Why Claude Code Changed My Work

Speaker 0:00

The last time this show talked about coding agents, the tool was Cursor and the word was vibe coding. That was back in March 2025. Everything I've built since, including Salience, was built with a tool this show has never covered. And here's the bit I didn't expect. Some weeks I use it more for SEO than for code. Hi, it's me, Ed Dawson, back as always, and this is SEO Is Not That Hard, and by the end of this episode, you'll know what Claude Code actually is, how I use it to build software, the three ways I use it on SEO work every week, and one rule that will stop it making things up with your data.

What Claude Code Actually Is

Speaker 0:36

So what is Claude Code? Claude Code is an AI agent that lives in your terminal. So it's not in a chat window, it's not auto-completing an editor. It's literally within the terminal on your computer. And if you don't know what a terminal is, just go and ask Claude or ask ChatGPT, "What is a terminal?" And it'll tell you all about it. But it's basically the fundamental layer of a computer that's a bit deeper and lower down than you generally tend to work in But it's very powerful down there Basically, what you do is you open a folder on your computer, you type in what you want in plain English, and it goes and does it. It can read the files in a folder, it can run commands, it can look at the results, it can decide what to do next, and it can keep going until it get its-- gets its job done. It can create computer code. It will write little software for itself to run things, and it just works in loops until it gets your question or your problem solved and answered. And that loop, the way that it loops around is the whole difference between a chatbot and an agent. A chatbot just answers a question, turn response basis. You're used to it in-- when you use Claude or ChatGPT in their website. But an agent has agency, it can act, it can do things. Now, Claude Code came out as a preview in February twenty twenty-five, and properly in May. Now, I didn't properly pick it up and start using it until Christmas when I was back ill on the sofa where we spoke about it in a couple of episodes ago. And I told you where that led. We got to Salient from that just from using this tool. But here's what matters for the rest of the episode. It doesn't care whether the folder holds code or a pile of spreadsheets, which is where the SEO

The Software Factory In Practice

Speaker 2:27

bit starts. So first, we'll cover the coding bit briefly. And this is just a recap really from the episode of the day and what a software factory is. So I'll keep this short. So I use it to code. I write a brief, which is the problem, an example of what done looks like, what tests must pass, and then Claude Code uses agents within itself, a manager agent that will turn that into a specification, an implementer agent which will build it And then a reviewer agent that will check the work and send corrections back. And then when it's done and it's ready, it will present it to me. I can review... I will review it. Always have a human review it, and if we're happy with it, then we'll push it out to production. That's our software factory, and that's the kind of powerful thing you can do with Claude Code. But it doesn't have to be that complicated. You don't have to be building a software factory to get stuff done. You can actually start much simpler, and that's where it actually comes in really useful for

Building WOLF For SEO Reporting

Speaker 3:26

SEO. So that's what we'll talk about next So as I've mentioned before, over many episodes, I run a handful of content sites that earn through affiliate links. So for years, answering a question about them and how they were doing, how they're performing really meant sort of three tabs. That was Search Console, Analytics, and the affiliate network. And that was always exporting, pasting, pivoting, pulling and collating together by hand, and that took time, which means the more time something takes, the less likely you are to do it, especially if you're me. But this is the kind of problem that is perfect for Claude Code. So what I had Claude Code do was build me a small tool that I called WILF WOLF stands for Workspace Intelligence Layer and Facts. And I'll be honest, I came up with the name first and then worked an, an acronym back towards it. I just like the name WOLF. I wanted to be able to call it something Now what Claude Code built Wolf to do is that every night it pulls search console data, Google Analytics data from the affiliate networks that I work with, and Clicky, which is also another of, tracking system that I use that's similar but simpler than Google Analytics, but does essentially the same thing. But it's like a second tracking system. I've talked about it before in previous episodes, and I do recommend it for simple analytics And it saves all that into a local database on my Mac, and then exposes that database to Claude Code through an MCP server. So if MCP is new to you, go back and listen to the May twenty twenty-five episode. It's how an agent gets hands. Essentially, an MCP server gives an easy way for an agent to query and work with data on another system. So essentially, I had Claude Code build this little wolf system that pulls in this data on a daily basis and then gives it a way for other agents to then get at and work with that data So then when I want to actually work with this data, all I need to do is open up a terminal, load up, load, load up Claude Code, and ask it a question in English, like which pages lost organic clicks s-since September and did affiliate revenue follow? Could be a question. And then Claude Code itself will take that question, go to the MCP server to Wilf. It will interrogate backwards and forwards, work out what data it needs, get all that data back, save it in-- locally for itself, query it, and build an answer, and then come back to me and tell me what it's found From that, I can then cross-question it, ask more questions about the data it's found, even ask it to visualize that data, create an artifact for me or a PDF or something useful from that data that we can then work further with. So it's essentially an incredible way of having a conversational interrogation of all the important data without having to trawl through lots of different dashboards, lots of different systems, without having to pull data manually all the time. It's just makes it simple But here's the next part, and this is about making it trustworthy, and it's the rule I mentioned at the top.

The Facts File That Stops Hallucinations

Speaker 6:45

Wilf has a fax file the agent must read before doing anything else This is where we give it the context that it needs to properly understand the data. An example being back in September twenty twenty-five when the normally, of course, one hundred flag was removed from Google Organic Search, and it made a big difference to the number of search co-console impressions that search Search Console reports. That kind of fact I've given to Wilf as I've worked with it because it came back and said, "Oh, there's this big crash in data," and I said-- And give it that explanation. It says, "No, that's fine. That happened because of this is what Google did." And it goes, "Oh okay." And it saves it to its context, to its memory, essentially. So it knows in future that, oh, yeah, the reason that drop happened was nothing to do with the site. It was to do with this change at Google. So when these things come up, you can backfeed information to it so that it improves its answers further down, and that's the trustworthy, that's the trustworthy piece. 'Cause this is why you always still need to question the data like you would if you were working on it by yourself without an agent, like the old-fashioned way. You still need to question your data, and then those assumptions, those things that you learn from your data, you need to feed back in. Because things that you-- That's context you would remember naturally as a human, you feed it back into it And without that kind of context, the agents can do things like confidently explain traffic drops that never happened. With them, it reasons like someone who's worked on your site for years. You need to tell it what you know. It won't remember otherwise So that's working with my data.

Using Agents With SEO Tools

Speaker 8:21

The second use is everybody else's bots So four things here quickly. One, Salience ships a command line tool and an MCP server itself. So from the terminal, I can ask which AI bots hit this site this week and which ones got blocked. The agent, it'll then call Salience, it'll read the log data, and it'll answer. And it-- we built Salience for agents on purpose because this is how I wanted to work with the data. We obviously have all the dashboards, all those kind of things, and they're important for certain times, but it's so much more powerful nowadays Being able to have your agent talk directly to your services like that because it can just pull data in and out and you can query it and work with it in ways that it's just so much harder to do if you're just relying on a dashboard only Secondly, browser tools. Claude Code can drive a real browser through another MCP server. So you can say, "Load this page the way Googlebot would. Does the main content render without JavaScript? Screenshot it, please." That used to be a Chrome extension, a dev tools panel, and lots of squinting and cutting and pasting. Basically, you can now say to your agent, "Go to this website, perform this action for me."

Speaker 2 9:35

Thirdly, keyword research straight into the brief. So Keywords People Use has its own MCP server. I definitely did an episode on that in the past. We were one of the very first places to do any kind of MCP server, I think. But with that MCP server, the agent can pull the people also ask questions and related searches for a topic without having to leave the terminal. You don't actually have to go and use our website anymore. You can just use the MCP server. So you can say to your Claude, "Go get me related searches. Say, get every question people ask about heat pump running costs and cluster them by intent, and draft the FAQ session-- section with one source per answer." And then this will go and research, get that data from Keywords People Use directly, pull it in, work on that first draft, give it to you ready for you to work on. And that is just amazingly powerful how quickly it can pull that data in, work with it, and it just saves you so much time and gets you much closer to having the published content that you want And fourth your websites are code. Our sites are code, so the agent can work and fix o-sites directly so now you know, every page or any page that we want to be worked on, we can just tell the agent what it is that we want done, what we need changing, where to get the data from All those kind of things And you can then send to it, open up a change for me to review. You can check it and then just click Merge when you're happy for it to go through. So You can just go end to end from querying the data, finding out what the problem is, getting the data you need for the new content that you need to work on, and getting it onto the site all from within your agent, all from within the terminal, all by working with Claude Code. So back in the old days, a technical SEO audit used to end with a document someone else might act on or that you would act on yourself later. Now, it just ends with a pull request that Claude's done for you, that you can go and review, work on, and then decide when to merge and publish. So yeah, it's just a completely different process, much more streamlined, much more efficient And once you've got the hang of it, the learning curve is actually less than trying to learn all the different tools that you need to work with otherwise to p- to achieve the same result And the third use,

Rapid Data Packages For Digital PR

Speaker 2 12:00

that was the second use. So the third use is if you heard the link building series you know my view. Build something that's worth citing, so tools, data, awards, all that kind of thing. And this summer, a journalist at a national newspaper in the UK, they wanted a data set from one of the, that one of my sites holds. And with Claude Code, I got them together a doc- document package, document data package, which covered every postcode, that's a zip code if you're in America. In the UK, that's over one and a half million postcodes worth of data in just one session with Claude Code. I also had it pull the regulator's public register, that's about another 11,000 records, into something that we could actually query and publish from for them, and pull that all together in a special data package that was branded for this newspaper. It had dedicated tools within it that the journalist could use to query that data and get all the stats together they needed for the piece of work they were working on. And it was just an hour or so session with the agent gathering the data, creating the tools, creating the data package, and sending it off.

Speaker 3 13:12

Two years ago, each of the bits of the package in there, not just the whole package itself, would've been a week of a developer's time. So it just wouldn't have happened. We couldn't have afforded to do it. Wouldn't have had the time. Now, it's a session in an afternoon. So these things do happen. And that's really the, what I'm talking about in the whole of the last three episodes here in one big example. The bottleneck isn't the building anymore. It's not the time to build that's the bottleneck. It's deciding what's worth building that is the bottleneck

Four Rules For Safe Agents

Speaker 3 13:42

So that's it. That is the four rules that I've learned over the past year or so working with agents like this is. So it's one You've gotta watch them because they will fill a gap with something sounding plausible. Always make it show it's working. Always interrogate the number that it comes back with. Ask for the query behind it. Keep a second source for it to check against Secondly, write things down for it or speak to it to tell it to write this down for itself, these instruction files, the facts files. Every session will start blank unless you or the agent itself has written it down somewhere for it to be shown and to refer to again. Thirdly, don't give it the power to send, publish, or deploy on its own. You can have it draft, have it propose, you can have it open a change, but always make sure you review this. The agents that work on Salient, they can't deploy, only I can deploy. My inbox agent can draft a reply, but it's never been allowed to send one. I always run over the draft myself, make changes where needed, and press send myself. And fourth, start smaller than you think, okay? Don't just go and say to it, "Audit my site." Start with one question, one page template, one export, then widen it out. With all these things, start small and then widen out.

A Simple Challenge For This Week

Speaker 3 15:03

If you were to do one thing this week, I would suggest you First of all, download ClawCode, and then secondly, export the last, say, 16 months of your search console performance data to a folder. Install ClawCode, open that folder, and ask it one question such as this: Which pages lost clicks after September 2025, and is the drop in impressions or in clicks? That kind of thing. Then read what it did, read what it says, and then open that conversation with it and see what you can learn from it So that's it for today. Hope you found this episode useful, and until next time, take care and I'll see you later