Rich Tabor

Rich Tabor

@richtabor.com

Writes about the future of WordPress, Blocks & Design ✴︎ Product @automattic ✴︎ Making @WordPress

1.1K followers 4 following107 posts

WordPress Almost Didn’t Happen What if Matt had joined Google instead of starting WordPress? The internet might have felt a little less like ours. In his recent post, Matt mentioned “How the internet might have turned out differently if I had taken that job, as my mom wanted me to (because they…

rich.blogWordPress Almost Didn’t HappenWhat if Matt had joined Google instead of starting WordPress? The internet might have felt a little less like ours. In his recent post, Matt mentioned “How the internet might have turned out differently if I had taken that job, as my mom wanted me to (because they offered free food).” Funny line. But also wild to think about.

My typical (Next.js) dev flow: 1. Plan with Claude 2. Build alongside Claude Code 3. Copilot reviews 4. Check out the Vercel preview to confirm 5. Deploy knowing it actually works It's like having a "on-it" dev team that's always ready to go. Unreal.

Write prompts, not issues.

Copy my Linear product manager subagent to make great issues on the fly, without ever leaving Claude Code. Works great for when you want to record something to do later. agents.foo/linear-prod...

agents.foolinear-product-manager | Agents.fooUse this agent when you need to create, structure, or manage issues in Linear, or set up MCP Linear integration. This includes writing well-formatted issue descriptions, selecting appropriate projects and teams, setting priorities, adding labels, ensuring issues follow best practices for product management, and configuring MCP Linear for automated workflows. The agent understands Linear's data model, MCP (Model Context Protocol) integration capabilities, and can help with issue templates, epics, project organization, and MCP setup. Examples: User wants to create a new feature request in Linear - 'I need to create an issue for adding dark mode to our settings page' - I'll use the linear-product-manager agent to help create a well-structured issue for this feature request. User has just finished implementing a feature and wants to document a bug found during testing - 'I found a bug where the login button doesn't work on mobile Safari' - Let me use the linear-product-manager agent to cre

Those of us with dev skills AND the ability to think creatively are going to absolutely crush it. 💪 And if you can design too — you win.

I've been building Claude Code subagents for weeks. Finally wrote about the ones that actually stuck around in my workflow. Spoiler: they're way more boring than you'd expect (and that's why they work)

👀 rich.blog/agents-foo

This flow makes it so easy to deploy confidently. Claude Code → Copilot review → Vercel preview → Deploy This is how deployment should feel.

After building loads of Claude Code subagents, I'm sharing the handful I actually use most days. Not the flashy demos you see everywhere, but mostly boring—but super useful—agents that make me a little faster. My honest take on what agentic programming actually looks like in practice ⤵️

View full thread

What’s surprising to me is that we’ve already distilled agentic programming down to simple markdown files. No complex frameworks or orchestration layers. Just clear instructions about what you want the agent to know and how you want it to help. This feels like how AI should actually work.

I shared all my daily driver agents on agents[dot]foo and wrote about them. Full post: rich.blog/agents-foo

After building loads of Claude Code subagents, I'm sharing the handful I actually use most days. Not the flashy demos you see everywhere, but mostly boring—but super useful—agents that make me a little faster. My honest take on what agentic programming actually looks like in practice ⤵️

My favorite: A Linear product manager agent that creates perfect issues when I find bugs but don't want to lose coding momentum. It explores my codebase, finds relevant components, includes file paths, and writes issues that actually help. Like having a technical triage guy sitting next to me.

Which pair programmer is your top pick?

What's funny is that the best practices for using Copilot are the same as working with any other developer: → Have well-scoped issues. → Assign the right issues to the right person/AI. → Provide good docs/instructions. → Give feedback and iterate on pull requests.

Read them for yourself: docs.github.com/en/enterpri...

docs-internal.github.comBest practices for using GitHub Copilot to work on tasks - GitHub Enterprise Cloud DocsLearn how to get the best results from Copilot coding agent.

Kanso is the best blogging WordPress theme, hands down. If you want a blog as cool as mine, it's free & open source.

I baked in a couple color/font variations too. One-click vibes.

Download Kanso for yourself: rich.blog/kanso/

rich.blogMeet Kanso, my best blogging theme yetSince my latest design refresh, many folks have been asking about the WordPress theme I’m using and how to get it. So, same as before, I’ve made my blog's…

I don't vibe code. That's not me. I build with Claude Code every day, but I care about what's being built ⤵️

View full thread

Less debugging/more thinking. The best developers are better at prompting, better product leaders, better strategic thinkers, and better at tracking what changed in their codebase. The good news: those skills transfer whether you’re working with AI or humans.

So yea, I don’t vibe code. Full thoughts: rich.blog/i-dont-vibe...

I don't vibe code. That's not me. I build with Claude Code every day, but I care about what's being built ⤵️

View full thread

I don’t need to understand every technical implementation detail, but I need to understand how to prompt these systems effectively. And how to distinguish good output from garbage.

I typically scope ideas with Claude Code, log the issues I don't want to do asap with my Linear PM agent, then tackle implementation. When it’s time for a pull request, I have another AI pair programmer (usually @Copilot) handle the initial review. I'm more of the technical lead making the calls.

I don't vibe code. That's not me. I build with Claude Code every day, but I care about what's being built ⤵️

The difference is partnership vs just getting code generated. Vibe coding = blind trust. AI-augmented coding = guidance. Will this scale? Is the architecture sound? Does it handle edge cases?

I Don’t Vibe Code I don't vibe code. You know what I mean by vibe coding? That approach where you throw prompts at an AI, get code back, and ship it without caring about what's actually under the hood. It's the "move fast and ship" mentality taken to an extreme. That's not me. I build with Claude…

rich.blogI Don’t Vibe CodeI don't vibe code. You know what I mean by vibe coding? That approach where you throw prompts at an AI, get code back, and ship it without caring about what's actually under the hood. It's the "move fast and ship" mentality taken to an extreme. That's not me. I build with Claude Code every day, but I care about what's being built.

so, why do you choose @wordpress?

if your AI product can be replaced by a good prompt to ChatGPT, you don't have a product. you have an expensive api call.

when AI gets so good that anyone can build software, what happens to software quality? democratization is great until everyone's shipping mvps with no one maintaining them. maybe there'll be an AI to clean up the mess.

now that you can build an interesting prototype in hours, what's the last thing you built? i'll go first: made a telegram ai nutritionist that logs meals and calls out my eating patterns (good, but especially bad). your turn.

DM me if you wanna try it/give feedback.

is building software finally democratized?

ai code generation actually feels like collaboration now, instead of fancy autocomplete.

stop bikeshedding on interfaces, build the intelligence first.

the ai tool race is so interesting because nobody can build a moat. cursor today, claude code tomorrow, something else next week maybe. each are basically playing leapfrog. pure product competition with almost zero switching costs. x.com/richard_tab...

build ten, ship one, trash nine. Claude Code makes this cycle so fast i can afford to be ruthless about what actually matters.

rich.blog/ridiculous-...

rich.blogRidiculous Swings (with AI)I used to kill ideas before they had a real chance. Every spark of curiosity met the same mental gate: Is this worth…

ai doesn't make typos, but it absolutely makes terrible architectural decisions (if you let it run wild).

every startup pitch: 'Cursor for _______ '

on the context engineering train yet?

using @diabrowser, this may be the first time i consider switching my default browser. i need these bookmarks to not look like an afterthought though.

it's risky move changing plan limits, especially without letting people know ahead of time. the season of vc-subsidized AI tokens is closing fast. once you prove product-market fit, free lunch is over. x.com/cursor_ai/s...

shipping ≠ done; it’s only the first draft for learning, iterating, refining.

how are you branding yourself? let's see your personal website. add it below 👇

design is the differentiator now. for real.

what even counts as “good” code anymore? zero duplication, passing tests, clear intent—what else makes the cut?

what tripped you up most when starting your last @wordpress site? share, so we can fix them👇

anyone else still grabbing domain names for your kids?

don’t fake ux chops. prompt ChatGPT (or any model) with your scenario, grab insights, and benchmark against proven patterns. too easy.

What Nobody Tells You About AI Coding Nobody tells you that AI-augmented coding makes implementation skills abundant and strategic thinking priceless.

rich.blogWhat Nobody Tells You About AI CodingNobody tells you that AI-augmented coding makes implementation skills abundant and strategic thinking priceless.