Devin Price

@rmelogli @jamesckemp @briancoords @KatieKeithBarn2 @ianmisner @pmgarman @BFTrick @MarcoAlmeidaPT I like a lot of things from checkout that come included. Address autocomplete, saved addresses, saved payment info across their network, fraud mitigation.

Happy Friday! Here’s this week’s #WooQuestionFriday for all the WooCommerce fans & makers out there 💜 💬What’s one Shopify feature or function you secretly admire—and wish WooCommerce had? @jamesckemp @briancoords @KatieKeithBarn2 @ianmisner @pmgarman @BFTrick @MarcoAlmeidaPT @remkusdevries @daveloodts @BobWP @bryceadams @MrBrianHaas @tommy_ecom @BrianHenryIE @SRHDesign @brentmackinnon @cipriangb @remicorson @kish2011_ @robinpietersen @devinsays @se_nadir @marinusklasen @wordpressjoe @codeagencybe @vyskoczilova @tnash @DaymoBrew @brettstone_ @PoeHaH @businessdad @colmtroy @simontomkins @neke989 @mark_jansen @toniievych @jonathan_dejong @chrisfromthelc @sinanisler @WPBundleHQ @toniievych @SternaleZA

@MarcoAlmeidaPT @KatieKeithBarn2 Ah, thanks for letting me know how that works. The gogcli does let you create and edit, but yes it command line so I’ve just been using in Claude Code.

@KatieKeithBarn2 @devinsays Yup, those are not real files, just links. I just checked, and all those I see on my mounted Google Drive folder are, without exception, 179 bytes regardless of their actual size.

Everyone’s raving about Claude Cowork but I don’t really work with files on my computer (which seems to be its main strength), and its browser and GoogleDrive integrations aren’t very good yet. Any tips on how to get more out of it?

@KatieKeithBarn2 I was hooking up more things today for other people at the company and realized they do have a built-in connector now. Is that not working for you?

@KatieKeithBarn2 I use Claude Code and have this package installed to access drive and email. gogcli.sh It works great! If you’re using Cowork, it might still work if it can access command line tools. I’d ask it.

@soundslikecanoe There’s a python sdk called “facebook-business”. Hardest part is the 5 minutes it takes to set up the facebook app and get the token, but Claude can talk you through it.

What's the easiest, least buggy way to get Meta data into my vibe coded app?

@marcusdburnette I suppose if it kept track of the converted images and could recover where it left off if the tab was closed it could work- but it's not ideal.

If you wanted to optimize 1000 images in your #WordPress site - JPG to webP - but you had to keep the tab open to do so, is that a deal-breaker?

@rmelogli @jamesckemp @briancoords @KatieKeithBarn2 @ianmisner @pmgarman @BFTrick @MarcoAlmeidaPT @remkusdevries @daveloodts @BobWP @bryceadams @rudrastyh If anyone is not saying Claude I'd have to ask for receipts.

Hello WooCommerce builders, it's Woo Question Friday! 💬What tool saved you the most time and/or money in the last few months? @jamesckemp @briancoords @KatieKeithBarn2 @ianmisner @pmgarman @BFTrick @MarcoAlmeidaPT @remkusdevries @daveloodts @BobWP @bryceadams @rudrastyh @MrBrianHaas @tommy_ecom @parvezvai @BrianHenryIE @SRHDesign @gridpane @brentmackinnon @cipriangb @remicorson @kish2011_ @robinpietersen @devinsays @se_nadir @marinusklasen @wordpressjoe @codeagencybe @vyskoczilova @tnash @DaymoBrew @brettstone_ @PoeHaH @businessdad @colmtroy @simontomkins @neke989 @mark_jansen

This article resonated. Instead of working on five tasks in sequence, it now makes sense to have five Claude sessions running the tasks in parallel- but it adds a huge amount of context shifting. hbr.org/2026/02/ai-doe…

@ianmisner WordPress/WooCommerce, Laravel (Data Service & PIM), Python apps (Inventory Forecasting, Production Tooling). Probably need to add a Nextjs app so we can we can get a bit more breadth... 😅

Are you a developer or agency that works across platforms? Or are you dedicated to just one?

I ran this today. It definitely provided some good recommendation for improving my workflows!

@RaananTz Pretty neat!

Been building something small: - Studied 2,000+ tech brand logos - Turned patterns into ready-to-use logos - All human-designed - $69 for a full brand kit

I just want everything to have a nice CLI interface now so I can stay in the terminal and easily hook everything into Claide. Just wired up gmail using gogcli.sh and it's great! (Thanks for the tip @jkudish!)

@nickmdiego Gosh. It's shockingly fast. Love it.

I migrated my personal site from WordPress to MDX files. Part experiment, part excuse to rethink my setup with AI. Some rough edges, but overall quite impressed.

I almost did this too when I refreshed devpress.com recently. I think it makes a lot of sense in the AI era. Nice site @nickmdiego! I did stay with WordPress though. AI tools can still get at all the content easily using WP CLI.

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

Yes, this. Opus 4.5 felt like a big shift. I haven't written code in the IDE for a few months now, which feels weird. But also closing PRs right and left and feel great about their level of quality.

Knowing that I can use all the transcripts at the end of review period also reinforces good 1:1 practices. If good feedback on performance (both positive and critical) is delivered consistently in 1:1s, then there should be no surprises at review time.

I'm doing performance evals this week. I wrote my initial draft, and then had Claude sync down all our 1:1 transcripts over the period + descriptions PRs. It used this context to provide so much good feedback. Definitely the best eval I've written in a while.

Introducing reviewbird - powerfully simple review collection and management for @WooCommerce reviewbird.com/2026/01/23/int…

If you use the "JSON Formatter" extension for Chrome, beware that's it's now injecting donation modals on checkout pages. Almost gave me a heart attack when I saw it on our production site. I assume your motives are good @callumlocke, but extensions should not do this!