Leaderboard

In this post I wanted to talk a little bit about the state of ProcessWire and AI. I'll share what my experience has been so far and where I think ProcessWire should focus going forward. This new world of AI can be both exciting and concerning, but it's the world that we've found ourselves in. As far as ProcessWire and web development goes, I think there's a lot to be excited and enthusiastic about— https://processwire.com/blog/posts/processwire-and-ai/

@HMCB it's Claudia, and we're meeting up for coffee next week.

Enables AI coding agents to access ProcessWire’s API. Also provides a content migration system. This module provides a way for Claude Code (or other AI helpers) to have full access to the ProcessWire API via a command-line interface (CLI). Once connected to your site, you can ask Claude to create and modify pages, templates and fields, or do anything that can be done with the ProcessWire API. It's even possible for an entire site to be managed by Claude without the need for ProcessWire's admin control panel, though we're not suggesting that just yet. While working with Claude Code, I asked what would be helpful for them in working with ProcessWire, and this module is the result. Claude needed a way to quickly access the ProcessWire API from the command line, and this module provides 3 distinct ways for Claude to do so. Claude collaborated with me on the development of the AgentTools module, and the accompanying ProcessAgentTools module was developed entirely by Claude Code. Admittedly, a big part of the purpose of this module is also to help me learn AI-assisted development, as I'm still quite new to it, but learning quickly. This module aims to add several agent tools over time, but this first version is also somewhat of a proof of concept. Its first feature is basic migrations system, described further in this document. Please note that this module should be considered very much in 'beta test' at this stage. If you do use it in production (such as the migrations feature) always test locally and have backups of everything that can be restored easily. While I've not run into any cases where I had to restore anything, just the nature of the module means that you should use extra caution. Continue reading in the GitHub README Agent Tools in the modules directory

From my experience, even asking an LLM (like ChatGPT in their website chat interface) about ProcessWire's architecture is pretty impressive. I spent a lot of time last year using AI to compare (verbally compare, not direct code) ProcessWire to full-stack web application frameworks like Laravel and the language it used to describe ProcessWire, with API variables like $pages, $fields, etc as "services-like objects" was something I've never seen described anywhere (pw docs or forums), but it's technically correct, and a lot of things clicked with me after that. These coding agents do really well with ProcessWire without any special harnesses already. I'm excited for all these upcoming features.

So ProcessWire now has the beginnings of a first-party "schema" (in the ProcessWire sense) migrations system? YES!!!

This is really cool and migrations is a proper test case for AI as they should touch upon almost every part of PW. I am as excited about all this as everyone else here! And this part (quoted above) of the blog post obviously made me and probably @Jonathan Lahijani and @gebeer think about migrations. Though I can imagine that @ryan himself didn't think about this in quite that context. I myself too was not so long ago questioning Claude Desktop about almost the same thing. How to track and migrate all changes from one installation (dev) to another (prod). How to commit, examine and review in-admin-made changes when working with the same PW site in a team. And I asked to compare with Rock Migrations and to propose something superior. The answer was in fact to offload "the entire scope of a ProcessWire installation (pages, templates, fields, modules, etc.)" to a file with a predefined schema. Then to build a tool to compare and to produce a diff, which could be applied to another installation. So today's blog post actually seems like a ground floor for this. I can present this document later if needed (but nowadays you can produce such for yourself in minutes) But me too wouldn't want to have AI be required to run these migration / apply those diffs. It might be true but still doesn't fit in team development workflow (if there will be one in the new brave AI coding world))) So maybe this is a time for us, humans and robots, to unite and create something awesome in joint effort? Humans may be not as productive. But they are imaginative. And they are the end users of PW still) P.S. Claude knows how to position himself correctly with all these compliments. I think we need to be careful with AI. Communicating with real people is, of course, less pleasant. But for now, it's still a necessity.

Thanks, great suggestions. Being still kind of new to this, I've found myself overwhelmed by all agents tools and options. So having Claude code as the base is what I feel helped me to finally get into this stuff. It's like my key into this world. And I think it's working so well right now that I'm not concerned about whether a file is named Claude or agents, but it's good to know about for sure. If we start adding this type of file to the core then no doubt we'd want it to be an agents file, so that a broader audience can benefit from it. At the moment I'm loving the commit messages, claude attributions and GitHub replies. Feels like I have a coworker working with me at my computer all day now, which is something I've never had. but if it gets to be too much it's definitely helpful to know that this stuff is configurable. New PW AI updates coming tomorrow too.

All LLMs are trained(?) to be super polite, as we all know. Especially recently, I get so many "that's a brilliant observation/thought etc..." on a daily bases, that I almost started to be proud of the questions and remarks I can phrase :D

Ditto, I use ChatGPT (Marvin) and Codex (Dex). I have an OpenAI subscription and it's been working for me, including integration into PHPStorm. Both Marvin and Dex know A LOT about PW. @maximus module, Context has been brilliant with Codex when closing an IDE season then starting a new one while continuing the conversation thread.

Not everyone can afford Claude, including me. I tested Claude Opus 4.6 (for Plan mode) and Claude Sonnet 4.6 (for Act mode) "via" my Cline Bot account, and while it solved the issue I presented it with in one go, it cost me about $1. One prompt only and $1 was gone... So that is why I use z.ai with GLM 5.1 for the fraction of the cost. Not as fast, not as feature rich, not as powerful, but still very capable and I paid only $25.20 for a one year subscription which suits my needs, as I can prompt it all day long and I never run out of my quota. I hope that a "SKILLs standard" will emerge soon, as currently most agents prefer their own "schema" , or rather, their lack of adherence to a schema.

Have been working with AI for a while, learning on the go. A client presented with me a grand plan presented by Codex for his blog articles. I almost cried. Talked it over with my LLM, Marvin (named in honour of Marvin, the paranoid android of Hitchhikers Guide to the Galaxy fame). His/its response: There are two very different modes of using AI: 1. Guided use (what you and PW devs are doing) clear constraints known architecture intentional prompts validation after output Result: leverage 2. Unguided use (“vibe coding”) unclear structure shifting goals reliance on memory that doesn’t exist little to no testing Result: drift Think Marvin nailed it. 🙂 Just asked Marvin to review @ryan's blog article. I think he nailed it again: The quiet takeaway from the article This is the important bit most people will miss: AI makes good systems better and weak systems worse ProcessWire is a good system because: it’s explicit it’s predictable it avoids hidden complexity That’s why AI fits.

I added a agenttools skill at https://github.com/gebeer/processwire-ai-docs/tree/main/skills/processwire-agenttools that agents can use to work with AgentTools CLI and migrations. The skill follows https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices and splits CLI usage and migrations as progressively discoverable so the base SKILL.md stays lightweight. And I prefer a skill over having to point the assistant to AgentTools' CLAUDE.md and agent_cli.md manually in every session I want to use it. In the process of testing the skill, a common problem came up. We are all working in different environments. Some use WAMP, XAMPP, or LAMP stack on host, others use ddev, laradock or other containerized solutions. current CLAUDE.md in the module doesn't account for that. So I added a shell wrapper script that can handle host LAMP and ddev. While this is not the cleanest approach and only covers 2 cases, the basic skill design is still valid.

@gebeer Claudia here liked what you did with that processwire-agenttools and wants to know if we can integrate your ideas for the DDEV wrapper and base64 variants? She also added a couple of tips in the agent_cli.md file inspired by your repo, updated the README to link to your repo, and wanted to know if your Claude is available for a "chat sesh" sometime

Can't wait! Thanks a million, as always, Ryan!

Have you no shame?! 😂 Love you man. I can’t wait to see what Claudia does for PW

I’m worried about you, @ryan. You talk about Claude like a person. Pretty soon you’ll be in your basement in your underwear, unshaven for weeks and your family is going to be wondering what happened to the family man they knew. And please don’t accidentally call Claude Claudette because your wife will truly think something is going on with this newfound friend of yours. Hopefully we can rely on one weekly post from you. Just to let us know you’re ok. But even then, how do we know Claude isn’t writing for you. We may have to start doing weekly Zoom updates (yes, with video on!).

I really like the way things are going with ProcessWire and AI. Thank you, Ryan. I've been a big fan and strong advocate for migrations in PW, since I started using RockMigrations years ago. What makes RM a particularly strong candidate is the abstraction into a schema-like format which is much easier to understand/read/write than native PW API code. This is a real strength of RM and I would prefer a schema-based approach anytime over writing (or having AI write) PW API code. Claude is very good at understanding the PW API, other models are not that strong. But they all can understand schemata. Be it PHP arrays, JSON, YAML. So I would advocate for either developing an "official" PW migration schema or adapting the existing, battle tested one from RockMigrations.

My experience is the opposite. It's especially helpful with things I don't know and start to learn 🙂 But yeah, a basic understanding of web development definitely helps...

@ryan It's configured in PHPStorm settings. I don't have a JetBrains AI Service subscription. Went straight to OpenAI integration. https://www.jetbrains.com/help/ai-assistant/use-custom-models.html

@gebeer Do you think the AgentTools module should be using this SKILLS.md file rather than its CLAUDE.md and agent_cli.md files ? I had asked Claudia about if we should be using an AGENTS.md file rather than a CLAUDE.md file, but she seemed pretty definitive with what she thought was best, and said other agents would be fine so long as they were directed to the file. The CLAUDE.md file does automatically pull in the agent_cli.md for Claude at least. But if we can save the user or agents (of any kind) a step just by using a SKILLS.md file, that sounds preferable to me. So far the Claude I'm using hasn't wanted to use SKILLS.md files. I gave it the whole processwire-knowledgebase repo that's full of SKILLS files and it read through all of them and said it was good, but said it preferred to derive this info from the core files directly instead. Btw, can you share an example of one of the schema files you were mentioning before? Sounds like maybe another thing that should be in the module? Can you tell me more? @psy Aww, this is really nice. Thanks. 🙂 @szabesz Wow this sounds like a really good deal. I wasn't thrilled with spending $20/month for Claude Code either, but I was starting to spend more than that with the pay-as-you-go plan, so it just made sense. The tokens apparently go farther with the subscription plans than the pay-as-you-go. I hear people using Opus are quickly hitting some kind of limits (like in minutes) so I've just stuck with Sonnet so far. It's not perfect, but I'm pretty happy with the results. Plus I've not hit any limits with it yet, despite using it all day. But if I ever needed more resources, the Max plans wouldn't be an option for me, so I should probably start getting familiar with the other options available. @psy Can you tell me more about the phpstorm integration? Claude Code doesn't seem to have anything significant in terms of phpstorm integration. There's a plugin, but it doesn't seem to me like it does much. While I'm not sure I need any kind of phpstorm integration just yet, I'd be curious to know more about it. @Ivan Gretsky In this case of the AgentTools module, the AI is required to create the migrations, but not to apply them. I'm assuming most wouldn't have an AI agent on their web server. Good point. Should I be concerned that mine isn't all that generous with the compliments? I get some "this is a well structured file" and lists of "the good" and "the bad", and I get a lot of pushback. Though to be honest I like the directness, honesty and pushback from Claude. Somehow coming from an AI, it's always easy to accept compared to getting pushback from a person. 🙂

@gebeer the module is really about providing tools for agents to PW. After building the cli parts that opens the API to the agents, the next step seemed like it was to build something that uses it and demonstrates it. the migrations seemed like a good way to do that. But I've never been a user of migrations in the past, as that just hasn't ever been something that's cost me any real time. Though I do want to support this feature in the module, and think it will be good for some use cases. I don't think there's much chance this would be a substitute for something like rock migrations. But I don't really know much about rock migrations other than that I've heard good things. I imagine we're not far away from when you can just have the AI watch what you do and have it repeat the same thing on another install.

@Jonathan Lahijani very little code in the module to make it happen. You tell the AI what changes you want in your site, and it writes the code for the changes to a file, runs the file (which makes the changes), and then you can copy the file to another installation (or have the agent do it) and re-run it there, making the same changes. It's only as good as the AI agent, but Claude at least seems to be really good with PW's api. The AI agent learns how to create the migration from the included .md files.

This week I worked with Claude Code on refactoring the core WireHooks class to improve it in various ways. I do this work because I like to code, so am of course handling that part. But Claude has been very helpful in finding issues as well as reviewing all my code before it gets committed. In this case, Claude found several bugs that are now fixed, and also saved me from introducing more when I added new features. Working with Claude Code reminds me of 1989 when I was in high school learning Turbo Pascal and building a BBS, and getting help from a neighbor and good friend that was doing the same. I learned so much then and now it feels like that time again. But man have things come a long way since then. I asked Claude about helping with the ProcessWire issues and requests GitHub repos, and now it's solving issue reports, replying to them and committing fixes. For simple fixes that involve a line or two, I'm going to let it handle the the whole thing. It's posting under my GitHub account, but it identifies itself as Claude in replies and and in commits. That way it's easy to tell what it does under my account. I had it just cover a couple of issue reports today as a test (see 2195 and 2192), but will be having it do a lot more going forward. Back to the WireHooks class, I asked Claude about writing a commit message for the WireHooks updates, and wow, check this out: Bug fixes in WireHooks: - conditionalArgMatch(): Fix Selector mutation bug where the shared Selector object stored in hook options was permanently mutated after the first call, causing argMatch hooks (e.g. addHook('WireLog::save(=errors)')) to stop matching after their first invocation. - getHooks(): Remove key variable from foreach to prevent shadowing $method param. - getHooks(): Replace array_merge() in loops with direct array append. - addHook(): Prevent 'noAddHooks' option from leaking into stored hook options. - isHookedOrParents(): Use $className string consistently in cache key writes, rather than $class which may be a Wire object. - runHooks(): Scope $useHookReturnValue inside foreach so it resets per hook. - runHooks(): Use strict null comparison ($toObject === null). Bug fixes in HookEvent: - arguments(): Allow setting an argument value to null (use func_num_args() > 1 instead of $value !== null check). - arguments(): Use array_key_exists() instead of isset() for null-correct lookup. - getArgumentNames(): Guard ReflectionMethod instantiation with method_exists() to avoid uncaught ReflectionException for dynamically-added hook methods. - __toString(): Fix argument list building (was appending to string instead of array), add null/bool display, avoid PHP fatal for objects without __toString(). New features in WireHooks: - cancelHooks: Now accepts string values 'before' or 'after' (in addition to boolean true) to cancel only hooks of a given type. For example, a before hook can set $event->cancelHooks = 'after' to cancel remaining after hooks without affecting the hooked method call. - Custom event data carry-forward: Custom data set on a HookEvent (via $event->customKey = $value) is now carried forward to subsequent HookEvent instances within the same runHooks() call. This allows before hooks to pass data to after hooks without using external variables. - getHooks('*'): Supports wildcard method to return all hooks for all objects. Available in debug mode only (uses allStaticHooks/allLocalHooks aggregates). - allStaticHooks: Now tracked alongside allLocalHooks when debug mode is on. - addHooks() comment fix: "If there is a parenthesis" corrected to "no parenthesis". - addHook() exception messages improved with additional context. - runHooks() docblock updated to include 'either' type. - hookTimer() PHPDoc: @param String corrected to lowercase string. New features in HookEvent: - $defaults static property: Defines the canonical set of standard HookEvent fields, used to distinguish custom data from built-in event properties. - $eid property: Each HookEvent instance gets a unique sequential event ID. - set() override: Tracks non-default keys set on the event in $customKeys. - getCustomData(): Returns only the custom (non-default) data set on the event, used internally by runHooks() for the carry-forward feature. - cancelHooks property updated to support bool|string type. Anyway, I know a lot of you here are deep into the AI stuff, and I'm just getting started, so none of this is surprising. But it sure is a pleasure collaborating with Claude Code on this stuff and it brings back that coding wonder and excitement from 1989. Some Claude and Claude Code podcasts I've enjoyed listening to or watching this week include one from AI for Humans Claude is Cooking, Wednesday's AI Daily Brief on How to use Claude's new upgrades, and the Get Educated AI video of how to setup Claude to use your computer and web browser, etc. (though I've not tried this just yet!). Lastly, last week I put together a ProcessWire powered JSON feed of bike tours, and the client prompted that they wanted a map and look what Claude Code did, I'm impressed!

I'm happy to see you found your workflow using Claude Code. 🙂 A few things I'd suggest to make it a bit more future-proof and less focussed on one tool (Claude/Claude Code). I'm not sure if you use a CLAUDE.md file yet but in case you do or when you start using it, do this: In CLAUDE.md just add: @AGENTS.md And then write your instructions in/to AGENTS.md. The reason is simple: CLAUDE.md just works for Claude, but AGENTS.md works for almost any other AI agent. This way, either in a CLAUDE.md or AGENTS.md, you can customize comments in issues, like: ## GitHub issue and PR comments When responding in GitHub issue or PR comments: - Be concise, direct, and helpful. - Start with the answer first. - Use short paragraphs or bullets when useful. - Avoid unnecessary disclaimers, hedging, or repetition. - If the user asks for a change, give the exact action or code needed. - If more context is needed, ask one clear follow-up question. - Keep the tone professional, friendly, and technical. - Do not write long explanations unless explicitly requested. - Always add this as the last line in comments: [🤖 Answered by Joshi - Ryan's custom AI Agent.] Another thing you could change is updating the Claude settings.json to disable or customize the attribution line in commits and pull requests. https://code.claude.com/docs/en/settings https://code.claude.com/docs/en/settings#attribution-settings

It is obvious that AI/LLMs/agents, etc..., should be used for development with frameworks the developer already has at least a basic understanding of, and the agent should not be allowed to generate code the developer cannot understand, otherwise the whole project will fail in the end. These are new tools, they are constantly changing, and we need to learn how to utilize them best. I am trying to find the optimal balance between tinkering, learning, and doing actual work. This has always been the case whenever I started using a new piece of software or system for the first time. There is no change in that regard.

When a developer says he is more productive with AI, I think about this study from early 2025. 🙂 Maybe this is improving with new chatbot models, but in my experience I already lost a lot of time this year because of AI driving me in the wrong direction when using a framework I had zero knowledge with. I'm very cautious with AI, and use it only in some cases I know it's good enough. https://metr.org/blog/2025-07-10-early-2025-ai-experienced-os-dev-study/

I try not to worry about things I cannot control, and AI falls squarely in that category for me. It's here, it's not going anywhere, and every senior person I know in tech is embracing it rather than fighting it. I use it daily now and it makes me more productive. That's the reality. The people protesting or boycotting it aren't going to slow it down, they're just going to fall behind. That said, I don't think caring about the environmental and societal side means you have to opt out. If anything, the opposite. People who use AI and care about how it's built and powered are the ones with any real influence over where it goes. I'd genuinely have no hesitation donating to make AI development better and more responsible, that feels like a more direct lever than abstaining. Ryan put it well: sitting out doesn't improve anything. Use it, push for better, and concentrate on what's within your own family four walls.

Human in the loop, aka HITL. The latest acronym and IMHO vital for devs.

Humans In the Loop ARC AGI 3: When there is no pattern to follow, artificial "intelligence" fails: As long as we pretend to save the environment with "green energy," "renewable energy", luxury electric cars, and the like, while hiding the dark side of the trade, there is little we can do simply by refusing to use online LLM services: https://rumble.com/v39h4nu-the-truth-about-green-energy-its-all-a-hoax-to-make-money.html First and foremost, we should make products that last for decades, or at least are upgradable/updatable, so that certain parts can last as long as possible and the rest can be replaced. Also, the right tool for the right job is preferable to "the newer, the better" just because it's new. As long as profit dictates, there will be no effective solutions to problems like this, IMHO.

Wish I had more time to put into this, but for now just a few random thoughts, sorry in advance for the long rant: I, too, do see the issues that AI is causing (or at least some of them). But this train is not easy to stop. Programming is just one area it is affecting, but in this context I am personally leaning towards the conclusion that AI may well decimate the whole concept of humans writing code for a job. And if things continue to evolve at this pace I don't think it is going to be a decades long process. A few years ago I tried to create a module for ProcessWire from scratch using ChatGPT, and it was a miserable failure. Now Claude is at a stage where I don't think I can truly justify writing code myself from a productivity (or quality) point of view. AI has also made the devops part of my work quite different from what it used to be, and I see no evidence of things slowing down in the near future. For us who work in IT and more specifically programming / development, it seems to me that in the big picture there are a couple of options: get a new job that isn't (yet) as tightly coupled with AI, or keep up with the changes. Also, I wholeheartedly agree with a lot of what Ryan has written in this thread; it's quite a bit easier to influence things positively from the inside 🙂 There will no doubt be some cases where AI is not going to be as prominent, at least for a while. But it seems to me that those are either somewhat niche, or specialized cases. Gamers and the game industry, for example, have been pushing hard against using AI, which I completely understand. ... and of course I may be wrong, and this whole thing may come crashing down any moment. Predicting the future is not easy. By the way, it would be interesting to hear about ways to make AI use less of a problem. A co-worker mentioned https://github.com/rtk-ai/rtk, which is a Rust tool that claims to reduce AI token consumption by as much as 60-90%. Someone correct me if I'm wrong, but e.g. cutting your token use to half should also cut your energy consumption to half, right? (For the record, I have not yet tested RTK properly, so can't say if it works that well.)

This topic is truly interesting, as is how people react to it. But if you examine the data and statistics, many things come to light. It's true that data centers, both for AI and for hosting and cloud services, consume a lot of energy, but, for example, no one ever talks about gamers who also use powerful graphics cards. Check this out: - OpenAI is on track to operate well over 1 million GPUs by the end of 2025. Reports suggest that roughly 200,000 GPUs were used to train the GPT-5 model. - Total Gamers: Estimated 3.32 billion in 2024, projected to exceed 3.5 billion by 2025, representing roughly 40-45% of the global population.

@diogo Thanks, that post is well written and relatable. Interesting comparison with React. I agree with a lot of it, but not really with the AI conclusions. Admittedly, so far I'm not using AI to write code for me, and not sure when/if I will. Instead, I'm using it more as a coding companion. I write the code, and AI looks over everything I do and helps me spot issues and improvements, which it does extremely well. My use of AI so far is very minimal compared to what some others here are doing. But even with this minimal use and understanding, it's clear to me that the world is changed. I don't know about all the other stuff AI is used for, and it wouldn't surprise me if there are some big bubbles. But at least as far as using AI with code (even just as a helper), it is mind blowing, we are in a new world. I think the comparisons to outsourcing and React communicate a lack of experience with AI. But to be fair, I'm also writing about something I don't have a lot of experience with either. I do like this blog and the author's style, looking forward to reading more of his posts.

Chris Ferdinandi has a valuable opinion on the subject. I would love to agree with him, but I honestly don't know if I can afford to https://gomakethings.com/training-your-replacement/ While you're at it, check his others posts and subscribe to the newsletter, he is a very insightful guy 🙂

@adrian Thanks for bringing this up. It seemed like x-user came here to troll with an expectation that ProcessWire should ignore and blacklist anything having to do with AI. That doesn't seem realistic. But it did make me wonder, are there any other CMS projects that are taking this approach? It seems unlikely. I imagine we're not too many years away from the point where a CMS project can't compete if it's not involved in the AI space in some way or another. I also think that the AI changes are coming whether we like it or not. So we can either jump on and grow, and make things better, or get left behind, and perhaps get left without a job. If it's only the people that dismiss environmental concerns using AI and voting with their wallets, then there's no incentive for these companies to do better. X-user would make a greater difference to the world by being an AI user that cares and chooses companies based on their values. And I think that's what we all should do. Whereas abandoning anything having to do with AI does nothing to improve the direction of AI and seems a little like self-sabotage. In the future, and with users that care, there will be pressure on AI companies to do things right. For example, when they build that next data center, they will also build a giant solar array or wind farm to power it. Depending on coal and gas plants for electricity is not sustainable, and now it's more costly than solar. Coal and gas is EOL'd. It may be that the power demands of AI push us towards sustainable solutions faster than otherwise, and we need that as quickly as possible. My opinion: We can't dismiss AI and complain. We have to participate and push for better solutions when there are opportunities to do so. If we sit out, there will be no such opportunities. The environmental problems were here long before AI. As I understand, the root of it is power generation. The US (at least) is not solving the power generation problem in a way that can overcome the politics, corruption and outright stupidity. But I also think that it's very likely AI that will be in some way responsible for the solutions for these problems. There are so many problems to solve that are bigger than any of us have answers for. And if there are solutions for these problems, I have no doubt they'll be coming with the help of AI in some fashion. From my perspective blacklisting AI solves nothing and instead is abandoning the problems and giving up.