# Writing Code Published articles for Writing Code. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Python Practice Problems: Parsing CSV Files DevFeed: [Python Practice Problems: Parsing CSV Files]() Original publisher: [Read original article]() Author: Jim Anderson Published: 2026-09-13T14:00:00Z Content type: tutorial Language: en Sources: [Real Python]() Topics: [CSV](), [Python](), [Test-driven development](), [Command-line interface](), [pass]() Tags: [code](), [coding](), [command-line](), [data](), [python](), [testing](), [tutorial](), [tutorials](), [writing-code]() ### AI overview An intermediate-level tutorial that helps Python developers practice parsing CSV files through interview-style problems. It covers writing solutions, test-driven development with pytest, solution improvements, and the trade-offs between Python's built-in csv module and pandas. ### Source excerpt In this tutorial, you'll prepare for future interviews by working through a set of Python practice problems that involve CSV files. You'll work through the problems yourself and then compare your results with solutions developed by the Real Python team. ## CodeSOD: Asynchronous Directories DevFeed: [CodeSOD: Asynchronous Directories]() Original publisher: [Read original article]() Author: Remy Porter Published: 2026-09-09T06:30:00Z Content type: article Language: en Sources: [The Daily WTF]() Topics: [Vala](), [async/await](), [Library](), [Programming]() Tags: [async](), [asynchronous](), [await](), [codesod](), [exceptions](), [filesystem](), [writing-code]() ### AI overview This article examines implementing an asynchronous version of Vala's directory-creation method when the core library provides only a synchronous version. The proposed function walks up the directory tree, then creates missing directories in reverse order, using exceptions for control flow. ### Source excerpt Eri has a mix of a "true confession" and a "wait, really?" today. The programming language Vala bills itself as a C# like language that compiles into something pretty close to C performance, designed specifically for writing code against Gnome and its associated libraries. One of the C#-isms in brings in is async/await type semantics. You can yield someAsyncFunction(), which returns control to the caller, allowing it to proceed until the yielded function returns an actual value. Because it has asynchronous functions, many library functions for handling I/O are already async. So you can make_directory_async, which yields control so you can keep executing while waiting for the filesystem to make your directory. There are also synchronous versions of those methods. And then there's create_directory_with_parents, which will create a chain of directories for you. That's the synchronous version, and Vala's core library has decided not to provide an asynchronous version of it, which is my "wait, really?" I suspect it's really about the race conditions involved and the risks of things going wrong while doing it asynchronously; all solvable problems, but tricky ones to solve. But it's the problem Eri had, and this is their solution: /// Note: does not throw if target already exists async void create_directory_with_parents_async(File file, Cancellable? cancellable = null) throws Error { var to_create = new File[0]; var? current_target = file; while(current_target != null) { try { yield current_target.make_directory_async(Priority.DEFAULT, cancellable); } catch(IOError.NOT_FOUND e) { to_create += current_target; current_target = current_target.get_parent(); continue; } catch(IOError.EXISTS e) { break; } break; } for (int i = to_create.length - 1; i >= 0; --i) { try { yield to_create[i].make_directory_async(Priority.DEFAULT, cancellable); } catch(IOError.EXISTS e) { // Created by another process } } } If I'm reading this correctly, we start by trying to create the full path to ## 1Password increases engineering productivity 21% with Codex DevFeed: [1Password increases engineering productivity 21% with Codex]() Original publisher: [Read original article]() Published: 2026-09-08T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [AI-assisted coding]() Tags: [codex](), [engineering](), [features](), [internal-tools](), [productivity](), [pull-request](), [security](), [site-reliability-engineering](), [software-delivery](), [user-stories](), [writing-code]() ### AI overview 1Password reports using Codex across its software delivery lifecycle to turn user stories into near-final prototypes and features more quickly. It cites improved engineering productivity and shorter pull request cycle times while maintaining security standards. ### Source excerpt Engineers at 1Password use Codex to rapidly build new features and internal tools, reaching production-readiness while maintaining rigorous security policies. ## Expanding OpenAI's presence in Brazil DevFeed: [Expanding OpenAI's presence in Brazil]() Original publisher: [Read original article]() Published: 2026-08-27T03:00:00Z Content type: news Language: en Sources: [OpenAI News]() Topics: [OpenAI](), [Artificial Intelligence](), [ChatGPT](), [Deployment](), [Code]() Tags: [ai](), [ai-adoption](), [brazil](), [chatgpt](), [company](), [deployment](), [developers](), [marketing](), [openai](), [production](), [writing-code]() ### AI overview OpenAI is launching commercial operations in Brazil, where ChatGPT adoption is growing rapidly. The local team will work with businesses, developers, researchers, and public institutions to support responsible AI use and broader economic and social benefits. ### Source excerpt OpenAI is expanding its presence in Brazil, deepening engagement with developers, businesses, and communities to support AI adoption across the country. ## How Semantic Code Navigation Cuts Agent Token Costs by up to 36% DevFeed: [How Semantic Code Navigation Cuts Agent Token Costs by up to 36%]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-21T21:51:15Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [coding](), [ai-coding](), [Code]() Tags: [agent](), [ai](), [ai-coding](), [code](), [coding](), [writing-code]() ### AI overview The article argues that coding agents spend substantial tokens finding where changes belong in a codebase before writing code. It examines semantic code navigation as a way to reduce that discovery cost, with a stated reduction of up to 36%. ### Source excerpt Understanding what an agent actually does with the tokens before it writes code. ## Figma is the New Dreamweaver: How Modern Prototyping Tools are Trapping Us in 2018 DevFeed: [Figma is the New Dreamweaver: How Modern Prototyping Tools are Trapping Us in 2018]() Original publisher: [Read original article]() Author: Noah Davis Published: 2026-08-17T12:04:00Z Content type: opinion Language: en Sources: [Web Designer Depot]() Topics: [Figma](), [Code](), [CSS](), [HTML](), [Web](), [Web Development](), [systems]() Tags: [accessibility](), [css](), [design](), [design-systems](), [design-tools](), [dreamweaver](), [figma](), [figma-alternatives](), [frontend-development](), [html](), [interface-design](), [modern-web-design](), [product-design](), [prototyping](), [responsive-design](), [systems](), [ui-design](), [user-experience](), [ux-design](), [web](), [web-design](), [web-designers](), [web-development](), [writing-code]() ### AI overview Figma's polished, pixel-based canvas and prototyping features can obscure the fluidity, document flow, layout behavior, and unpredictable content of the web. The article argues that designers who rely on fixed artboards and simulated code risk repeating Dreamweaver's history of separating visual design from HTML, CSS, responsive behavior, performance, and systems thinking. ### Source excerpt Just like Dreamweaver convinced a generation they could ignore HTML and CSS, Figma's perfect canvas may be hiding the messy realities of how the web actually works. The future belongs to designers who understand systems, behavior, performance, and code--not just pixels. ## We Became Editors-in-Chief, and Nobody Trained Us DevFeed: [We Became Editors-in-Chief, and Nobody Trained Us]() Original publisher: [Read original article]() Author: Freek Van der Herten (freek@spatie.be) Published: 2026-08-03T14:56:25Z Content type: opinion Language: en Sources: [freek.dev - all blogposts]() Topics: [Artificial Intelligence](), [Development](), [Code]() Tags: [ai](), [career](), [code](), [code-review](), [developer-experience](), [development](), [essay](), [soft-skills](), [writing-code]() ### AI overview An essay examines how AI-assisted development shifts engineers from writing code toward reviewing AI-generated diffs. It argues that this change creates cognitive fatigue and may widen the gap between senior and junior engineers. ### Source excerpt An essay on how AI-assisted development turns engineers into full-time reviewers. We spend our days evaluating AI-generated diffs instead of writing code, and that shift carries a new cognitive fatigue and may widen the senior/junior gap. Read more ## As AI writes and reads more software, human-readable source code may become less essential DevFeed: [As AI writes and reads more software, human-readable source code may become less essential]() Original publisher: [Read original article]() Author: Mike Yerou Published: 2026-07-30T15:51:05Z Content type: opinion Language: en Sources: [Rock and Null]() Topics: [Code](), [Artificial Intelligence](), [Large Language Model](), [ide]() Tags: [ai](), [code](), [debugging](), [developers](), [llms](), [software-engineering](), [thoughts](), [writing-code]() ### AI overview The article argues that as AI models increasingly generate, understand, and fix software, developers may spend less time writing human-readable source code and more time verifying AI-produced software. It notes that readable code still reduces token use, aids inspection and debugging, and benefits current AI systems. ### Source excerpt For decades, we wrote code for humans. As AI becomes both the author and the primary reader of software, developers may spend less time writing code and more time verifying that it matches their intent. ## How to build a faceted search interface with Algolia and Webflow without managing infrastructure DevFeed: [How to build a faceted search interface with Algolia and Webflow without managing infrastructure]() Original publisher: [Read original article]() Author: Ismail Ajagbe Published: 2026-07-26T00:00:00Z Content type: tutorial Language: en Sources: [Webflow Blog]() Topics: [Algolia](), [webflow](), [Content Management System](), [Next.js](), [Cloudflare Workers](), [React](), [API](), [API keys](), [Front end]() Tags: [api](), [app](), [architecture](), [blog](), [cloudflare](), [cloudflare-workers](), [guide](), [guides](), [how-to](), [integrations](), [next-js](), [react](), [search](), [ui](), [webflow](), [writing-code]() ### AI overview A tutorial on building faceted Algolia search for Webflow CMS content with a Next.js app on Webflow Cloud. It covers indexing content through the Webflow Data API, a React search interface with filters, highlighting, and pagination, webhook-based synchronization, and secure separation of frontend and server-side API keys. ### Source excerpt Learn how to build a faceted search with Algolia and Webflow Cloud by indexing CMS content, adding filters, and syncing the index with webhooks. ## C++ Dependencies Without the Headache: vcpkg + Copilot CLI DevFeed: [C++ Dependencies Without the Headache: vcpkg + Copilot CLI]() Original publisher: [Read original article]() Author: Augustin Popa Published: 2026-07-20T21:05:25Z Content type: article Language: en Sources: [C++ Team Blog]() Topics: [GitHub Copilot CLI](), [Vcpkg](), [C++](), [GitHub Copilot](), [MSVC](), [Command-line interface](), [GitHub]() Tags: [blog](), [c-plus-plus](), [cli](), [cmake](), [copilot](), [github](), [github-copilot](), [github-copilot-cli](), [msvc](), [open-source](), [programming](), [pure-virtual-c-plus-plus](), [vcpkg](), [writing-code]() ### AI overview A practical walkthrough of building a C++ console application from an empty folder with CMake, MSVC Build Tools, vcpkg, and GitHub Copilot CLI. It demonstrates dependency selection, installation, integration, reproducible builds, and controlled dependency updates through a terminal-first workflow. ### Source excerpt At Pure Virtual C++ 2026, we build a C++ console app from an empty folder using CMake, MSVC, and GitHub Copilot CLI. This walkthrough shows a practical prompt sequence for dependency selection, reproducible builds, and controlled updates. The post C++ Dependencies Without the Headache: vcpkg + Copilot CLI appeared first on C++ Team Blog. ## How AI-Assisted Coding Is Changing the Engineering Role DevFeed: [How AI-Assisted Coding Is Changing the Engineering Role]() Original publisher: [Read original article]() Author: Wix Engineering Published: 2026-07-19T10:33:35Z Content type: opinion Language: en Sources: [Wix Engineering]() Topics: [Artificial Intelligence](), [Programming](), [Claude Code]() Tags: [2026](), [ai](), [claude-code](), [programming](), [prompting](), [workflow](), [writing-code]() ### AI overview This opinion article examines how AI-assisted coding is changing software engineering. It argues that writing code is increasingly an iterative dialogue involving prompting, evaluation, and pushback, while acknowledging engineers' uncertainty about the future of their work. ### Source excerpt During 2026, I shipped code that I don't fully understand. It was written in a programming language I'm not even fluent in. A year ago, this would have been a fireable offense. There's no way I would have stood on a stage at a Wix Engineering conference, my employers in the crowd, and said that sentence out loud. Last week, it was just another Tuesday. And here's the part that's been keeping me up at night: I was proud of it. That's a paradox, right? If someone else wrote it, I can't be proud... ## How AI Changes the Cost of Evaluating Small Code Changes DevFeed: [How AI Changes the Cost of Evaluating Small Code Changes]() Original publisher: [Read original article]() Author: Dalia Abuadas Published: 2026-07-17T16:46:47Z Content type: opinion Language: en Sources: [GitHub]() Topics: [Artificial Intelligence](), [GitHub Copilot](), [GitHub](), [Code]() Tags: [ai](), [career-growth](), [code](), [code-review](), [copilot](), [developer-skills](), [engineering](), [github](), [writing-code]() ### AI overview This commentary argues that AI-generated first patches can make trying small code changes cheaper than debating their scope. Engineers should use the patch as a probe to inspect real impact, while recognizing that reviewing, testing, deploying, and owning the change remain costly. ### Source excerpt The cost of writing code dropped; the cost of owning it didn't. A framework for deciding which changes are actually cheap in the AI era. The post The cost of saying yes has changed appeared first on The GitHub Blog. ## Agentic Coding on Supabase with OpenCode DevFeed: [Agentic Coding on Supabase with OpenCode]() Original publisher: [Read original article]() Author: Eric Kharitonashvili Published: 2026-06-30T07:00:00Z Content type: article Language: en Sources: [Supabase Blog]() Topics: [Supabase](), [agentic-coding](), [ai-coding](), [Model Context Protocol](), [Database](), [Agent Skills](), [coding](), [Terminal]() Tags: [agentic-coding](), [ai-agents](), [ai-coding](), [backend](), [coding](), [database](), [ide](), [mcp](), [open-source](), [writing-code]() ### AI overview Supabase's OpenCode integration connects an open-source AI coding agent to Supabase account and project management APIs, bundled Supabase skills, and--through MCP--project capabilities such as databases, Edge Functions, logs, data queries, and deployments. The integration can also monitor agent activity, create projects, and run within a terminal, IDE, or desktop. ### Source excerpt OpenCode integrates with Supabase. Connect your agent to your database, Edge Functions, and logs. MCP setup is configured automatically. ## AI Coding Tools Shift Experienced Developers from Slower to Faster Work DevFeed: [AI Coding Tools Shift Experienced Developers from Slower to Faster Work]() Original publisher: [Read original article]() Author: Jon C. Phillips Published: 2026-06-28T17:56:00Z Content type: opinion Language: en Sources: [Jon C. Phillips]() Topics: [Artificial Intelligence](), [Code](), [Stack Overflow]() Tags: [ai](), [articles](), [audience-building](), [code](), [design](), [developers](), [digital-products](), [judgment-bottleneck](), [music](), [photography](), [product-engineering](), [side-projects](), [survey](), [web-development](), [writing-code]() ### AI overview The article argues that experienced developers' measured performance with AI coding tools shifted from roughly 19% slower in mid-2025 to roughly 18% faster by early 2026. It attributes the change to better tools and developers gaining experience directing and reviewing generated code, while noting sample-selection caveats. ### Source excerpt That puts me on one side of a heated argument. A well-known METR study in 2025 found experienced developers were around 19% slower with AI while sure they were faster, and skeptics passed it around as proof. ## How OmniNode uses Redpanda to scale AI agent workflows DevFeed: [How OmniNode uses Redpanda to scale AI agent workflows]() Original publisher: [Read original article]() Author: Jonah Gray Published: 2026-06-02T00:00:00Z Content type: article Language: en Sources: [Redpanda]() Topics: [AI-assisted coding](), [AI Agent](), [Software Engineering](), [pull-requests](), [Code]() Tags: [ai](), [ai-agent](), [engineering](), [pull-requests](), [software-engineering](), [writing-code]() ### AI overview OmniNode's founder describes using AI code generation and multiple agents to automate software engineering work beyond writing code, including pull-request review, failure tracing, configuration checks, and codebase-wide renames. The article explains that coordinating independent agents required routing tasks, tracking status, verifying results, and enforcing ordering. It also describes using Redpanda to scale an event catalog and maintain consistent topic names through contracts. ### Source excerpt OmniNode's founder shares his journey building the AI agent workflows that became OmniNode, and how Redpanda keeps topic names from drifting with contracts. ## AI-assisted coding can outpace code review, increasing the need for smaller PRs and clearer architecture context DevFeed: [AI-assisted coding can outpace code review, increasing the need for smaller PRs and clearer architecture context]() Original publisher: [Read original article]() Author: hello@ankit-rana.com Published: 2026-05-17T00:00:00Z Content type: article Language: en Sources: [Ankit Rana | Mechanical Sympathy]() Topics: [AI-assisted coding](), [Code review](), [Pull Request](), [Latency](), [Network](), [Hardware](), [Database](), [Concurrency]() Tags: [ai](), [architecture](), [branch](), [cloud](), [code-review](), [cost](), [hardware](), [incident](), [latency](), [network](), [production](), [productivity](), [review](), [system-design](), [writing-code]() ### AI overview AI-assisted coding can make implementation much faster than review. The article explains that reviewers must reconstruct context, trace data flow, and assess hardware, network, latency, connection-pool, and architecture implications. It recommends keeping AI-written PRs small, documenting operational costs, and showing network boundaries early. ### Source excerpt AI made writing code a local, fast operation while review stayed cold and global: the reviewer must reload architecture, trace data flow, and mentally simulate hardware and network cost. A 400-line PR can take twice as long to review as it took to generate. Keep AI-written PRs under 100 lines, state endpoint count and expected latency in the description, and show the network boundary up front. ## Behind the Flame: Joe Hart DevFeed: [Behind the Flame: Joe Hart]() Original publisher: [Read original article]() Author: Megan Batterbury Published: 2026-04-23T10:00:00Z Content type: article Language: en Sources: [The incident.io Blog]() Topics: [incident](), [incident management](), [dashboards](), [Code](), [Slack]() Tags: [code](), [code-testing](), [collaboration](), [developer](), [engineering](), [incident](), [incident-channel](), [incident-management](), [incident-response](), [integrations](), [outage](), [post-mortem](), [slack](), [slack-incident](), [testing](), [tools](), [work](), [writing-code]() ### AI overview This profile introduces Joe Hart, a Product Engineer on incident.io's Response team. It describes his work on status pages, the incident management lifecycle, integrations, dashboards, customer issues, coding, testing, and collaboration across engineering teams. ### Source excerpt Meet Joe Hart, Product Engineer here at incident.io. 🔥 ## Laravel AI SDK, Boost, or MCP: Which Tool Do You Need? DevFeed: [Laravel AI SDK, Boost, or MCP: Which Tool Do You Need?]() Original publisher: [Read original article]() Author: Ana Tavares Published: 2026-03-04T17:18:51Z Content type: article Language: en Sources: [Laravel Blog]() Topics: [Laravel](), [vercel ai sdk](), [Laravel Boost](), [MCP](), [Artificial Intelligence](), [SDKs](), [API](), [text-generation]() Tags: [ai](), [api](), [laravel](), [mcp](), [text-generation](), [tool](), [writing-code]() ### AI overview This article compares Laravel's AI SDK, Laravel Boost, and Laravel MCP. It explains that the AI SDK adds AI capabilities to Laravel applications, Boost helps AI agents write Laravel code, and MCP lets external AI tools interact with an application. ### Source excerpt Laravel AI SDK, Boost, and MCP serve different purposes. Learn when to use each one, how they work together, and how to build faster with Laravel. ## Why AI-Assisted Development Exposes Terraform's Infrastructure Provisioning Bottleneck DevFeed: [Why AI-Assisted Development Exposes Terraform's Infrastructure Provisioning Bottleneck]() Original publisher: [Read original article]() Author: Ivan Cernja Published: 2026-02-25T00:00:00Z Content type: opinion Language: en Sources: [Encore Updates]() Topics: [Terraform](), [Provisioning](), [Artificial Intelligence](), [Development]() Tags: [ai](), [development](), [provisioning](), [terraform](), [typescript](), [writing-code]() ### AI overview The article argues that AI-assisted development has made Terraform-based infrastructure provisioning a bottleneck. Although AI agents can generate application and Terraform code quickly, separate infrastructure and application workflows still require multiple reviews, plan/apply cycles, staging verification, and synchronization between codebases. ### Source excerpt Terraform solved the right problem. AI just made it the wrong answer. ## Why AI-Generated Software Often Lacks Distinctive Taste DevFeed: [Why AI-Generated Software Often Lacks Distinctive Taste]() Original publisher: [Read original article]() Author: Carlos Alexandro Becker Published: 2026-02-03T00:00:00Z Content type: opinion Language: en Sources: [Carlos Becker]() Topics: [Artificial Intelligence](), [Code](), [Software]() Tags: [ai](), [code](), [software](), [writing-code]() ### AI overview This opinion article argues that AI can make developers more productive and generate software quickly, but its output often feels generic and soulless. Drawing on Richard W. Hamming's ideas about developing personal style and judgment, the author suggests that distinctive taste helps people choose important problems and make better software. ### Source excerpt Code is cheap, show me the... what exactly? ## Writing Clean Code with Laravel: The Artisan of the Day Is Jamie Peters. DevFeed: [Writing Clean Code with Laravel: The Artisan of the Day Is Jamie Peters.]() Original publisher: [Read original article]() Author: Ana Tavares Published: 2025-12-05T17:56:30Z Content type: article Language: en Sources: [Laravel Blog]() Topics: [Laravel](), [coding](), [Code](), [PHP](), [Frameworks]() Tags: [career](), [code](), [coding](), [developer](), [development](), [framework](), [hobby](), [laravel](), [php](), [uk](), [writing-code]() ### AI overview Jamie Peters describes how discovering Laravel in 2018 transformed his approach to architecture, clarity, maintainability, and clean code. He now develops with Laravel at Jump24 in the United Kingdom and views the work as a rewarding craft. ### Source excerpt Jamie Peters shares how discovering Laravel in 2018 transformed his career, sharpened his coding practices, and led him to his role at Jump24 in the UK. ## Double click: What does it mean to be a designer in the age of AI? DevFeed: [Double click: What does it mean to be a designer in the age of AI?]() Original publisher: [Read original article]() Author: Andrew Hogan Published: 2025-12-03T00:00:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Artificial Intelligence](), [Code](), [App]() Tags: [ai](), [certifications](), [complexity](), [developers](), [generalist](), [software-engineer](), [writing-code]() ### AI overview The article examines how AI and expanding workflows are blurring the boundaries among designers, developers, and product managers. It explores the growing value of generalist skills and questions how changing responsibilities may affect job titles, professional identity, and ways of working. ### Source excerpt The scope of what designers, developers, and product managers do is expanding, and the boundaries between them are blurring. As workflows shift, a bigger question emerges: What happens to job titles--and the ways of working and sense of identity that comes with them? ## The cinch DevFeed: [The cinch]() Original publisher: [Read original article]() Published: 2025-10-14T07:00:00Z Content type: opinion Language: en Sources: [Mary Rose Cook]() Topics: [Large Language Model](), [Figma](), [Code](), [ui](), [Notion]() Tags: [code](), [context](), [figma](), [implement](), [llm](), [model](), [ui](), [writing-code]() ### AI overview An account of using an LLM to implement UI refinements by combining Figma mocks, existing UI code, and a concise list of relevant revisions. The added context helped focus the model on current changes despite noise in the mocks and saved substantial coding time. ### Source excerpt When generating code with an LLM, sometimes a task is so laborious to specify that you may as well do it manually. But, sometimes, you can find just the right information to cinch together to enable the model to do the work. Here's an example. At Notion, I had built some UI for a new feature. Ken, my designer colleague, reviewed the working software and updated his Figma mocks with some refinements he wanted. I needed to implement those refinements. The Figma mocks provided all the necessary information about how the UI should look and work. And the existing code represented the current state. But I couldn't just point the LLM at the mocks and tell it to implement the differences. The comparison between code and mocks was too noisy. The mocks included things we were planning for the farther future, things that were out of date, things that another engineer was implementing. But, it wasn't worth the effort of directing the LLM to do each change, one by one. Which brings me to the cinch: I realized I could combine the mocks and the current UI code with just a little bit of extra context: a terse bullet point list of the revisions. The mocks provided the full context of each change, but the bullets directed the model's attention to the relevant information. This cinch took me maybe fifteen minutes to compile, but saved hours of writing code. Seeing how to draw together the crucial information to let an LLM understand what to do. The cinch. ## Double click: When coding becomes conversation DevFeed: [Double click: When coding becomes conversation]() Original publisher: [Read original article]() Author: Carly Ayres Published: 2025-02-20T00:00:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Vibe coding](), [coding](), [Artificial Intelligence](), [Figma](), [Repl.it](), [Val Town]() Tags: [ai](), [code](), [coding](), [design](), [developers](), [development](), [figma](), [val-town](), [vibe-coding](), [writing-code]() ### AI overview This article examines vibe coding, an AI-assisted development style in which people describe what they want conversationally and iteratively refine the result instead of writing code line by line. It presents the approach as a playful, more accessible way to prototype and build software, while acknowledging debate about whether it creates more mayhem than magic. ### Source excerpt Developers are embracing a new way of building software that's more conversation than code. But is it more mayhem than magic? [Next page]()