Use AI to create knowledge base articles for customer or user support.

Creating knowledge base articles (KBAs) is essential for providing efficient customer support and keeping your team on the same page.

In this tutorial, you'll learn you how to use ChatGPT to create comprehensive KBAs for your user support. Let's dive in and make sure your KBAs are structured, informative, and user-friendly.

Why are knowledge base articles important?

  • They make your customers happy by providing quick solutions.
  • They lighten the load on your support team by handling common issues.
  • They ensure consistent and accurate information is shared across your organization.

How can ChatGPT help here?

ChatGPT can help you generate content, suggest article structures, and improve readability and clarity. It’s like having a co-writer who’s always ready to help.

Collecting and organizing customer data

To write great KBAs, you need to understand what your customers need. This part is all about gathering and organizing customer data to pinpoint the key issues you need to address.

Steps:

1. Gather Your Data:

Collect data from customer support tickets, emails, social media mentions, and any other places where your customers reach out. This will give you a solid foundation of real customer issues. This is probably the hardest part because you need to gather the data. Some tools offer the option to export conversations, which could be really helpful here.

2. Prepare Your Data:

Export this data into a CSV file. Make sure it’s clean and organized so you can easily analyze it. In my feedback file there's just two columns: customer and feedback.

You can totally copy the data (messages, conversations, questions, reviews...), paste it in ChatGPT, and ask the assistant to format it and give you a structured CSV file back.

3. Analyze with ChatGPT:

Upload your CSV file into ChatGPT and use this prompt:

I have a [type of company e.g. bike rental company]- our product is [product], primarily for [main customer type]. I am looking to analyze my customer data to see where I can improve my service/product and to understand customer pain points. I have spent some time collecting data from customer support tickets, emails, and social media mentions - the data is in the attached CSV. Given this list of customer issues, please identify recurring themes or categories they fall into.

ChatGPT will help you identify the recurring themes or categories in your data.

Structuring the knowledge base

Organizing your KBAs into logical categories makes it easier for users to find what they need. This part will help you create a well-structured knowledge base.

Steps:

1. Categorize customer problems:

Use ChatGPT to group customer problems into logical categories. Here’s a prompt to get you started:

Please categorize these customer problems into logical groups for a knowledge base structure. For these categories of problems, recommend the most effective article format (FAQ, step-by-step guide, video tutorial) for each.

2. Organize your categories:

Based on ChatGPT's suggestions, organize your knowledge base into a user-friendly structure. This will help users quickly find the information they need.

Keyword analysis and article titles

Your KBAs need clear and concise titles that are optimized for search engines. This part will help you identify the main keywords and create suitable article titles.

Steps:

1. Identify Keywords:

Use ChatGPT to find the main keywords related to each problem. Try this prompt:

Based on these categories and the customer problems already discussed, determine the main keywords related to each problem that customers are likely to search for.

2. Write Article Titles:

Generate clear and concise titles for each article using ChatGPT:

Now use the keywords you've identified to write clear and concise titles for each article I should include in my knowledge base.

If the titles need some tweaking to fit your brand’s style, ask ChatGPT for more refined suggestions:

Can you make them sound like less blog titles and more functional/descriptive?

Outlining and drafting articles

A well-structured article is easier to understand and follow. This part focuses on outlining and drafting your articles with ChatGPT’s help.

Steps:

1. Outline Your Articles:

Draft the key points you want to cover in each article. This is the part where you actually give explanations as to how to use your product or service. Then, use ChatGPT to organize these points into a rough outline:

Now I need your help outlining what to include in these articles. Let's start with the article titled [article title]. I've drafted some key points that I know I want to include; organize the key points into a rough outline for an article.
- [Point 1]
- [Point 2]
- [Point 3]
- [Point 4]

2. Draft the Initial Content:

Use ChatGPT to write the content of the article based on your outline:

Now, based on that outline, help me draft an article with simple language and short sentences. You should also:
1. Indicate where I may need to break down any technical or complex steps into simplified explanations for a broad audience.
2. Suggest where visuals could enhance understanding.
3. Identify sections in this article where adding a real-world example or use case could improve understanding.
4. Identify any relevant keywords for this article, and strategically incorporate the identified keywords into your article's title, headings, and body text without compromising readability.

Reviewing and refining articles

Ask ChatGPT to suggest improvements for clarity, flow, and user-friendliness with this prompt:

Review this article draft and suggest improvements for clarity, flow, and user-friendliness.

Finally, don't forget to provide the visuals that ChatGPT asked for. Most of the time, these visuals will help make your knowledge base articles more relevant and helpful for your users, thus increasing the helpfulness of your knowledge base. Also the real-world example that you can see above would also add more clarity and tangibility to your articles.

Got an idea for a new feature or tutorial? Help us make the academy even better.

More tutorials like this

Learn how to build a custom support agent with Lindy to streamline customer support.
📖
Customer Support
Lindy
👨‍🎓
Intermediate
Use DeepThink R1 to turn complex data into actionable strategic insights.
📖
General
Deepseek
👨‍🎓
Intermediate