How Ahrefs team is automating blog content with AI | Ryan Law (Ahrefs)

So Ryan, I was thinking today, it didn't take us too long to go from this AI thing, cannot really do great content to, oh my god, this is amazing, right? And here we are. You have devised an AI content automation workflow that you used to actually publish quite a few articles on the Trev's blog already. And these are good articles. These are great articles. And yeah, full disclosure, I haven't seen it yet. So I'll be checking it out alive together with anyone watching it. And I'm excited. Yeah. Do you want to say a few quick words on what people are about to see? Yeah, well, exactly that. So we've obviously been tinkering with using AI in our content workflows for years at this point. And it's always been very effortful. It can be helpful, but you have to sink a ton of time in edgy into it. There's still a lot of manual stuff that has to happen. I kind of feel like that's not the case anymore. It's a bit spooky, actually. I think since Claude code is probably the big thing that has changed this, this kind of agentic workflow where Claude can make some decisions on your behalf and you can provide it with some guard rails to actually make it do things in a certain way. So we've basically built, I call it the blog pipeline. And it is a kind of content automation system for new articles and for content updates. We've done maybe like 30 article updates with it so far. Wow. So published maybe 10, 15 articles got maybe something similar in progress at the moment. Yeah, it's been pretty good. Let's let's review it, show it to me. Yeah, let's do it. So obviously two things on the screen right now. We have a terminal and we have Claude code running in that terminal. So that is just a folder that I've called blog pipeline. And Claude code is living in that folder and it will do stuff in that folder for me when they ask it to. And we've got VS code over here. This is just a really good way of showing you the contents of that folder in a way that is a bit easier to understand. These are all the folders on the left hand side and they've all got files inside them. And I of course, I asked Claude, I said, I'm going to present this process on a podcast with Tim, give me some notes and visualizations to help explain this. So it added a handy little podcast folder here that has some notes and visualizations to make this a bit more interesting. But the basic premise is we have basically set it up such that there are maybe 23 or so skill files in here. You can see them in this folder. And what skill files that is a lot. And each of these skill files is basically a process. It is a process that at some point during creating content or updating content as a human, we generally do something like this or very similar to this. And this is just a mockdown document with very high. You lost me already. I kind of know what skills are, but you lost me already. Let's start from the beginning. Where does the process start? What do we start from? Do we start from a keyword? Do we start from an idea? What's the first step with this? Yes. So what you can do is, so this is a keyword idea of CSV. So it's a bit hard to see in this format. But basically, we've even set up a process right now where we can use the HF's MCP, which is obviously a way for Claude and other LLMs to access HF's data. And it will run a content gap analysis for us. And I then set up another process where we review this list of keywords and prioritize them. It looks exciting. Again, let me use my Eastern European politeness to bring you right to the point. We're not talking about keyword research. We're talking about creating content. So let's say we have a keyword or a topic. What do we do with it? We want to create content. All right, let me show you the clear list. So I can trigger blog pipeline. I can put in a keyword like keyword opportunities. And if I want, I can add some context to it and explain if there are points I want to add, I can add that. And off-claw goes and probably somewhere from between eight to 11 minutes from now, it will have a draft ready for review. It goes through about 12 steps at this point, as you can see. Oh, wow. It's actually telling me we've already, it's so clever, it's not letting me do the same one that we've already done before. So there's a research step. There's a reference step where it looks at existing articles on the HF's blog. There's an outlining step where it turns that into a structured outline. There's a product annotation stage where we look for opportunities to mention specific HF's products. There is a drafting phase, a citation phase for internal linking and finding supporting sources. There's a screenshot phase, which doesn't work very well, but we're working on that. A preview phase where you can actually preview how it would look on the blog. And then a formatting for publish phase where it will add in all the WordPress short codes, all the kind of stuff we need. And so basically when you ask it to create a piece of content around the given keyword, you are essentially launching a skill, which is a combination of steps where each step is a separate skill. And basically it has to finish them one by one or how does it work? Exactly that. Yeah. So you can either trigger the skills individually. So if you just want an outline, you can just ask for an outline by triggering that skill. But I've created these kind of master skills and they are very simple. They exist just to tell Claude to work through the other skills in a particular order. So this one's called blog pipeline and there's also update pipeline. And they literally just stitched them together and make Claude systematically work through these processes. Okay. Let me go straight into the phase of being critical of this. How is this not a slot? So what makes this process produce good content and not some generic stuff? Yeah. So that's a very good question. I think this definitely works best for one thing on topics that we have already covered in some capacity on the HF's blog. So one we published recently, content gap. We have never written an article about content gap, spist word, or is it keyword gap? One of these two content decay and keyword gap. We've written loads about these concepts generally, but in slightly different contexts. But we've never specifically targeted that keyword. But because this is able to go and look up existing HF's articles and anchor the content generation process in what we've already written, that goes a long way to getting rid of a lot of the problems you'd have. And there are also some topics, I think, I'm mainly using this for very straightforward informational topics, things that the LLM's know a lot about. There are opportunities for you to provide some context in it. There's a particular step in here that looks for opportunities to add information gain. So it actually reads the top ranking articles, summarizes the contents of them, and make suggestions for ideas that are not covered, but would be useful for the reader to understand within this. And I think AI is better at research than a person is as well. It can be faster and more systematic about it. You can go out and look up, you know, like to research articles, the latest stats, all these kinds of things. OK, so we definitely cannot go through all of your skills in the course of this podcast episode, because there is a lot of content in each of the skills. But I want you to start from the very first step of creating content and then go to the second and third and highlight maybe one or two kind of counterintuitive things. So for example, what might people get wrong if they would want to kind of recreate your process? Because I'm not sure that we want to just give out your process to everyone else. If we want just like open source it and have everyone else have access to the same process. And I would imagine that people would want to make it personal to them and their voice and their block and the style of content that they want. But yeah, walk me through each step and tell me if you uncovered anything interesting about giving instructions to AI on how to kind of improve the output of this specific step. If you know what I mean. Yeah, yeah. So you made a very good point there as well. I think the way we are using this is not as though this is the universal process that everyone the team has to follow. We've actually set it up such that the team can fork their own versions of this repo so they can make their own version of this folder. And they can modify it how they like this version has examples of content that I like and my writing voice and it's used as part of the article generation process. It would be super weird if SQ all the ways did the same thing use my writing voice for their articles. So it's very easy to actually update it and personalize it. And part of that might be changing the steps it goes through your own personal preferences. This is kind of very unique to me, I think. And that's kind of I think how this should be used. Another good point as well. You said you were surprised that how many steps there were in this process. I think that is actually a very, very good thing. The more steps you create, the more kind of introspection you have into the process, the better you understand it. The more opportunities you have to actually control and personalize how the content turns. out. So one very important thing I learned very quickly. Obviously I could just set this process in motion and it would give me an article in eight minutes and either it's good or it's bad. It's quite hard to work out how to fix and improve the process if you do that. So actually at every single step of the process you can actually see it will give me an output at every stage. So if something goes wrong, if I don't like the article or how it turned out, I can go back and see which part of the process it didn't work very well. I'm actually surprised that when you initially tried to launch this process, you said that you would wait like eight to 12 minutes because I was expecting that you would actually babysit it from step to step. So you would see the output of the first step. See if you want to refine it if it's according to your expectations and then allow it to go to the second step. But it's all just batched for you. And the thing is that's actually an interesting tip. This is exactly what I was looking for. Some tips for people of what they need to look for when they're building these themselves. And the tip is make sure that the process saves the output of the step. So if you don't like the final thing, you can go step by step and review at which step kind of it went sideways so that you could give it more instructions or refine the skill that refers to this step and make it do over again and see if that would help. But yeah, I'm surprised that you let it run for like eight to 12 minutes. Is this the point that you trust it well enough? You like your steps? Or yeah, probably is that I don't see any other reason why you would just let it cook for so long and follow all the steps. Yeah, great point. Very importantly, this is actually months and months of refinement has gone into this thinking and the process in here. And actually the last podcast episode we talked about where we had the custom GPTs. It was like the kind of baby version of this process. So a lot of the skills I have in here are things that we improved and refined and did hand hold and babysit as part of that process. So we'd already written these already tested these already made dozens and dozens of article outputs with them and kind of learn to refine them. So the thing that Claude does very well is just stitching those together and actually automating that process. Okay, let's go step by step. The first step I think I see it though it is quite small is research, right? Any like one or two tips to that you saw that would significantly improve the output of this step. So it does a combination of things. Maybe most people would assume you know keyword research is the most important thing to do and we have that in here. It goes and gets a bunch of hrefs data from the MCP, related keywords, parent topic, all this kind of thing. We don't have this yet but I've asked for it. What is more important I think is going and looking at the existing SERP, the content that is ranking and analyzing that and seeing the topics that are kind of consensus and commonly used there, opportunities to differentiate from that. That is what AI content helper is perfect for doing but we don't have the endpoint for that yet. So this does a kind of laborious manual version of that. But what is exactly like what are you asking it to do? Do you ask it like open the top ranking articles for this keyword and what and and read them and summarize them? What do you ask it to do? Like give me something interesting about the research step. Yeah, let me try and find it. Here we go. This is the skill file. So it starts with keyword ideas. It gets a primary keyword metrics and parent topic. It finds long tail keyword variations that share the same parent topic. There's some prioritization where it groups them together and discards ones that wouldn't fit the right intent. Pulls the questions report through the MCP as well so we get commonly asked questions that people might have related to this topic. Groups them into question themes so we're not just doing like FAQ spam. We get the SERP overview. We use that to go and look at the type of content that is ranking, the estimated traffic, all these kinds of things, analyze the dominant search intent of the SERP results so we can see what type of content performs best. That's going to go into this process. And then it looks at the actual top ranking pages so it uses web fetch. It retrieves the content. It extracts the headers. It summarizes them. It looks for themes and gaps in them and creates content gaps and opportunities. And you can see an example of the output. So it basically creates a report, like a research report at this step. I don't have to see this, but this is what gets fed into Claude at the next stage of the process. So you've got loads of keyword data, questions to answer, organic results. You know what? At this point, as I'm looking at how detailed and sophisticated these steps are, I want to say the word over-engineered. I'm actually wondering if you would like remove half of that. Would it just do as good of a job? Yeah, quite possibly. And that's another really important part of this process. I'm always surprised at how good increasingly the most like frontier, most up-to-date models actually are on their own without any input. So a big part of the testing and iteration we've been doing is to we've actually been writing test cases. We've been following these steps with the skill file and without it and seeing whether the without version is actually good enough. Does the skill file actually add any benefit to it? Good number of cases, the models do a very good job on its own and it just needs a little nudging in a particular direction. So I expect as we continue to improve on these, these skill files and these outputs will just get simpler and simpler over time until they're distilled down to the handful of things that are very important for getting the output that we want. Because yeah, it's probably completely over-engineered at this point, I think. But again, my brain wants some kind of structure to what we're trying to do. So the structure, I would, so if I were building this process myself from scratch and they needed to start from research of competitors and I know that my competitors are the pages that are ranking at the top. What I would tell AI or Claude specifically to do, I would tell it to download all the content in the folder and then yeah, I would I would ask it to extract from each piece of content kind of the main themes and the main ideas and then I would ask it to cross reference those main themes and the main ideas between the articles and create me one master document with all of the kind of ideas stories, interesting points from all of the content. So my my output, I don't necessarily need like you had the people also ask questions and that stuff, I would just ask it to analyze articles and create kind of a blended master file with everything unique that is pulled from all the articles. Actually, I do a similar process right now when I when I prepare for podcast interviews with marketing leaders, what I do is I do a pretty similar thing. I give Claude their previous interviews, links to their previous interviews on YouTube, it downloads the transcript and then it creates me for each of these transcripts because I don't want to read the whole thing, I want TLDR too long didn't read. So I ask it extract the questions because questions are topics within the interview and then differentiate between main questions and follow-up questions where the host is digging more into this topic. So yeah, you know like where the main question where the follow-up question and then instead of giving me the whole answer, give me TLDR just a few sentences of what the guest replied, give me if there was any hot take, give me if there was any story, give me if there was any specific number like oh, we increased our leads by 300 percent or something and I think there was something else but I forgot about it. So it creates me TLDR for each of the interviews and as a next step, I ask it now create me a master TLDR and this is what I would read while preparing for the podcast interview because it would give me all the unique information from like a dozen interviews. So it feels that when I want to create a piece of content, it's kind of the same. I want to know what has been said already by on this topic. So this is what I would include in the research phase. But yeah, you're giving it people also ask questions, parent topics, but it feels that when you say that you're extracting kind of topics from a page, it feels the same what I'm doing when I'm extracting questions that the host asked my guest and then I do do you also ask it to create a master document with everything? Well, that is the basic that research document is the kind of this is the research document it would hand over to the next step of the process. Okay, we discussed research. What is the next step? So the next step, hate traps references. So how does it work? So this was actually added this very recently and this has been very helpful. Claude can do a good job writing an article on most topics. It can go and look up other content. That's all well and good. I really wanted a part of the process where, you know, as a human writer, I would go and see what we already have on a topic because I want to make sure a new article is consistent with old things we've written. I want to interlink between them. I want to make sure the kind of framing is useful. I want to be efficient and make sure I'm not repeating myself. I can just pluck out the elements from existing articles. So this specifically looks up the target keyword to see what we have already published on that topic, what is already ranking for similar topics and it incorporates elements of that into the like outlining and generation process. Okay, it feels like it feels again, I will try to explain it from my perspective. I will try to kind of simplify the process. So it feels the same as research as the first step where you take the pages where you extract kind of unique information from them and you want to understand kind of the overall topic coverage as pulled from like a dozen different pages. And now what you're doing, you're referencing our own content. So rather than searching which the top 10 ranking pages for the topic, you're going and searching, okay, what relevant pages does a drafts does our website already have on this topic and can we pull something interesting from them and again cross reference with my master document. If we're saying something unique that this master document is not saying and what's what's important is because our content is very product led and we try to fill our content with use cases of our tools and data. Oftentimes the unique bits that AI can pull from our content of the topic are those use cases and you can even specifically instructed so you can tell clothes so specifically look for whenever we're discussing this topic, how are we teaching people to use our tools, what kind of actionable use cases we're teaching them. And then it would create you another document with like, okay, this is the master document of what all competitors are talking about this topic and these are unique insights that I saw published on your blog and here I unique, I know use cases of your product that I saw in your articles on this topic. So is this more or less what you're looking for? Yeah, exactly that. And this step is quite simple as well. It's basically I wanted to provide a almost like a list of modules or sections that could be relevant to this topic that we have already covered so that when it comes to outlining a draft in Claude can go and look up these examples incorporate those headers link back to them as an internal linking step. Just make it kind of an integrated part of how we create content. Okay, and then we have next step. Yeah, now onto the outlining phase. So let's have a look, see if I'm fine the skill for this one. So these are, this is very similar to what we had in the custom GPT's. This is kind of the editorial process that when a writer puts together an outline, this is how I expect them to do it. So it's got some very simple core concepts, you know, every we must use the bluff principle. So every section must open with the most important idea and then segue to examples extra context that kind of thing. We need to make sure we're logically supporting the thesis so the headers must make sense within the context of the title you've created. We need to be exhaustive and how we cover the topic need to be mutually exclusive so we don't have loads of overlap between each of the sections. And again, these are things that if you ask Claude to edit an article and make it me see it does a fairly good job of that has a good comprehension of what that means. And then you can see an example out of an outline here. So we've got hook key points, any ideas for transition it wants to include or a specific example it wants to include it wants to include a table. These are the bones of the article. You mentioned a very important word the word is example. I can give you a quick reference of why I'm talking about it. So I have a bunch of skills in my Claude code for creating LinkedIn posts. For example, I have a product based LinkedIn posts when I'm announcing a feature. I have podcast announcements when I'm announcing that I had a new guest on the podcast or just regular posts when I have an idea and they want to kind of deliver it in the best possible and punchy way. The thing is for like each of those is a separate skill that I have created that I have instructed Claude code of what I'm looking for because when I'm announcing a podcast that's one format when I'm announcing a product update from a chef's that's another format when I want just to improve a random post that can be about anything that's a different set of instructions. But the thing is for each of those skills I have a folder where I have given Claude code a bunch of examples here are the examples of my previous podcast announcements so that not only you have my instructions of how to write them how to structure them you have examples of how I did that in my voice already previously and also like those examples come also with the engagement matrix so it's a it even sees which post perform better which post performed worse. Same for podcast announcements same for product announcements and same for random posts so we'd always have a folder with examples to reference and they almost feel like when it only has instructions versus when it has instructions and like five to 10 examples. I feel it does a better job when it has kind of the actual examples to fall back to so when you're saying that this is the there's a step of an outline I almost want to you to have a folder where you have five examples of outlines of previous posts. We do have that somewhere is it templates. Yeah, somewhere we do have that maybe some part of the skill files because exactly the same thing I you know we will every time you generate something we generally want it to maybe sound like us or sound in particular way and I used to see a lot of people feed it writing and say can you distill my writing down to a handful of principles that you can then. I was always very skeptical of that though like how can you reduce somebody's unique voice down to a handful of things that then Claude without that example to back it up can actually go away and do. I think what you're right the much better thing to do is let the model infer itself from an actual example. You're writing style I don't think is always going to map neatly across to a five bullet point lists of your writing style or whatever but Claude is a large language model it can infer from large samples of text the patterns that do actually exist in your content and that is how it will end up sounding like you so I totally agree and create with an actual example in saying make it sound like and feel like this is actually pretty good from what I've seen. And this is this is exactly how people should create those skills in the first place because the way I created my skills is I gave it a bunch of my previous podcast announcements I said analyze this posts tell me what I'm doing here tell me what's my style. It would tell me like what it kind of inferred from reading my posts and I would correct it if I disagree somewhere if it doesn't feel like it understands what I'm doing sometimes it would understand what I'm doing better than myself which is funny I'm like oh that's that's really what I'm doing I just I was doing it subconsciously I didn't understand that and then for example speaking of podcast announcements I would give it some podcast announcements from Lenny Rachitsky how he announces his podcast interviews on LinkedIn. And I would say OK analyze what Lenny is doing here it would analyze what Lenny is doing again I would correct if I disagree with something and then I would say now create kind of something in between something between my approach and Lenny's approach and tell me what set of instructions you will come up with so basically I'm not creating instructions myself I don't need to write out instructions I'm giving it examples I'm telling I'm telling it analyze and tell me what you see like what's the kind of principles behind. And then I would correct it if I disagree with something I would monitor what what instructions it is creating for itself and I would correct it and then like I said it's very important to have those examples for it to fall back on because then I just I just feel the output is always better. OK so that's outlining step like you said you you do have some outline examples actually it says easy as asking Claude hey outlining step tell me do we have examples for it how they store are they stored in a text document are they stored in a folder and it would tell you and if you don't you can just say OK then create this folder and these examples and cross reference it so yeah a lot of people kind of I'm not sure if I can use the word over engineer but they overthink they are not going to be a lot of things. Overthink they overthink what is a I but it's like as easy as just talking to it asking questions like how did you do this how did you do that and guiding it well of course if you have a good idea of what you want to achieve but it's very important to be able to break the process into kind of smaller steps into building blocks so to say yeah. OK next after outline was the step so now what we do is we look at the outline we've created and we ask Claude to find specific opportunities to mention relevant hatred products. I tried you know having this at integrated into other steps and it was a bit hit miss and this is obviously something that really matters to us because this is why we write content we want to talk about the product in context where it makes sense to do that so this is a discrete stage this will do this every single time. It's very simple because it was in the skill I'm going to talk about. actually have a kind of master list of HF products and features, which I asked Claude to create for me and then I updated and tweaked myself to include like newer ones, add some features. So it goes to that and it looks at the outline, it says, which of these can I can textually mention in this outline and have it make sense, how it be useful for the reader. And it just adds a little signpost for the next step so that when it comes to drafting, it knows to actually incorporate HFs into it. Now you know, keyword explorer, that kind of thing. And again, probably this is not something that people need to write, start to finish themselves. Just drop links to your landing pages, to your video overviews, ask it, tonalize it and tell you what the product is, what is it, what is it good for, what are the top use cases, what are they like use cases for, I don't know, for this area, for that area and then you just correct it. So yeah, it's actually those things are easier to create than than people might think. Yeah, exactly. We've got site order rank tracker, content explorer, Claude did most of the heavy lifting here, I just reviewed it and I added in some, I need to add in like fire hose and things like that actually. But again, Claude can do all this for you, it's a fantastic diligent worker. And then after that is the drafting stage. And I think when most people would do like an AI content process, this is probably the only stage they would create and certainly when I've talked to people, this is all they do. They focus on what are the best prompts for making an article. But yeah, from all of our trial and error, I think having tons of steps for research and structure before you get to writing is what ends up giving you the best outcome. And this is again, similar to the writing rules we had in our previous GPT, it just has some, this is adapted from our own internal writers like style guide for writing. Use the problem agitates solution formula. Here's an example of it in action as part of the introduction that works pretty well. Some structural stuff about inverted pyramid, always explain what and why all these very simple things. Draft is not a final step, right? It is not the final step. What goes after draft? So we have a kind of verify claim stage. Internal linking is very important for us and for SEO and also making sure we have included useful up-to-date sources for everything that we do. So there is a particular step in here that it actually goes through the draft and it looks for the claims. Things, you know, claims that the article is making that we would need to go out and validate and it makes sure that it has an up-to-date source for that or it updates, it reviews it to see if it's accurate or not. And actually, I've been working on this updating this skill because this is a big part of our content updating workflow. We want to go back to old articles, find all the claims, make sure they have the most up-to-date validation and accurate stats for it. So that's the next step of that process there. And there's more steps after this? Yeah, not too many more. So we have a preview stage. So at this point, I wanted to be able to look at the draft and sound, he checked it and see if I was happy with it. And it's not always, I don't like looking at markdown files like this, so it actually generates a HTML file that is styled to look like the H3Fs blog. And I can then open that up in my browser just to like see what I would look like and feel like on the blog so I can quickly review it from that point of view. And the thing that still takes a ton of my time that I am trying to work on is screenshots. So much of our content is product-led, it involves using the H3Fs product, screenshots are so important for that. At the moment, what this does is it will suggest a report that we can actually go and visit and take a screenshot of. And we actually have another skill that other people in the company have built, which allows the Clotter structure correct URLs for our reports. So it can actually generate a Genuine Report URL for you to visit in H3Fs. And then I can take a screenshot of that. So that's quite useful. I'm trying to automate that with some headless browser stuff and some screenshotting and that kind of thing. But at the moment, I spend as much time doing the screenshots as I do actually editing, reviewing, generating. So that's a big part of it. Okay, since my job on this podcast and in our calls is to essentially criticize everything you do, what I found job people would think I'm a terrible person, but it is what it is. To be honest, one step, I expected to see in this process is when you would kind of dictate to this system some of your thoughts of where to take this article in free form. And I would explain why you have it or something, you're pointing something out. It do indeed. Yeah, I kind of glossed over it. I totally agree. Sometimes you just want to provide a few sentences of thought or direction. You want to mention a specific product and you don't trust it will do it itself. So one of the things I added recently was this context trigger. So this right of the get go, when you trigger the workflow, you can provide it with as many sentences of context as you would like. And that is then used to shape and inform the rest of the process. So often I'll say cover this topic or this topic or review this existing article and bring elements of that into it or mention this new product and that kind of thing. And it's just a little directional nudge. And again, that seems to be very useful for getting a good outcome from it. I think it's like a critical step in my opinion. Again, we are still in the very early days of all that. We're still experimenting. And like I have so many thoughts in regards to all this. So first of all, I think it's important to point out that what you just showed is a work in progress because any any kind of skill, any kind of workflow that you build for yourself in Cloud Code or any other AI, it shouldn't be set in stone every time you run it and every time you analyze the output, whether total output or whether output of the steps. And you don't like something you need to go and refine and you keep refining and refining and you're basically teaching your AI workflow, AI agent, AI skills skill to do a better job and with every run it would get better and better. So this is the first point. The second point I feel this this step of giving it context is super important because it is what will essentially make your content unique because again, the reason why I was also surprised that you would let it run for eight minutes and just generate something for you is because I would expect that you would get a TLDR file from the top competitors. You would go through it and you would just like in free form. I'm using whisper flow. This thing to dictate into into anywhere basically in text all the time and I was just click a button and I would say, oh, like so I disagree with this part. I think this part is good. Don't even mention this part is not important. Here is where I think you can and you can give it a lot of instructions. It's almost as when we had those content mastermind calls where we would discuss ideas and we would brainstorm where to take every idea in the same way that we were giving each other feedback and kind of figuring out what angle is best to take with any given content idea. In the same way, you can provide feedback to or context to AI and I feel it would it typically would do a great job at doing this. And that's very another very good point. Maybe I'll talk briefly about how I think conceptually this process should be used for content marketing generally. Like this is not the HREF's content process going forward. It is not as though everything we create has to come through this or will come through this. We spend a lot of time writing stuff that is AI is still not very good at helping with things that require tons of thought and experience and unique perspectives and ideas that maybe other people haven't even shared before. I think this is really useful because we've written literally thousands of articles over the years and what I see being really important for us going forward is having this well maintained library of evergreen search content. I want to make sure we cover all the core topics that relate to our product and how to use it, keep them updated. And a lot of times that is very simple, quite repetitive stuff. Like how many ways are there to do keyword research? Quite a few as it turns out. So I think this is really good for topics. We have tons of information documenting keyword research and all these kinds of topics that can be used to inform this process. This is almost like doing our housekeeping for us in some sense. It's not something that requires a ton of direct involvement and guidance because we've already done that. We've written dozens of articles on these topics that is using, used to shape these articles now. And you know, I've generated tons of articles from this that were, I could have published and would have been fine, but I didn't know enough about them. I didn't think they were interesting enough and I've chosen not to do that because I still deeply care about everything we publish and I want to make sure we put out the best thing we can. So yeah, I feel this process and the reason why kind of you let it run on itself with little output. It feels that it's best used to take some kind of what we call a general knowledge topic and adapt it to us because one of the steps it pulls from our existing content and it finds what kind of unique stuff we said, then it finds the way to include a traps in our use cases in this post. So basically, for example, there's plenty of information about link building, but it doesn't necessarily share what we have shared about link building and it doesn't necessarily makes good use of a traps tools when it comes to link building. So with this automated process, this is where you don't need to write something from scratch. You can analyze existing content and AI can find a lot of information from our existing articles and from our tools to include in the post and yeah, you have the post ready. Am I right? Yeah, exactly that. Yeah, I like to think, is this a boring topic that I don't want to write because we've covered it a thousand times. If so, maybe it's a good candidate for the AI process, which is not everything we publish. In that regard, oh, you have something else to see. Yeah, it's very briefly, I just kind of ties on to this and also we built a content updating pipeline. This is a bit new, I'm still tinkering with this, but in a similar way, we have a thousand publish articles, for example, and it's very hard for human people to keep on top of that, keep them updated. So we're working on a similar process here that is designed to basically periodically give you updated content to review and edit and approve and potentially publish. And very similar thing, there are basically three things this does. It looks for claims that might be outdated. So there's an old stat or something that doesn't make sense. Claude will review it and try and find a new version of that and allow you to accept it if you want to. You can find opportunities to add new HREFs product features. So obviously, some of our articles were published like eight years ago. They don't mention our latest products like FireHose or AI content helper. This can make recommendations for you. And lastly, updating topic gaps. So this is where it looks at the SERP and it says, is there anything that has other articles talk about that we don't? Perhaps we should draft a section for you to review and edit and include. And it just makes a very boring, unstructured process, a bit more organized and a bit more fun for people to engage with, I think. I really, really like where all of this is going because I think this is actually the future of how content is going to be created. And I wanted to wrap this up from a different perspective because you essentially shared a workflow of how to create content on what you call like a boring topic. Something that has been covered over and over and we just have like some unique spin or we want to cover this topic and include our products and services. I wanted to share a quick story from the other side when you want to create something completely unique. And that is so I'm in the process of writing a book as I mentioned many times on this podcast already. And just eight months ago, I was complaining to a bunch of our team members that it is very hard for me to contact switch because when I stop working on the book and they do some like projects inside the traps and then I need to return to the book like a few weeks later. I barely remember what I was writing about. I barely remember my train of thought and it's almost like I need to upload all the information from scratch. And I think it was further who said why don't you just upload like all your chapters to AI and kind of ask it to guide you like AI would ask like a journalist or a ghost writer who'd been interviewing you asking you questions and would be kind of writing the book for you. It was eight months ago about eight months ago and I said I cannot see how I would be able to do that. So back in the day we didn't have Claude Cod back in the day like chat GPT just released their custom GPT or something. I couldn't see how I would upload like my entire book and be able to work with it. Fast forward eight months and the last chapter of my book I just finished the draft. The last chapter I wrote it with AI by dictating my ideas into Claude Cod and my process was I told it okay the name of the chapter is this. What is going to happen is you're going to create a folder with my random dictations because I have a list of notes what I want to say within this chapter and those notes exist in the form of three words or one sentence basically talk about this or expand on this idea and I would hit a button and I would just ramble. So there's this idea and I wanted to say blah blah blah and we like did this thing at HS and we have this interesting story blah blah dictation over next idea and I was just rambling on each of my ideas. I had a few dozen of them. Okay it saved that to the folder and I said okay I'm also like one talking when talking about those ideas I was referencing a few things some of the things that I discussed with some other marketing leaders on the podcast some of the things that we actually covered on a chef's blog for example we have an article about taste and I just said oh like I'm talking about taste in in my chapter and you have my voice dictation with my ramblings about it but we also wrote a nice post please include it as sources when talking about taste. So I gave AI I gave it all my dictations and they gave it all the resources that I remembered like different YouTube videos interviews different articles that I want to reference etc even some LinkedIn posts that I saw from people who are sharing these ideas and then I said okay now the general idea of this chapter is this I'm trying to make a point that blah blah blah blah blah now you know like all my dictations now you know all my resources all the stories I want to tell tell me how would you connect the dots how would you structure it so essentially create me an outline and it would write me oh so I suggest that you lead with this story then it transitions well this and then this argument and then these things blah blah blah at which point I would say like I would give it some feedback where change it or not or I would say sounds good to me write it and it would write a chapter for me and then I also like uploaded to Claude code I I downloaded from Google documents all my previous chapters and I said okay for each chapter create kind of a synopsis file what this chapter is about what are the key arguments that I'm making and what is that tell they are outline of a chapter what are the main stories and key ideas and I'm sharing so for each chapter it created this file kind of with a recap of the chapter and then I said now refer to all the files of all the chapters and create me a synopsis of the book I want to know like what the book is about how this structure and what is illogical and it is so good it's like it's literally like you you're you're affloating some of your brain work to someone else like you have an external brain that processes information for you so this is why kind of when when we started talking and when you shared that you created a system for creating a blog post fast and you said that your productivity increased that you published like three articles in a few days or something like that I am actually expecting that all of the content that we're going to create it would go through AI that we will no longer manually write stuff we would just hit a button we would ramble to AI what we want to say we would point it at like whatever resources we want to use to make a point and it would help us write even a better article because it's ability to connect the dots and understand what you're saying it's actually quite crazy I'm very surprised how well it was able to distill my ramblings into coherent ideas and connect the dots between them and organize it in a way where I'm like whoa this actually looks quite good so yeah the process that that we just covered in in this podcast is mostly for kind of semi-automated content you still want to like overlook it and like like you said you have a step to give it context of way you want to take it and what's the unique angle and stuff like this but it's still like you're you're floating the majority of the work while I think going forward creating content yeah AI would act like a journalist an editor a ghostwriter and you would act as a source of ideas and opinions and people who don't have a good writing skill but have strong opinions would be able to publish their content fast so what are your thoughts on this yeah I totally agree with that I always find some people think that human creativity is too unique and magical and special that like AI could never help with it and never be a useful aid in that process but actually there's a lot of mental drudgery we do when we're writing a book or an essay or anything like that I think the ideas the motivations the experiences the things we care about that is still uniquely you in your book it's still your book and your ideas yeah but all you know just sitting down for hours and shuffling these ideas about and working out what are the common themes that is something that AI is fantastic at doing yeah if it can make these writing and creative processes more fun for us then like well that shouldn't be scary I think that should be fun would be more prolific we'll share more stuff there'd be more of our unique thoughts and ideas out in the world so if yeah for all the kind of like sad drudgery and you know are we automating careers and jobs away actually we could create more cool stuff than has ever existed before in human history that's totally possible now I like the word drudgery I think what what AI does it it literally eliminates drudgery because like I said for me it was a pain to go back and to because I would need to read my entire chapter again to remember what I was was saying there. And now we can say, remind me what was the synopsis of the chapter, where we left off, which ideas need work. It will tell me all that. And I'm like, immediately I can continue working and I can pick up where we left off. So yeah, let's not make it longer than we need. Thanks a lot for sharing your process. Thanks a lot for as always letting me to jump in with my thoughts and ideas. I generally think we're on the right track with these kinds of things and this is the future definitely. This is the future of content marketing and content creation. Thank you Ryan. Thanks too.