Rizel Scarlett

Raise your hand if you thought WebMCP was just an MCP server. Guilty as charged. I did too. It turns out it's a W3C standard that uses similar concepts to MCP. Here's what it actually is.

On New Year's Day 2026, while many were recovering from the night before, a different kind of hangover took hold of every AI-pilled, chronically online software engineer. Steve Yegge published a new blog post: "Welcome to Gas Town." Some walked away inspired to finally use their agents optimally; others were just plain confused. If you're like me, you felt a bit of both.

Yegge's 34 minute post is a sprawling vision filled with futuristic ideas, playful characters, and enough side tangents to make your head spin. But underneath the lore is a massive architectural shift. I want to take a step back and simplify the "Big Idea" for everyone: Gas Town is a philosophy and a proof of concept to help people coordinate multiple agents working together.

Agents fundamentally changed how we program. They enable developers to move faster by disintermediating the traditional development workflow. This means less time switching between specialized tools and fewer dependencies on other teams. Now that agents can execute complicated tasks, developers face a new challenge: using them effectively over long sessions.

The biggest challenge is context rot. Because agents have limited memory, a session that runs too long can cause them to "forget" earlier instructions. This leads to unreliable outputs, frustration, and subtle but grave mistakes in your codebase. One promising solution is Code Mode.

Everyone on Tech Twitter has been buying Mac Minis, so they could run a local agentic tool called OpenClaw. OpenClaw is a messaging-based AI assistant that connects to platforms such as Discord and Telegram allowing you to interact with an AI agent through DMs or @mentions. Under the hood, it uses an agent called Pi to execute tasks, browse the web, write code, and more.

Seeing the hype made me want to get my hands dirty. I wanted to see if I could build a lite version for myself. I wanted something minimal that used goose as the engine instead of Pi. I tentatively dubbed it AltOpenClaw.

MCP Apps allow you to render interactive UI directly inside any agent supporting the Model Context Protocol. Instead of a wall of text, your agent can now provide a functional chart, a checkout form, or a video player. This bridges the gap in agentic workflows: clicking a button is often clearer than describing the action you hope an agent executes.

MCP Apps originated as MCP-UI, an experimental project. After adoption by early clients like goose, the MCP maintainers incorporated it as an official extension. Today, it's supported by clients like goose, MCPJam, Claude, ChatGPT, and Postman.

Even though MCP Apps use web technologies, building one isn't the same as building a traditional web app. Your UI runs inside an agent you don't control, communicates with a model that can't see user interactions, and needs to feel native across multiple hosts.

After implementing MCP App support in our own hosts and building several individual apps to run on them, here are the practical lessons we've picked up along the way.

Can you automate taste? The short answer is no, you cannot automate taste, but I did make my design preferences legible.

But for those interested in my experiment, I'll share the longer answer: I wanted to participate in Genuary, the annual challenge where people create one piece of creative coding every day in January.

My goal here wasn't to "outsource" my creativity. Instead, I wanted to use Genuary as a sandbox to learn agentic engineering workflows. These workflows are becoming the standard for how developers work with technology. To keep my skills sharp, I used goose to experiment with these workflows in small, daily bursts.

As AI agents grow in capability, more people feel empowered to code and contribute to open source. The ceiling feels higher than ever. That is a net positive for the ecosystem, but it also changes the day-to-day reality for maintainers. Maintainers like the goose team face a growing volume of pull requests and issues, often faster than they can realistically process.

We embraced this reality and put goose to work on its own backlog.

One day, we will tell our kids we used to have to wait for agents, but they won't know that world because the agents in their day would be so fast. I joked about this with Nick Cooper, an MCP Steering Committee Member from OpenAI, and Bradley Axen, the creator of goose. They both chuckled at the thought because they understand exactly how clunky and experimental our current "dial-up era" of agentic workflows can feel.

Model Context Protocol (MCP) has moved the needle by introducing a new norm: the ability to connect agents to everyday apps. However, the experience isn't perfect. We are still figuring out how to balance the power of these tools with the technical constraints of the models themselves.

To plan or not to plan, that's the wrong question. Rather than a binary yes/no, planning exists on a spectrum. The real question is which approach fits your current task and working style.

Different developers approach planning in different ways. One builder might draft detailed pseudocode before touching a keyboard, while another practices test driven development to let the architecture emerge organically. You'll find teams sketching complex diagrams on whiteboards and others spinning up fast prototypes to "fail fast" and refactor later.

If planning is a spectrum when coding manually, why wouldn't it be a spectrum when using an agent to code as well?

AI agents are often described as brilliant, overeager interns. They're desperate to help, but sometimes that enthusiasm leads to changes you never asked for. This is by design: the large language models powering agents are trained to be helpful. But in code, unchecked helpfulness can create chaos. Even with clear instructions and a meticulous plan, you might hear, "Let me just change this too…" A modification that's either unnecessary or, worse, never surfaced for review.

Sure, you can scour git diff to find and revert issues. But in a multi-step process touching dozens of files, untangling one small, unwanted change becomes a manual nightmare. I've spent hours combing through 70 files to undo a single "helpful" adjustment. Asking the agent to revert is often futile, as conversational memory isn't a snapshot of your codebase.

You've heard the buzz: AI is reshaping our work. Maybe you've tinkered with ChatGPT, or your company is pushing you to "level up." But between the hype and the endless tutorials, a gnawing question remains: how do you move from theory to building something real?

The answer is practice. Not just following steps, but creating, problem-solving, and learning by doing.

That's why we're launching Advent of AI, a 17-day challenge series starting December 1st. Whether you're a beginner taking your first steps or an advanced developer exploring AI agents, this is for you. Each weekday, you'll get a new, hands-on project designed to transform you from an AI spectator into a confident builder.

"Migrate my app from x language to y language." You hit enter, watch your AI agent spin its wheels, and eventually every success story you've heard feels like a carefully orchestrated lie.

Most failures have less to do with the agent's capability and more to do with poor prompt and context strategy. Think about it: if someone dropped you into a complex, unfamiliar codebase and said "migrate this," you'd be lost without a plan. You'd need to explore the code, ask questions about its structure, and break the work into manageable steps.

Your AI agent needs the same approach: guided exploration, strategic questions, and decomposed tasks.

I code best when I sit criss-cross applesauce on my bed or couch with my laptop in my lap, a snack nearby, and no extra screens competing for my attention. Sometimes I keep the editor and browser side by side; other times, I make them full screen and switch between applications. I don't like using multiple monitors, and my developer environment is embarrassingly barebones.

The described setup allows me to fall into a deep flow state, which is essential for staying productive as a software engineer. It gives me the focus to dig beneath the surface of a problem, trace its root cause, and think about how every fix or improvement affects both users and the system as a whole. While quick bursts of multitasking may work well for other fields, real productivity in engineering often comes from long stretches of uninterrupted thought.

Recently, my workflow changed.

You shouldn’t need a credit card to vibe code with goose. While goose is completely free to use, the reality is that most performant LLMs aren't. You want to experience goose in action without breaking the bank or jumping through hoops. We've been thinking about how to make that first step easier for newcomers to goose.

That's why we're thrilled about our newest provider integration: Tetrate's Agent Router Service. New goose users can get $10 in credits to use goose with any model on the Tetrate platform.

Working with AI tools can feel like working with a flaky, chaotic, but overconfident coworker. You know, the kind who forgets tasks, lies unprovoked, starts new projects without telling you, then quits halfway through. It's enough to make you say: "Forget it. I'll do it myself." But before we write off AI entirely, it's worth understanding what's actually happening under the hood so we can avoid common pitfalls and make AI tools worth using.

"The best AI agent workflows go beyond demos. They deliver real productivity."

The DevRel team at Block is a huge fan of PulseMCP. Their weekly newsletter has been an amazing way for us to discover trending MCP servers and stay in the loop with any changes within the ecosystem. When the PulseMCP creators, Mike and Tadas, shared their goals of using Goose to help automate the boring parts of their newsletter workflow, we were excited to see what they'd build.

Their implementation showcased exactly why we built Goose's feature set the way we did, and they documented the entire journey to help others learn from their experience.

When my team launched Goose in early January 2025, we knew we had something special. We built a free, open source AI agent that leverages the Model Context Protocol. It was inventive in its approach, offering developers a local solution with the flexibility to bring their LLM of choice.

The LLM Cost Problem​

After using the product internally for a few months, my teammates were eager to share Goose with the developer community through workshops and hackathons. We wanted to provide hands-on experiences where people could actually build with Goose, because that's how developers fall in love with a product.

But we hit a thorny challenge: while Goose is free, high-performing LLMs are not.

I built Postman meets Google Docs for 10-year-olds.

Cue record scratch.

Cue freeze frame.

Cue movie cliché.

You're probably wondering how I got here.

Developers deserve to have fun. There was a time when the internet felt magical. I remember going to the library just to create a character on The Doll Palace. At home, I'd spend hours changing fonts with WordArt. But as I grew up, the industry did too. We've shifted away from marquees and glittery cursors. Grown-up me started using ones and zeros to build reliable systems for insurance, banking, and healthcare companies. There's pride in that, but it's harder to justify doing something just because it's fun.

That's why I tapped into my inner child and used Goose to build a UI that reacts to users' emotions.

Localhost Ports Hoarding​

I'm perpetually drowning in open tabs. Yes, I do need Bluesky, ChatGPT, Claude, Goose, Cursor, Discord, Slack, Netflix, and Google Docs all open at the same time. I've learned that tab management isn't my only vice.

"Hi, my name is Rizel, and I'm a localhost ports hoarder. 👋🏿"

Ratatouille isn't just a heartwarming (and slightly unhygienic) film about a rat chef. It's also analogous to a popular tech trend: AI agents and the Model Context Protocol (MCP).

"Stop using AI," reads yet another viral post. I get it. It's frustrating to review a colleague's auto-generated work, filled with AI's classic giveaways like generic code comments and phrases like "In today's fast-paced world..."

Still, AI plays a pivotal role in my career. I don't rely on AI to do my work, but I use it to help me brainstorm and work more efficiently. The introduction of Model Context Protocol (MCP) has made this even easier. MCP is an open standard that gives AI tools the context they need to be useful in the real world. It enables AI agents to interact with APIs, apps, and systems in a structured way. I use Codename goose, an open source AI agent built on MCP.

Here are 11 real ways I use AI Agents without sacrificing authenticity, creativity, or quality: