, you can build any frontend application by giving a prompt. The Build feature in AI Studio generates applications that use the Gemini SDK without any server-side components. The apps run in a sandboxed frame. For this post, you will create a tech resume reviewer that will score your resume out of 100 against a given job description. Let’s get started! Table…
Imagine being able to open a pull request or close an issue without leaving your IDE/Editor. This is made possible by the GitHub Model Context Protocol (MCP) server. In this post, you will learn how to use the remote GitHub MCP server with GitHub Copilot on VS Code. Let's get started! Table of contents # What is MCP Official GitHub MCP server Using GitHub MCP server locally Remote GitHub MCP…
Gemma is a collection of lightweight, modern open models built by Google. They are designed to run fast on devices like phones, on machines in the cloud, to help developers create AI applications. In this post, you will learn the easiest and fastest way to run the latest version of Gemma, 3 (4 B), on Google Cloud Run deployed from Google AI Studio. Let’s get started! Table of Contents # Gemma 3 on…
Can you code and deploy a basic but functional app with minimal coding experience? With the latest Google AI Studio feature, you can build and deploy apps by instructing an agent in minutes. You can also deploy the app on Google Cloud Run and make changes easily. This post will show you how. Let’s get started! Table of contents # The goal Build an app with a prompt on Google AI Studio Deploy to…
With Cloud Run, just bring your code! Google handles the complex server stuff and scaling, so you don't have to. Typically, you could run only web services with a URL on Google Cloud Run as services. For some time now, you can also run Cloud Run Jobs to execute a task to completion, which might take longer than minutes or even hours. In this beginner-friendly post, you will learn how to run jobs…
Amazon Elastic Container Service (ECS) is a fully managed container orchestration service that simplifies the deployment, management, and scaling of containerized applications on AWS. It manages containers without the need to learn Kubernetes. With Fargate, resource management can also be serverless. In this post, you will learn how to deploy a built container image from Amazon Elastic Container…
Amazon Elastic Container Registry (ECR) is a fully managed container registry that can store (Docker) container images, making it easy to pull, share, and deploy container images. This post will teach you how to create a private Amazon ECR and push Docker container images of a simple Node.js Hello World app with Express. Let’s get started! Table of contents # What is Amazon ECR The Node.js Hello…
Ollama gives you one of the easiest ways to run most open LLMs on your machine. It is open-source and easy to use. In addition to using it with a command line or its APIs, you can use it with a web user interface using Open WebUI . This post will teach you how to run Ollama and Open WebUI to run any open LLM with a web-based chat interface like ChatGPT. Let’s get started! Table of contents # Recap…
Ollama is open-source software that makes running most open LLMs seamlessly on your own machine (or even on the cloud). Written in Go, Ollama is user-friendly and easy to start. In this post, part 3 of the Ollama blog post series, you will learn about using Ollama’s APIs for generating responses (LLM inference) and much more; let’s get going! Table of contents # Quick review of the Ollama series…
Ollama is an open-source tool that helps you run open LLMs on your machine or a server. It is the glue layer between your machine (or hardware) and the open LLM of your choice. In this post, you will learn about the Ollama commands you can use to get the most out of it; let’s get going! Table of contents # Quick recap Ollama commands Ollama serve Ollama run Ollama list Ollama pull Ollama ps Ollama…
The world of AI has been hyped for more than two years now since the release of ChatGPT in November 2022. New tools and technologies emerge daily, promising to revolutionize our work and lives. If you're looking to harness the power of large language models (LLMs) for personal projects or even professional applications, Ollama might be the key. In this post, you will learn what Ollama is, how to…
LLMs generally reply in a nondeterministic format; it does not always comply with the formatting instructions given. This is where controlled generation (structured output) comes into play, where you ask an LLM to reply to comply with a given schema. In this post, you will learn how to use Gemini over Vertex AI and controlled generation to get structured output that follows a schema on job…
Ollama is a great way to run many open Large Language Models (LLMs). You can run Google Gemma 2, Phi 4, Mistral, and Llama 3 on your machine or the cloud with Ollama . You can also host these open LLMs as APIs using Ollama. In this post, you will learn how to host Gemma 2 (2b) with Ollama 0.5.x on Google Cloud Run; let’s get started! Table of contents # Why Google Cloud Run Create a GCS bucket…
I started writing the year-in-review (recap) posts from 2019 , so this will be the sixth consecutive year I will write a yearly recap. Taking some time to reflect on things accomplished this year from a professional point of view, I think it will be a good rearview mirror view to look back at 2024; let’s dive in! A motorcycle rear view mirror background image generated using Image FX (Imagen 3)…
Do you feel your resume, LinkedIn profile, or GitHub contributions don't convey the right message? Your CV, LinkedIn profile, and GitHub repositories are your digital storefront, and keeping them fresh and relevant is key to attracting opportunities. In this post, we'll explore leveraging Google Gemini 2.0's real-time streaming capabilities to improve your CV, LinkedIn, and GitHub profile,…
Updating existing data is a core requirement of any web application; doing it efficiently will make your life easier. PostgreSQL, a robust and feature-rich relational database, offers a powerful and elegant solution for managing these updates: INSERT ON CONFLICT UPDATE . It is helpful to combine insert and update operations into an upsert and use the same logic for both operations. In this post,…
Environment variables are essential for configuring your Node.js applications, allowing you to tailor settings for different environments like development, testing, and production. While you can set environment variables directly in your system or terminal, a more organized approach is to use a .env file . This file allows you to store all your environment variables in one central location,…