Javascript

Fly.io for Easier Cloud Deployment with Annie Sexton

Published Nov 6, 2024

Updated Dec 11, 2024

2 min read

Annie Sexton, Developer Advocate at Fly.io, to discuss Fly.io’s approach to simplifying cloud deployment. Annie shares Fly.io's unique position as a public cloud that offers the flexibility of infrastructure control with a streamlined developer experience. They explore Fly.io’s private networking and distributed app capabilities, allowing developers to deploy applications close to users worldwide with ease. Annie also addresses common challenges in distributed systems, including latency, data replication, and the balance between global reach and simple, single-region projects.

Chapters:

00:00 - 01:32 Introduction to the Modern Web Podcast and Guests
01:33 - 04:00 Overview of Fly.io and Annie’s Role as Developer Advocate
04:01 - 06:35 What Makes Fly.io Stand Out Among Cloud Platforms
06:36 - 08:57 Distributed Applications: Benefits and Use Cases
08:58 - 11:28 Understanding Distributed Web Servers and Private Networking
11:29 - 13:49 Challenges in Distributed Data and Replication Techniques
13:50 - 16:12 Fly.io’s Unique Solutions for Data Consistency
16:13 - 18:34 When to Consider a Distributed Setup for Your Application
18:35 - 20:35 Tools and Tips for Evaluating Geographical Distribution Needs
20:36 - 22:22 Simplifying Global Deployment with Fly.io’s Command Features
22:23 - 24:18 Considerations for Latency and Performance Optimization
24:19 - 26:45 Balancing Simplicity with Advanced Control for Developers
26:46 - 29:04 Easy Deployment for Hobbyists and Smaller Projects
29:05 - 31:27 Getting Started on Fly.io with Fly Launch
31:28 - 33:48 Developer Advocacy and Meeting Diverse Needs in the Cloud
33:49 - 36:15 Catering to Beginners and Experienced Developers Alike
36:16 - End Closing Remarks and Where to Find Fly.io and the Hosts

Follow Annie Sexton on Social Media Linkedin: ⁠https://www.linkedin.com/in/annie-sexton-11472a46/⁠ Github: ⁠https://github.com/anniebabannie⁠

Introduction to Zod for Data Validation

As web developers, we're often working with data from external sources like APIs we don't control or user inputs submitted to our backends. We can't always rely on this data to take the form we expect, and we can encounter unexpected errors when it deviates from expectations. But with the Zod library, we can define what our data ought to look like and parse the incoming data against those defined schemas. This lets us work with that data confidently, or to quickly throw an error when it isn't correct. Why use Zod? TypeScript is great for letting us define the shape of our data in our code. It helps us write more correct code the first time around by warning us if we are doing something we shouldn't. But TypeScript can't do everything for us. For example, we can define a variable as a string or a number, but we can't say "a string that starts with user_id_ and is 20 characters long" or "an integer between 1 and 5". There are limits to how much TypeScript can narrow down our data for us. Also, TypeScript is a tool for us developers. When we compile our code, our types are not available to the vanilla JavaScript. JavaScript can't validate that the data we actually use in our code matches what we thought we'd get when we wrote our TypeScript types unless you're willing to manually write code to perform those checks. This is where we can reach for a tool like Zod. With Zod, we can write data schemas. These schemas, in the simplest scenarios, look very much like TypeScript types. But we can do more with Zod than we can with TypeScript alone. Zod schemas let us create additional rules for data parsing and validation. A 20-character string that starts with user_id_? It's z.string().startsWith('user_id_').length(20). An integer between 1 and 5 inclusive? It's z.number().int().gte(1).lte(5). Zod's primitives give us many extra functions to be more specific about *exactly* what data we expect. Unlike TypeScript, Zod schemas aren't removed on compilation to JavaScript—we still have access to them! If our app receives some data, we can verify that it matches the expected shape by passing it to your Zod schema's parse function. You'll either get back your data in exactly the shape you defined in your schema, or Zod will give you an error to tell you what was wrong. Zod schemas aren't a replacement for TypeScript; rather, they are an excellent complement. Once we've defined our Zod schema, it's simple to derive a TypeScript type from it and to use that type as we normally would. But when we really need to be sure our data conforms to the schema, we can always parse the data with our schema for that extra confidence. Defining Data Schemas Zod schemas are the variables that define our expectations for the shape of our data, validate those expectations, and transform the data if necessary to match our desired shape. It's easy to start with simple schemas, and to add complexity as required. Zod provides different functions that represent data structures and related validation options, which can be combined to create larger schemas. In many cases, you'll probably be building a schema for a data object with properties of some primitive type. For example, here's a schema that would validate a JavaScript object representing an order for a pizza: ` Zod provides a number of primitives for defining schemas that line up with JavaScript primitives: string, number, bigint, boolean, date, symbol, undefined, and null. It also includes primitives void, any, unknown, and never for additional typing information. In addition to basic primitives, Zod can define object, array, and other native data structure schemas, as well as schemas for data structures not natively part of JavaScript like tuple and enum. The documentation contains considerable detail on the available data structures and how to use them. Parsing and Validating Data with Schemas With Zod schemas, you're not only telling your program what data should look like; you're also creating the tools to easily verify that the incoming data matches the schema definitions. This is where Zod really shines, as it greatly simplifies the process of validating data like user inputs or third party API responses. Let's say you're writing a website form to register new users. At a minimum, you'll need to make sure the new user's email address is a valid email address. For a password, we'll ask for something at least 8 characters long and including one letter, one number, and one special character. (Yes, this is not really the best way to write strong passwords; but for the sake of showing off how Zod works, we're going with it.) We'll also ask the user to confirm their password by typing it twice. First, let's create a Zod schema to model these inputs: ` So far, this schema is pretty basic. It's only making sure that whatever the user types as an email is an email, and it's checking that the password is at least 8 characters long. But it is *not* checking if password and confirmPassword match, nor checking for the complexity requirements. Let's enhance our schema to fix that! ` By adding refine with a custom validation function, we have been able to verify that the passwords match. If they don't, parsing will give us an error to let us know that the data was invalid. We can also chain refine functions to add checks for our password complexity rules: ` Here we've chained multiple refine functions. You could alternatively use superRefine, which gives you even more fine grained control. Now that we've built out our schema and added refinements for extra validation, we can parse some user inputs. Let's see two test cases: one that's bound to fail, and one that will succeed. ` There are two main ways we can use our schema to validate our data: parse and safeParse. The main difference is that parse will throw an error if validation fails, while safeParse will return an object with a success property of either true or false, and either a data property with your parsed data or an error property with the details of a ZodError explaining why the parsing failed. In the case of our example data, userInput2 will parse just fine and return the data for you to use. But userInput1 will create a ZodError listing all of the ways it has failed validation. ` ` We can use these error messages to communicate to the user how they need to fix their form inputs if validation fails. Each error in the list describes the validation failure and gives us a human readable message to go with it. You'll notice that the validation errors for checking for a valid email and for checking password length have a lot of details, but we've got three items at the end of the error list that don't really tell us anything useful: just a custom error of Invalid input. The first is from our refine checking if the passwords match, and the second two are from our refine functions checking for password complexity (numbers and special characters). Let's modify our refine functions so that these errors are useful! We'll add our own error parameters to customize the message we get back and the path to the data that failed validation. ` Now, our error messages from failures in refine are informative! You can figure out which form fields aren't validating from the path, and then display the messages next to form fields to let the user know how to remedy the error. ` By giving our refine checks a custom path and message, we can make better use of the returned errors. In this case, we can highlight specific problem form fields for the user and give them the message about what is wrong. Integrating with TypeScript Integrating Zod with TypeScript is very easy. Using z.infer<typeof YourSchema> will allow you to avoid writing extra TypeScript types that merely reflect the intent of your Zod schemas. You can create a type from any Zod schema like so: ` Using a TypeScript type derived from a Zod schema does *not* give you any extra level of data validation at the type level beyond what TypeScript is capable of. If you create a type from z.string.min(3).max(20), the TypeScript type will still just be string. And when compiled to JavaScript, even that will be gone! That's why you still need to use parse/safeParse on incoming data to validate it before proceeding as if it really does match your requirements. A common pattern with inferring types from Zod schemas is to use the same name for both. Because the schema is a variable, there's no name conflict if the type uses the same name. However, I find that this can lead to confusing situations when trying to import one or the other—my personal preference is to name the Zod schema with Schema at the end to make it clear which is which. Conclusion Zod is an excellent tool for easily and confidently asserting that the data you're working with is exactly the sort of data you were expecting. It gives us the ability to assert at runtime that we've got what we wanted, and allows us to then craft strategies to handle what happens if that data is wrong. Combined with the ability to infer TypeScript types from Zod schemas, it lets us write and run more reliable code with greater confidence....

Nov 15, 2024

7 mins

JavaScriptZod

The 2025 Guide to JS Build Tools

The 2025 Guide to JS Build Tools In 2025, we're seeing the largest number of JavaScript build tools being actively maintained and used in history. Over the past few years, we've seen the trend of many build tools being rewritten or forked to use a faster and more efficient language like Rust and Go. In the last year, new companies have emerged, even with venture capital funding, with the goal of working on specific sets of build tools. Void Zero is one such recent example. With so many build tools around, it can be difficult to get your head around and understand which one is for what. Hopefully, with this blog post, things will become a bit clearer. But first, let's explain some concepts. Concepts When it comes to build tools, there is no one-size-fits-all solution. Each tool typically focuses on one or two primary features, and often relies on other tools as dependencies to accomplish more. While it might be difficult to explain here all of the possible functionalities a build tool might have, we've attempted to explain some of the most common ones so that you can easily understand how tools compare. Minification The concept of minification has been in the JavaScript ecosystem for a long time, and not without reason. JavaScript is typically delivered from the server to the user's browser through a network whose speed can vary. Thus, there was a need very early in the web development era to compress the source code as much as possible while still making it executable by the browser. This is done through the process of *minification*, which removes unnecessary whitespace, comments, and uses shorter variable names, reducing the total size of the file. This is what an unminified JavaScript looks like: ` This is the same file, minified: ` Closely related to minimizing is the concept of source maps#Source_mapping), which goes hand in hand with minimizing - source maps are essentially mappings between the minified file and the original source code. Why is that needed? Well, primarily for debugging minified code. Without source maps, understanding errors in minified code is nearly impossible because variable names are shortened, and all formatting is removed. With source maps, browser developer tools can help you debug minified code. Tree-Shaking *Tree-shaking* was the next-level upgrade from minification that became possible when ES modules were introduced into the JavaScript language. While a minified file is smaller than the original source code, it can still get quite large for larger apps, especially if it contains parts that are effectively not used. Tree shaking helps eliminate this by performing a static analysis of all your code, building a dependency graph of the modules and how they relate to each other, which allows the bundler to determine which exports are used and which are not. Once unused exports are found, the build tool will remove them entirely. This is also called *dead code elimination*. Bundling Development in JavaScript and TypeScript rarely involves a single file. Typically, we're talking about tens or hundreds of files, each containing a specific part of the application. If we were to deliver all those files to the browser, we would overwhelm both the browser and the network with many small requests. *Bundling* is the process of combining multiple JS/TS files (and often other assets like CSS, images, etc.) into one or more larger files. A bundler will typically start with an entry file and then recursively include every module or file that the entry file depends on, before outputting one or more files containing all the necessary code to deliver to the browser. As you might expect, a bundler will typically also involve minification and tree-shaking, as explained previously, in the process to deliver only the minimum amount of code necessary for the app to function. Transpiling Once TypeScript arrived on the scene, it became necessary to translate it to JavaScript, as browsers did not natively understand TypeScript. Generally speaking, the purpose of a *transpiler* is to transform one language into another. In the JavaScript ecosystem, it's most often used to transpile TypeScript code to JavaScript, optionally targeting a specific version of JavaScript that's supported by older browsers. However, it can also be used to transpile newer JavaScript to older versions. For example, arrow functions, which are specified in ES6, are converted into regular function declarations if the target language is ES5. Additionally, a transpiler can also be used by modern frameworks such as React to transpile JSX syntax (used in React) into plain JavaScript. Typically, with transpilers, the goal is to maintain similar abstractions in the target code. For example, transpiling TypeScript into JavaScript might preserve constructs like loops, conditionals, or function declarations that look natural in both languages. Compiling While a transpiler's purpose is to transform from one language to another without or with little optimization, the purpose of a *compiler* is to perform more extensive transformations and optimizations, or translate code from a high-level programming language into a lower-level one such as bytecode. The focus here is on optimizing for performance or resource efficiency. Unlike transpiling, compiling will often transform abstractions so that they suit the low-level representation, which can then run faster. Hot-Module Reloading (HMR) *Hot-module reloading* (HMR) is an important feature of modern build tools that drastically improves the developer experience while developing apps. In the early days of the web, whenever you'd make a change in your source code, you would need to hit that refresh button on the browser to see the change. This would become quite tedious over time, especially because with a full-page reload, you lose all the application state, such as the state of form inputs or other UI components. With HMR, we can update modules in real-time without requiring a full-page reload, speeding up the feedback loop for any changes made by developers. Not only that, but the full application state is typically preserved, making it easier to test and iterate on code. Development Server When developing web applications, you need to have a locally running development server set up on something like http://localhost:3000. A development server typically serves unminified code to the browser, allowing you to easily debug your application. Additionally, a development server will typically have hot module replacement (HMR) so that you can see the results on the browser as you are developing your application. The Tools Now that you understand the most important features of build tools, let's take a closer look at some of the popular tools available. This is by no means a complete list, as there have been many build tools in the past that were effective and popular at the time. However, here we will focus on those used by the current popular frameworks. In the table below, you can see an overview of all the tools we'll cover, along with the features they primarily focus on and those they support secondarily or through plugins. The tools are presented in alphabetical order below. Babel Babel, which celebrated its 10th anniversary since its initial release last year, is primarily a JavaScript transpiler used to convert modern JavaScript (ES6+) into backward-compatible JavaScript code that can run on older JavaScript engines. Traditionally, developers have used it to take advantage of the newer features of the JavaScript language without worrying about whether their code would run on older browsers. esbuild esbuild, created by Evan Wallace, the co-founder and former CTO of Figma, is primarily a bundler that advertises itself as being one of the fastest bundlers in the market. Unlike all the other tools on this list, esbuild is written in Go. When it was first released, it was unusual for a JavaScript bundler to be written in a language other than JavaScript. However, this choice has provided significant performance benefits. esbuild supports ESM and CommonJS modules, as well as CSS, TypeScript, and JSX. Unlike traditional bundlers, esbuild creates a separate bundle for each entry point file. Nowadays, it is used by tools like Vite and frameworks such as Angular. Metro Unlike other build tools mentioned here, which are mostly web-focused, Metro's primary focus is React Native. It has been specifically optimized for bundling, transforming, and serving JavaScript and assets for React Native apps. Internally, it utilizes Babel as part of its transformation process. Metro is sponsored by Meta and actively maintained by the Meta team. Oxc The JavaScript Oxidation Compiler, or Oxc, is a collection of Rust-based tools. Although it is referred to as a compiler, it is essentially a toolchain that includes a parser, linter, formatter, transpiler, minifier, and resolver. Oxc is sponsored by Void Zero and is set to become the backbone of other Void Zero tools, like Vite. Parcel Feature-wise, Parcel covers a lot of ground (no pun intended). Largely created by Devon Govett, it is designed as a zero-configuration build tool that supports bundling, minification, tree-shaking, transpiling, compiling, HMR, and a development server. It can utilize all the necessary types of assets you will need, from JavaScript to HTML, CSS, and images. The core part of it is mostly written in JavaScript, with a CSS transformer written in Rust, whereas it delegates the JavaScript compilation to a SWC. Likewise, it also has a large collection of community-maintained plugins. Overall, it is a good tool for quick development without requiring extensive configuration. Rolldown Rolldown is the future bundler for Vite, written in Rust and built on top of Oxc, currently leveraging its parser and resolver. Inspired by Rollup (hence the name), it will provide Rollup-compatible APIs and plugin interface, but it will be more similar to esbuild in scope. Currently, it is still in heavy development and it is not ready for production, but we should definitely be hearing more about this bundler in 2025 and beyond. Rollup Rollup is the current bundler for Vite. Originally created by Rich Harris, the creator of Svelte, Rollup is slowly becoming a veteran (speaking in JavaScript years) compared to other build tools here. When it originally launched, it introduced novel ideas focused on ES modules and tree-shaking, at the time when Webpack as its competitor was becoming too complex due to its extensive feature set - Rollup promised a simpler way with a straightforward configuration process that is easy to understand. Rolldown, mentioned previously, is hoped to become a replacement for Rollup at some point. Rsbuild Rsbuild is a high-performance build tool written in Rust and built on top of Rspack. Feature-wise, it has many similiarities with Vite. Both Rsbuild and Rspack are sponsored by the Web Infrastructure Team at ByteDance, which is a division of ByteDance, the parent company of TikTok. Rsbuild is built as a high-level tool on top of Rspack that has many additional features that Rspack itself doesn't provide, such as a better development server, image compression, and type checking. Rspack Rspack, as the name suggests, is a Rust-based alternative to Webpack. It offers a Webpack-compatible API, which is helpful if you are familiar with setting up Webpack configurations. However, if you are not, it might have a steep learning curve. To address this, the same team that built Rspack also developed Rsbuild, which helps you achieve a lot with out-of-the-box configuration. Under the hood, Rspack uses SWC for compiling and transpiling. Feature-wise, it’s quite robust. It includes built-in support for TypeScript, JSX, Sass, Less, CSS modules, Wasm, and more, as well as features like module federation, PostCSS, Lightning CSS, and others. Snowpack Snowpack was created around the same time as Vite, with both aiming to address similar needs in modern web development. Their primary focus was on faster build times and leveraging ES modules. Both Snowpack and Vite introduced a novel idea at the time: instead of bundling files while running a local development server, like traditional bundlers, they served the app unbundled. Each file was built only once and then cached indefinitely. When a file changed, only that specific file was rebuilt. For production builds, Snowpack relied on external bundlers such as Webpack, Rollup, or esbuild. Unfortunately, Snowpack is a tool you’re likely to hear less and less about in the future. It is no longer actively developed, and Vite has become the recommended alternative. SWC SWC, which stands for Speedy Web Compiler, can be used for both compilation and bundling (with the help of SWCpack), although compilation is its primary feature. And it really is speedy, thanks to being written in Rust, as are many other tools on this list. Primarily advertised as an alternative to Babel, its SWC is roughly 20x faster than Babel on a single thread. SWC compiles TypeScript to JavaScript, JSX to JavaScript, and more. It is used by tools such as Parcel and Rspack and by frameworks such as Next.js, which are used for transpiling and minification. SWCpack is the bundling part of SWC. However, active development within the SWC ecosystem is not currently a priority. The main author of SWC now works for Turbopack by Vercel, and the documentation states that SWCpack is presently not in active development. Terser Terser has the smallest scope compared to other tools from this list, but considering that it's used in many of those tools, it's worth separating it into its own section. Terser's primary role is minification. It is the successor to the older UglifyJS, but with better performance and ES6+ support. Vite Vite is a somewhat of a special beast. It's primarily a development server, but calling it just that would be an understatement, as it combines the features of a fast development server with modern build capabilities. Vite shines in different ways depending on how it's used. During development, it provides a fast server that doesn't bundle code like traditional bundlers (e.g., Webpack). Instead, it uses native ES modules, serving them directly to the browser. Since the code isn't bundled, Vite also delivers fast HMR, so any updates you make are nearly instant. Vite uses two bundlers under the hood. During development, it uses esbuild, which also allows it to act as a TypeScript transpiler. For each file you work on, it creates a file for the browser, allowing an easy separation between files which helps HMR. For production, it uses Rollup, which generates a single file for the browser. However, Rollup is not as fast as esbuild, so production builds can be a bit slower than you might expect. (This is why Rollup is being rewritten in Rust as Rolldown. Once complete, you'll have the same bundler for both development and production.) Traditionally, Vite has been used for client-side apps, but with the new Environment API released in Vite 6.0, it bridges the gap between client-side and server-rendered apps. Turbopack Turbopack is a bundler, written in Rust by the creators of webpack and Next.js at Vercel. The idea behind Turbopack was to do a complete rewrite of Webpack from scratch and try to keep a Webpack compatible API as much as possible. This is not an easy feat, and this task is still not over. The enormous popularity of Next.js is also helping Turbopack gain traction in the developer community. Right now, Turbopack is being used as an opt-in feature in Next.js's dev server. Production builds are not yet supported but are planned for future releases. Webpack And finally we arrive at Webpack, the legend among bundlers which has had a dominant position as the primary bundler for a long time. Despite the fact that there are so many alternatives to Webpack now (as we've seen in this blog post), it is still widely used, and some modern frameworks such as Next.js still have it as a default bundler. Initially released back in 2012, its development is still going strong. Its primary features are bundling, code splitting, and HMR, but other features are available as well thanks to its popular plugin system. Configuring Webpack has traditionally been challenging, and since it's written in JavaScript rather than a lower-level language like Rust, its performance lags behind compared to newer tools. As a result, many developers are gradually moving away from it. Conclusion With so many build tools in today's JavaScript ecosystem, many of which are similarly named, it's easy to get lost. Hopefully, this blog post was a useful overview of the tools that are most likely to continue being relevant in 2025. Although, with the speed of development, it may as well be that we will be seeing a completely different picture in 2026!...

Feb 14, 2025

12 mins

JavaScriptDevTools

Introduction to Vercel’s Flags SDK

Introduction to Vercel’s Flags SDK In this blog, we will dig into Vercel’s Flags SDK. We'll explore how it works, highlight its key capabilities, and discuss best practices to get the most out of it. You'll also understand why you might prefer this tool over other feature flag solutions out there. And, despite its strong integration with Next.js, this SDK isn't limited to just one framework—it's fully compatible with React and SvelteKit. We'll use Next.js for examples, but feel free to follow along with the framework of your choice. Why should I use it? You might wonder, "Why should I care about yet another feature flag library?" Unlike some other solutions, Vercel's Flags SDK offers unique, practical features. It offers simplicity, flexibility, and smart patterns to help you manage feature flags quickly and efficiently. It’s simple Let's start with a basic example: ` This might look simple — and it is! — but it showcases some important features. Notice how easily we can define and call our flag without repeatedly passing context or configuration. Many other SDKs require passing the flag's name and context every single time you check a flag, like this: ` This can become tedious and error-prone, as you might accidentally use different contexts throughout your app. With the Flags SDK, you define everything once upfront, keeping things consistent across your entire application. By "context", I mean the data needed to evaluate the flag, like user details or environment settings. We'll get into more detail shortly. It’s flexible Vercel’s Flags SDK is also flexible. You can integrate it with other popular feature flag providers like LaunchDarkly or Statsig using built-in adapters. And if the provider you want to use isn’t supported yet, you can easily create your own custom adapter. While we'll use Next.js for demonstration, remember that the SDK works just as well with React or SvelteKit. Latency solutions Feature flags require definitions and context evaluations to determine their values — imagine checking conditions like, "Is the user ID equal to 12?" Typically, these evaluations involve fetching necessary information from a server, which can introduce latency. These evaluations happen through two primary functions: identify and decide. The identify function gathers the context needed for evaluation, and this context is then passed as an argument named entities to the decide function. Let's revisit our earlier example to see this clearly: ` You could add a custom evaluation context when reading a feature flag, but it’s not the best practice, and it’s not usually recommended. Using Edge Config When loading our flags, normally, these definitions and evaluation contexts get bootstrapped by making a network request and then opening a web socket listening to changes on the server. The problem is that if you do this in Serverless Functions with a short lifespan, you would need to bootstrap the definitions not just once but multiple times, which could cause latency issues. To handle latency efficiently, especially in short-lived Serverless Functions, you can use Edge Config. Edge Config stores flag definitions at the Edge, allowing super-fast retrieval via Edge Middleware or Serverless Functions, significantly reducing latency. Cookies For more complex contexts requiring network requests, avoid doing these requests directly in Edge Middleware or CDNs, as this can drastically increase latency. Edge Middleware and CDNs are fast because they avoid making network requests to the origin server. Depending on the end user’s location, accessing a distant origin can introduce significant latency. For example, a user in Tokyo might need to connect to a server in the US before the page can load. Instead, a good pattern that the Flags SDK offers us to avoid this is cookies. You could use cookies to store context data. The browser automatically sends cookies with each request in a standard format, providing consistent (no matter if you are in Edge Middleware, App Router or Page Router), low-latency access to evaluation context data: ` You can also encrypt or sign cookies for additional security from the client side. Dedupe Dedupe helps you cache function results to prevent redundant evaluations. If multiple flags rely on a common context method, like checking a user's region, Dedupe ensures the method executes only once per runtime, regardless of how many times it's invoked. Additionally, similar to cookies, the Flags SDK standardizes headers, allowing easy access to them. Let's illustrate this with the following example: ` Server-side patterns for static pages You can use feature flags on the client side, but that will lead to unnecessary loaders/skeletons or layout shifts, which are never that great. Of course, it brings benefits, like static rendering. To maintain static rendering benefits while using server-side flags, the SDK provides a method called precompute. Precompute Precompute lets you decide which page version to display based on feature flags and then we can cache that page to statically render it. You can precompute flag combinations in Middleware or Route Handlers: ` Next, inside a middleware (or route handler), we will precompute these flags and create static pages per each combination of them. ` The user will never notice this because, as we use “rewrite”, they will only see the original URL. Now, on our page, we “invoke” our flags, sending the code from the params: ` By sending our code, we are not really invoking the flag again but getting the value right away. Our middleware is deciding which variation of our pages to display to the user. Finally, after rendering our page, we can enable Incremental Static Regeneration (ISR). ISR allows us to cache the page and serve it statically for subsequent user requests: ` Using precompute is particularly beneficial when enabling ISR for pages that depend on flags whose values cannot be determined at build time. Headers, geo, etc., we can’t know their value at build, so we use precompute() so the Edge can evaluate it on the fly. In these cases, we rely on Middleware to dynamically determine the flag values, generate the HTML content once, and then cache it. At build time, we simply create an initial HTML shell. Generate Permutations If we prefer to generate static pages at build-time instead of runtime, we can use the generatePermutations function from the Flags SDK. This method enables us to pre-generate static pages with different combinations of flags at build time. It's especially useful when the flag values are known beforehand. For example, scenarios involving A/B testing and a marketing site with a single on/off banner flag are ideal use cases. ` ` Conclusion Vercel’s Flags SDK stands out as a powerful yet straightforward solution for managing feature flags efficiently. With its ease of use, remarkable flexibility, and effective patterns for reducing latency, this SDK streamlines the development process and enhances your app’s performance. Whether you're building a Next.js, React, or SvelteKit application, the Flags SDK provides intuitive tools that keep your application consistent, responsive, and maintainable. Give it a try, and see firsthand how it can simplify your feature management workflow!...

May 23, 2025

5 mins

Vercel

Roo Custom Modes

Roo Custom Modes Roo Code is an extension for VS Code that provides agentic-style AI code editing functionality. You can configure Roo to use any LLM model and version you want by providing API keys. Once configured, Roo allows you to easily switch between models and provide custom instructions through what Roo calls "modes." Roo Modes can be thought of as a "personality" that the LLM takes on. When you create a new mode in Roo, you provide it with a description of what personality Roo should take on, what LLM model should be used, and what custom instructions the mode should follow. You can also define workspace-level instructions via a .roo/rules-{modeSlug}/ directory at your project root with markdown files inside. Having different modes allows developers to quickly fine-tune how the Roo Code agent performs its tasks. Roo ships out-of-the-box with some default modes: Code Mode, Architect Mode, Ask Mode, Debug Mode, and Orchestrator Mode. These can get you far, but I have expanded on this list with a few custom modes I have made for specific scenarios I run into every day as a software engineer. My Custom Modes 📜 Documenter Mode I created this mode to help me with generating documentation for legacy codebases my team works with. I use this mode to help produce documentation interactively with me while I read a codebase. Mode Definition You are Roo, a highly skilled technical documentation writer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices. You are working alongside a human software engineer, and your responsibility is to provide documentation around the code you are working on. You will be asked to provide documentation in the form of comments, markdown files, or other formats as needed. Mode-specific Instructions You will respect the following rules: * You will not write any code, only markdown files. * In your documentation, you will provide references to specific files and line numbers of code you are referencing. * You will not attempt to execute any commands. * You will not attempt to run the application in the browser. * You will only look at the code and infer functionality from that. 👥 Pair Programmer Mode I created a “Pair Programmer” mode to serve as my personal coding partner. It’s designed to work in a more collaborative way with a human software engineer. When I want to explore multiple ideas quickly, I switch to this mode to rapidly iterate on code with Roo. In this setup, I take on the role of the navigator—guiding direction, strategy, and decisions—while Roo handles the “driving” by writing and testing the code we need. Mode Definition You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices. You are working alongside a human software engineer who will be checking your work and providing instructions. If you get stuck, ask for help and we will solve problems together. Mode-specific Instructions You will respect the following rules: * You will not install new 3rd party libraries without first providing usage metrics (stars, downloads, latest version update date). * You will not do any additional tasks outside of what you have been told to do. * You will not assume to do any additional work outside of what you have been instructed to do. * You will not open the browser and test the application. Your pairing partner will do that for you. * You will not attempt to open the application or the URL at which the application is running. Assume your pairing partner will do that for you. * You will not attempt to run npm run dev or similar commands. Your pairing partner will do that for you. * You will not attempt to run a development server of any kind. Your pairing partner will handle that for you. * You will not write tests unless instructed to. * You will not make any git commits unless explicitly told to do so. * You will not make suggestions of commands to run the software or execute the test suite. Assume that your human counterpart has the application running and will check your work. 🧑‍🏫 Project Manager I created this mode to help me write tasks for my team with clear and actionable acceptance criteria. Mode Definition You are a professional project manager. You are highly skilled in breaking down large tasks into bite-sized pieces that are actionable by an engineering team or an LLM performing engineering tasks. You analyze features carefully and detail out all edge cases and scenarios so that no detail is missed. Mode-specific Instructions Think creatively about how to detail out features. Provide a technical and business case explanation about feature value. Break down features and functionality in the following way. The following example would be for user login: User Login: As a user, I can log in to the application so that I can make changes. This prevents anonymous individuals from accessing the admin panel. Acceptance Criteria * On the login page, I can fill in my email address: * This field is required. * This field must enforce email format validation. * On the login page, I can fill in my password: * This field is required. * The input a user types into this field is hidden. * On failure to log in, I am provided an error dialog: * The error dialog should be the same if the email exists or not so that bad actors cannot glean info about active user accounts in our system. * Error dialog should be a red box pinned to the top of the page. * Error dialog can be dismissed. * After 4 failed login attempts, the form becomes locked: * Display a dialog to the user letting them know they can try again in 30 minutes. * Form stays locked for 30 minutes and the frontend will not accept further submissions. 🦾 Agent Consultant I created this mode for assistance with modifying my existing Roo modes and rules files as well as generating higher quality prompts for me. This mode leverages the Context7 MCP to keep up-to-date with documentation on Roo Code and prompt engineering best practices. Mode Definition You are an AI Agent coding expert. You are proficient in coding with agents and defining custom rules and guidelines for AI powered coding agents. Your specific expertise is in the Roo Code tool for VS Code are you are exceptionally capable at creating custom rules files and custom mode. This is your workflow that you should always follow: 1. 1. Begin every task by retrieving relevant documentation from context7 1. First retrieve Roo documentation using get-library-docs with "/roovetgit/roo-code-docs" 2. Then retrieve prompt engineering best practices using get-library-docs with “/dair-ai/prompt-engineering-guide" 2. Reference this documentation explicitly in your analysis and recommendations 3. Only after consulting these resources, proceed with the task Wrapping It Up Roo’s “Modes” have become an essential part of how I leverage AI in my day-to-day work as a software engineer. By tailoring each mode to specific tasks—whether it’s generating documentation, pairing on code, writing project specs, or improving prompt quality—I’ve been able to streamline my workflow and get more done with greater clarity and precision. Roo’s flexibility lets me define how it should behave in different contexts, giving me fine-grained control over how I interact with AI in my coding environment. Roo also has the capability of defining custom modes per project if that is needed by your team. If you find yourself repeating certain workflows or needing more structure in your interactions with AI tools, I highly recommend experimenting with your own custom modes. The payoff in productivity and developer experience is absolutely worth it....

Jun 13, 2025

6 mins

AIRoo Code

Let's innovate together!

We're ready to be your trusted technical partners in your digital innovation journey.

Whether it's modernization or custom software solutions, our team of experts can guide you through best practices and how to build scalable, performant software that lasts.