Most common questions (FAQ)

This article collects the most important issues that may come up during the first project setup and everyday work with the Semly panel.

What is Semly?

Semly is a platform for monitoring and increasing brand visibility in answers generated by AI models such as ChatGPT, Gemini, Claude, Grok, Google AI Mode, or Google AI Overviews.

Semly works like a team of specialized AI agents working 24/7 on your brand’s visibility in LLM models. The agents analyze AI responses, prompts, competitors, sources, content, and brand data, and then point out actions that can help increase the chances of the brand appearing in AI recommendations.

Semly helps you check:

• whether AI knows your brand

• which questions your brand appears for

• whether AI recommends it

• how it compares to competitors

• which sources AI models use

• which actions can improve visibility

Semly isn’t a classic SEO tool. The platform analyzes brand visibility in AI-generated answers, not just positions in search results.

When will I see the first data?

The first data may appear after monitoring is launched and the AI models’ answers are processed.

How quickly the data appears can depend on:

• number of prompts

• number of analyzed AI models

• active plan

• project configuration

• site availability

• product feed availability

• scope of analysis

The first results show your starting point. It’s best to assess stable visibility changes over a longer period, e.g. after a few weeks of regular monitoring.

Why isn’t my brand showing up in AI?

There can be a few reasons why your brand doesn’t appear in AI answers.

The most common reasons:

• AI doesn’t have enough information about the brand

• the brand isn’t well connected with a given prompt

• the competitors has stronger sources

• the site is missing content that answers the user’s question

• the brand description is too generic

• products have poor descriptions

• the site may be poorly accessible for AI bots

• there’s not enough content in the knowledge base

• the AI model uses sources where your brand doesn’t appear

What you can do:

• complete your brand profile

• add products or a Google Shopping XML file (online stores only)

• check the prompts

• analyze the sources

• compare yourself with the competitors

• follow Semly’s recommendations

• generate content for the most important visibility gaps

The absence of a brand in the answer doesn’t always mean there’s an error. It often means that AI still doesn’t have clear and reliable enough information to recommend a brand in a given context.

Why does the competitors show up more often than my brand?

The competitors may show up more often if AI models have more data, sources, or content that connect it to a given user question.

Possible reasons:

• the competitors appears in rankings

• the competitors has more reviews

• the competitors has better how-to content

• the competitors has more detailed product descriptions

• the competitors is quoted more often

• the competitors shows up in sources used by AI

• your brand doesn’t have content for a given prompt

• your offer is described too generally

What to check:

• prompts only for the competitor

• sources supporting the competitors

• the brand’s position in the answers

• sentiment of the answers

• Semly’s recommendations

• gaps in content and product data

Greater visibility of the competitors doesn’t always mean a better offer. It often means that AI has more structured information about the competitors.

Why do results differ between AI models?

Different AI models can generate different answers to the same prompt.

The differences can come from:

• other data sources

• a different way of generating answers

• model updates

• different interpretations of the prompt

• different mechanisms for citing sources

• differences in data availability

• a different context for the answer

Example:

Differences between models are normal. That’s why it’s worth analyzing visibility separately for each model and also together for the whole project.

Why does visibility change over time?

AI answers aren’t fixed. The same prompt can give different results depending on time, model, sources, and context.

Visibility can change because of:

• AI model updates

• new sources on the Internet

• changes on the brand’s website

• changes in competitors’ content

• new articles in the knowledge base

• product feed updates

• seasonality of queries

• implemented recommendations

• changes in source availability

Don’t judge visibility based only on one day. The most important thing is the trend over time.

Does Semly automatically improve brand visibility?

Semly analyzes visibility, shows the sources of problems, and prepares recommendations. Some actions are done automatically, and some need to be implemented manually.

Examples of automatic actions:

• generating an article

• preparing content in the Content Generator

• publishing in the knowledge base

• marking the recommendation as completed

• preparing ready-made content or files

Examples of manual actions:

• pasting the llms.txt file

• updating robots.txt

• adding a link in the page footer

• adding the knowledge base to the XML sitemap

• improving content in the CMS

• updating data in the store

Semly often prepares a ready-made solution. Your task is to implement it automatically in the panel or copy it and add it in the right place.

Do I have to install code on the website?

In most cases, the basic Semly setup doesn’t require installing any code on your site.

You can use Semly via:

• a Google Shopping XML file (online stores only)

• ready-made integrations

• a knowledge base on your subdomain

Some actions may require technical changes, e.g. DNS configuration, adding a link in the footer, updating robots.txt or adding llms.txt.

If a recommendation requires a technical action, Semly provides instructions or a ready-made solution to copy.

Does Semly affect my site’s SEO?

Just monitoring visibility in Semly shouldn’t interfere with your site’s SEO, because it doesn’t require installing scripts or changing the code.

SEO can only be affected by the actions you implement outside Semly, such as:

• publishing new content

• adding a knowledge base

• internal linking

• updating robots.txt

• changes in the sitemap

• changes in the site structure

• improving product descriptions

Technical changes, such as robots.txt or sitemap, are worth implementing carefully. If you’re not sure, consult them with a technical person.

What is a Google Shopping XML file?

Google Shopping XML is a product file that contains data about products in an online store.

It can contain, among other things:

• product names

• product descriptions

• prices

• availability

• categories

• photos

• links to products

• product IDs

• brand

• EAN or GTIN

Semly uses the XML file to better understand the store’s offer and analyze it in the context of questions asked to AI models.

If you don’t know where to find the XML file, check out the article “How to get a link to the XML file from the store platform”.

What to do if product import doesn’t work?

If the products weren’t imported, check the most common reasons.

Possible issues:

• the link doesn’t lead directly to the XML file

• the file requires a login and password

• the login details are incorrect

• the file is empty

• the file contains technical errors

• the server blocks access to the file

• the file address has been changed

• the file has incorrect encoding

• the file doesn’t contain the required product data

What to do:

• open the XML link in the browser

• check the link in incognito mode

• make sure you can see the XML structure

• add login and password if the file is protected

• check the file encoding

• contact a technical person or Semly support

If the XML link doesn’t work in the browser, Semly probably won’t be able to fetch the products either.

What is a prompt?

A prompt is a question or instruction from the user to the AI.

In Semly, a prompt represents a real user intention, e.g. a question about a product, a service, a comparison or a recommendation.

Example of a weak prompt:

Example of a good prompt:

The prompt should feel like a natural conversation with AI, not a short SEO phrase.

How many prompts should you add at the start?

The more well-chosen prompts you add, the better market coverage you'll get in Semly. A larger number of questions lets you better see for which customer intentions your brand is visible, where competitors show up, and in which areas you have the biggest gaps.

However, it's worth remembering that it's not just the number of prompts that matters, but also their quality. Prompts should reflect real customer questions, different stages of the purchase decision, and the most important product or service categories.

A good set of prompts should include:

• questions about the most important categories of products or services

• purchase-related questions

• comparison questions

• educational questions

• questions about specific customer problems

• questions about availability, price, delivery, or location

• questions related to the competitors

The broader and more accurate your set of prompts, the more precisely Semly can show how your brand stacks up against the market. That way, reports aren’t based on a few random questions, but show a real picture of brand visibility in AI.

What are AI answer sources?

Sources are domains, pages, and materials that AI models can use when generating answers.

Sources can be:

• brand website

• blog

• knowledge base

• product pages

• category pages

• rankings

• catalogs

• reviews

• forums

• industry media

• marketplaces

• competitors’ websites

Sources help you understand why AI recommends a given brand or why the competitors shows up more often.

What is Semly’s knowledge base?

The Semly knowledge base is a public page with articles prepared based on the analysis of brand visibility in AI.

It can run under your subdomain, e.g.:

knowledge.yourdomain.com

The knowledge base is available for users and LLM bots. It’s technically optimized for AI models and can include an automatic sitemap, llms.txt, structured data, content in Markdown and JSON-LD, and public access via API and MCP.

The knowledge base helps organize information about the brand in a way that’s friendly for users and AI systems.

Should the content in the knowledge base be unique?

Yes. Articles in the knowledge base should be unique and shouldn’t be copied 1:1 from the blog, product page, or category page.

To avoid duplicate content:

• create articles for specific prompts

• describe the topic from a different perspective

• add practical context

• link to existing pages instead of copying their content

• update articles according to the recommendations

• avoid repeating the same paragraphs

Don’t publish copies of content from the current site in the knowledge base. Articles should be unique and useful for users.

Do I have to add a link to the knowledge base on my site?

Yes, it’s a good idea to add a link to the knowledge base from your website, for example in the footer.

It’s also worth adding the knowledge base to the XML sitemap.

This way:

• users will find content more easily

• bots can detect the knowledge base faster

• the knowledge base will be better linked with the main domain

• articles can be more easily analyzed by AI systems

After launching the knowledge base, add a link to it in the site footer and add it to the XML sitemap.

What is llms.txt?

The llms.txt file is a simple text file that helps AI systems understand what a site is and where its most important resources are located.

It can contain:

• brand description

• link to the sitemap

• link to the knowledge base

• links to the most important sections

• information about the language and market

• tips for AI systems

The llms.txt file doesn’t replace good content, but it helps AI systems find the most important resources faster.

Are the effects of the recommendations immediate?

Not always. AI models and systems that analyze sources may need some time to take new content or technical changes into account.

The effect can be influenced by:

• frequency of model updates

• availability of new sources

• quality of implemented content

• correctness of linking

• site availability for bots

• competitors in a given topic

• number of monitored prompts

• changes in product data

After implementing the recommendations, watch the trend over time. Don’t judge the effect based on just one day.

How to report a problem to Semly?

If you need help, write to the Semly support team:

[email protected]

It’s useful to include the following in your ticket:

• account email address

• brand name

• domain address

• short description of the problem

• screenshot

• link to the XML file if the problem concerns products

• prompt name if the problem concerns a report

• information about when the problem occurred

The more specific information you provide in the ticket, the faster the Semly team will be able to help.

Related articles

Summary

The most common questions are usually about project setup, brand visibility, differences between AI models, product import, sources, recommendations, and the knowledge base.

The most important rules:

• complete your brand profile

• add products or an integration

• create prompts as natural user questions

• analyze the report together with competitors and sources

• implement recommendations starting from the highest priority

• publish unique content in the knowledge base

• add a link to the knowledge base on your website

• track trends over time

• if you have any issues, contact [email protected]

If you’re not sure where to start, go to the article “Quick start with Semly” and complete the basic project setup steps.