See how working with LLMs can make your content more human by turning customer, expert, and competitor data into usable insights.

One of the major things we talk about with large language models (LLMs) is content creation at scale, and it’s easy for that to become a crutch.

We’re all time poor and looking for ways to make our lives easier – so what if you could use tools like Claude and ChatGPT to frame your processes in a way that humanizes your website work and eases your day, rather than taking the creativity out of it?

This article tackles how to:

• Analyze customer feedback and questions at scale.
• Automate getting detailed and unique information from subject matter experts.
• Analyze competitors.

These are all tasks we could do manually, and sometimes still might, but they’re large-scale, data-based efforts that lend themselves well to at least some level of automation.

And having this information will help ground you in the customer, or in the market, rather than creating your own echo chamber.

Analyzing customer feedback at scale

One of the fantastic features of LLMs is their ability to:

• Process data at scale.
• Find patterns.
• Uncover trends that might otherwise take a human hours, days, or weeks.

Unless you’re at a global enterprise, it’s unlikely you’d have a data team with that capability, so the next best thing is an LLM.

And for this particular opportunity, we’re looking at customer feedback – because who wants to read through 10,000 NPS surveys or free text feedback forms?

Not me. Probably not you, either.

You could upload the raw data directly into the project knowledge and have your LLM of choice analyze the information within its own interface.

However, my preference is to upload all the raw data into BigQuery (or similar if you have another platform you prefer) and then work with your LLM to write relevant SQL queries to slice and analyze your raw data.

I do this for two reasons:

• It gives me a peek behind the curtain, offering me the opportunity to learn a bit of the base language (here, SQL) by osmosis.
• It’s another barrier or failsafe for hallucinations.

When raw data is uploaded directly into an LLM and analysis questions are asked directly into the interface, I tend to trust the analysis less.

It’s much more likely it could just be making stuff up.

When you have the raw data separated out and are working with the LLM to create queries to interrogate the data, it’s more likely to end up real and true with insights that will help your business rather than lead you on a wild goose chase.

Practically, unless you’re dealing with terrifyingly large datasets, BigQuery is free (though to set up a project, you might need to add a credit card).

And no need to fear SQL either when you’re pair programming with an LLM – it will be able to give you the full query function.

My workflow in this tends to be:

• Use SQL function from LLM.
• Debug and check data.
• Input results from SQL query into LLM.
• Generate visualizations either in an LLM or with SQL query.
• Rinse and repeat.

Dig deeper: 7 focus areas as AI transforms search and the customer journey in 2026

Get the newsletter search marketers rely on.

---

Automating subject matter expert interviews

It seems to be a common trait among subject matter experts that they’re time poor.

They really don’t want to spend an hour talking with the marketing person about a new feature they’ve already discussed with the manufacturer for the last eight months.

And who could blame them? They’ve probably talked it to death.

And yet we still need that information, as marketing folk, to strategize how we present that feature on the website and give customers helpful detail that isn’t on the spec sheet.

So how do we get ahold of our experts?

Create a custom GPT that acts as an interviewer.

Fair warning, to get the most out of this process, you’ll want a unique version for each launch, product, or service you’re working on.

It may not need to be as granular as per the article, but it may end up being that specific.

To do this, you’ll need at least a ChatGPT Plus subscription.

Instructions will depend on your industry and the personality of your subject matter experts or sales team.

They should include:

• Role and tone: How the “interviewer” should come across.
• Context: What you’re trying to learn and why.
• Interview structure: How to open, topics, how to probe more deeply.
• Pacing: Single question, wait for response, expanding questions.
• Closing: how to wrap and what to deliver at the end.

Once we do that, we’ll want to test it ourselves and pretend to be an SME. Then we refine the instructions from there.

This way, you’ll be able to reach your SMEs in the five minutes they have between calls.

And you can use an LLM to extrapolate the major points, or even an article draft, from their answers.

Dig deeper: SEO personas for AI search: How to go beyond static profiles

Analyzing competitors for strategic insights

This one may be a bit sneaky and may require a bit of gray thinking.

But there are a few things you can do with competitive data at scale that can help you understand the competitive landscape and your gaps within it, like:

• If you were able to gather your competitors’ reviews, you could see themes such as benefits, values, common complaints, and weaknesses.

• If you were able to gather their website copy, you could identify their positioning, implied audience, and any claims they may be making, as well as the industries they might be targeting, extrapolated through case studies.

• With their website copy and support from Wayback Machine, you’d be able to identify with an LLM how their messaging has shifted over time.

• Job postings could tell you what their strategic priorities are or where they may be looking to test.

• Once we have their positioning, we’d be able to compare us and them. Where are we saying the same thing, and where are we differentiating?

• If you were able to gather their social interactions and engagement, we might be able to understand, again at scale, where they’re able to answer customer needs and where they might be falling down. What questions aren’t they able to answer?

Dig deeper: How to use competitive audits for AI SERP optimization

Scaling research without losing the human thread

Pair programming with an LLM to ground yourself in your customer with large data sets can be an endless opportunity to get actionable, specific information relatively quickly.

These three opportunities are solid places to start, but they’re by no means the end.

To extrapolate further, think about other data sources you own or have access to, like:

• Sales call transcripts.
• Google Search Console query data.
• On-site search.
• Heatmapping from user journey tools.

While it may be tempting to include Google Analytics or other analytics data in this, err on the side of caution and stick with qualitative or specifically customer-led data rather than quantitative data.

Happy hunting!

---

Contributing authors are invited to create content for Search Engine Land and are chosen for their expertise and contribution to the search community. Our contributors work under the oversight of the editorial staff and contributions are checked for quality and relevance to our readers. Search Engine Land is owned by Semrush. Contributor was not asked to make any direct or indirect mentions of Semrush. The opinions they express are their own.

---

About the Author

Amanda King has been in the SEO industry over a decade, has worked across countries and industries, and is currently consulting through her business, FLOQ. She’s always been focused on the product, the user and the business. Along with a passion for solving puzzles, she’s incorporated data & analytics, user experience and CRO alongside SEO. Always happy to trade war stories, find her on Twitter or LinkedIn for intermittently shared advice and thoughts on the industry.