Recommendations in Semly are ready-made action ideas prepared based on the analysis of your brand, prompts, sources, competition, AI model responses, and project configuration.
Their goal is to show what’s worth improving, adding, or implementing to increase the chances of your brand showing up in AI answers.
What matters is that Semly doesn’t just show a general suggestion. In many cases you get a ready-made solution that you can either implement automatically in Semly or copy and paste into the right place on your site or in the technical configuration.
Recommendations are specific tasks that help improve your brand’s visibility in AI.
They can cover, among other things:
technical configuration of the website or store
robots.txt file
llms.txt file
sitemap
brand data
product data
content on the site
knowledge base
sources
prompts
competition
Each recommendation points out a problem or opportunity and shows what action is worth taking.
The report itself shows what’s happening with your brand’s visibility. The recommendations show what you can do about it.
With the recommendations you can:
improve your site’s accessibility for AI bots
organize your brand data
fill in missing information
create content for your customers’ key questions
expand your knowledge base
improve product data
increase your chances of being recommended in AI
reduce gaps compared to your competitors
react faster to technical issues
To go to the recommendations:
Log in to the Semly panel
Choose the right project
Go to the Recommendations section
Check the task list
Open the details of the selected recommendation
Perform the action automatically or copy the ready-made solution
In the Recommendations section you can see, among other things:
recommendation title
description of the problem or opportunity
priority
status
action details
ready-made solution
action execution button if available
manual implementation instructions
Semly can generate different types of recommendations, depending on the data detected in the project.
The most common types of recommendations are:
technical
content-related
product-related
brand-related
source-related
prompt-related
competition-related
knowledge-base-related
They relate to elements that can affect the availability of data for AI models.
Examples:
fix the robots.txt file
add or update the llms.txt file
add a sitemap
check the availability of sitemap.xml
add a link to the knowledge base
make sure AI bots can read important pages
These are about articles, descriptions, FAQs, and content that answers customer questions.
Examples:
create an article on the given topic
expand the content based on a specific prompt
add an answer to a frequently asked question
prepare a comparison guide
describe the brand’s advantages in a given category
They concern the quality of product data and how well the offer matches customer questions.
Examples:
improve product descriptions
fill in missing categories
add better product names
check product availability
update the Google Shopping XML file
They concern the places that AI can use when generating answers.
Examples:
check a source that supports the competition
make sure you’re present in an important directory
prepare content similar to a source that AI often uses
analyze the ranking where the competition appears
In Semly, some recommendations can be implemented automatically, and some need to be done manually outside the panel.
You can do some actions directly in Semly.
This can apply, for example, to:
generating an article
preparing content in the Generator
creating content in the knowledge base
marking the recommendation as done
preparing a ready-made file or piece of content
starting an action available in the panel
If a recommendation can be carried out automatically, you’ll see the right button or action in its details.
Example:
Create content
Mark as done
Copy the ready-made solution
Some recommendations require copying a ready-made solution and pasting it in the right place outside Semly.
This can apply for example to:
robots.txt file
llms.txt file
sitemap
DNS settings
link in the site footer
link in the menu
changes in the CMS
changes in the shop panel
updating the content on the site
Example:
Semly can prepare ready-made content for the llms.txt file, but you or a technical person have to paste it on the site in the right place.
Priority helps you figure out where to start.
In Semly you can come across recommendations with different levels of importance.
Most often:
critical
high
medium
low
Means an action that can block or seriously limit the analysis and visibility of the brand in AI.
Examples:
AI bots have limited access to the site
the robots.txt file blocks important resources
a key sitemap is missing
important data isn’t available
the configuration makes it harder to read the site
It’s worth doing these recommendations first.
This means an action that can have a big impact on brand visibility.
Examples:
creating content for an important prompt
improving product data
expanding the knowledge base
improving the brand description
filling in important sources
This means an action that’s important, but usually doesn’t block the basic analysis.
Examples:
polishing the content
expanding the FAQ
improving a less important category
filling in additional data
Means a supporting or optimization action.
Examples:
small content tweaks
additional data extensions
organizing less important elements
When you open a recommendation, you’ll see more info about why Semly suggests a given action.
The details may include:
problem description
explanation of the impact on visibility
ready-made solution to copy
button to perform an automatic action
manual implementation guide
In many recommendations, Semly prepares a ready-made solution that you can use right away.
This can be, for example:
ready article content
ready llms.txt file
ready sitemap
ready robots.txt file
ready brand description
ready list of recommendations
ready content to paste on the website
ready FAQ structure
ready suggestions for product descriptions
If the recommendation contains a ready-made solution:
Open the recommendation details
Read the description of how it works
Check the ready-made content or configuration
Copy the prepared solution
Paste it in the right place
Save the changes in your system
Go back to Semly and mark the recommendation as done if such an option is available
If Semly detects that the robots.txt configuration may be making it harder for AI bots to access your site, it can prepare a technical recommendation.
In such a recommendation you might see:
description of the problem
an explanation of why robots.txt matters
the full proposed content of the file
instructions on where to paste the change
info on what to check after deployment
Example steps:
Copy the ready-made content prepared by Semly
Open the robots.txt file of your site
Paste the copied content
Save the file
Check if the file is available at https://yourdomain.com/robots.txt
Mark the recommendation as done or run the test by clicking the Check again
The llms.txt file is a simple text file placed in the root directory of the domain that helps AI systems understand what the site does and which resources are the most important. It can contain a short brand description, links to key sections, sitemaps, knowledge bases, and other materials that are worth sharing with AI models.
The llms.txt file helps describe the site in a way that’s clear for AI systems and point to the most important resources.
If Semly generates a recommendation about llms.txt, you can get a ready-made file content.
In such a recommendation you might see:
a ready-made site description
links to the most important sections
information about language and market
instructions on how to publish the file
Example action:
Copy the ready-made content llms.txt
Create a file llms.txt in the main directory of the domain
Paste the content prepared by Semly
Save the file
Check if it works at https://yourdomain.com/llms.txt
Mark the recommendation as done
If Semly detects a prompt where the competition is visible and your brand doesn't show up in the answers, it can suggest creating content.
The recommendation can point to:
article topic
prompt related to the gap
competitor that appears more often
reason for creating the content
potential impact on visibility
option to generate an article in Semly
Example flow:
Open the recommendation
Check the prompt and the justification
Click the option to generate an article if it’s available
Review the generated content
Edit it if needed
Publish the content in the knowledge base or on the website
Monitor changes in visibility in the next reports
After implementing a recommendation, it’s worth marking it as completed if the panel offers such an option.
This helps organize your work and separate finished tasks from those that still need action.
Marking a recommendation as completed helps you:
track work progress
avoid repeating the same actions
tidy up your task list
come back later to analyze the results
manage your team’s work better
The effect of a recommendation doesn’t always show up right away. AI models and systems that use sources may need some time to take the new data into account.
After implementing the recommendations, check:
brand visibility
position for the related prompt
sentiment of the responses
sources of the AI responses
presence of competitors
change over time
new recommendations
It’s best to compare results before and after implementation in the same area, e.g. for the same prompt, topic, or source.
Some recommendations require access to site files, DNS, CMS, or the store panel.
If you don’t have technical access, pass the ready-made solution to the person responsible for the site.
It’s worth passing on:
recommendation content
ready-made solution from Semly
implementation location
short description of the purpose of the change
link to help article
screenshot of the recommendation
Sample message to the technical person:
Hi, Semly generated a recommendation for improving the visibility of the site in AI. I’m sending in the attachment the ready-made content to implement and the place where it should be added. Please check it and implement it according to the instructions.
The most common mistakes are:
ignoring critical recommendations
doing only easy tasks without analyzing priority
copying content to the wrong place
marking a recommendation as done before implementation
not checking how it works after implementation
removing existing robots.txt rules without analysis
publishing content without reading and editing it
implementing many changes at once without monitoring the effect
skipping recommendations related to sources
not comparing results before and after implementation
It’s best to treat recommendations as a current list of actions to improve your brand’s visibility in AI.
A good work rhythm might look like this:
once a week, check new recommendations
start with critical and high priority items
do the most important technical actions
pick 1 to 3 content recommendations
generate or prepare the content
mark completed tasks
check the results after a few days or weeks
compare the visibility change in the report
What are AI answer sources
How to read the Sources section
How to analyze prompt details
How to interpret AI model answers
How to generate the first article
How to set up a knowledge base on a subdomain
Semly recommendations show specific actions that can help improve brand visibility in AI answers.
The most important rules:
start with the highest priority recommendations
check the details and justification of each recommendation
use ready-made solutions prepared by Semly
do some actions automatically in the panel
copy some actions and apply them manually on the site or in the configuration
after implementation, mark the task as done
monitor the results in the visibility report
don’t ignore technical recommendations
