Turn your blog archive into a personalized recommendation engine
SleekAI adds an AI chatbot for Chatbot for Content Marketing to your WordPress site. It answers from the content you choose, such as posts, pages, custom post types, post meta, taxonomies and user data, with your own OpenAI, Anthropic, Google, or OpenRouter key.
Most content libraries are read by nobody after week two
Content marketing has a discoverability problem. A team publishes 80 posts a year, sinks 4 to 6 hours into each, and after a quarter only the top 5 by traffic actually get read.
The rest sit in the archive collecting dust because the navigation, the sidebar, and the related-posts widget were never designed for the volume of content the site now has. Even the most loyal readers see maybe 3 articles per session before they leave.
SleekAI reads the entire archive: wp_posts for titles and excerpts, wp_postmeta for custom fields and Yoast or Rank Math keywords, wp_terms for categories and tags. The chatbot recommends the post that actually answers the visitor’s question, in the context of what they have just asked.
A reader who shows up via Google for a beginner topic and then asks a follow-up question about a more advanced angle gets recommended the right intermediate post, not whatever the related-posts plugin matched on shared tags.
The same approach works for lead magnets and course modules. Map the lead magnet library or the LearnDash module catalog as variables, and the bot weaves the relevant download or lesson into its replies. The conversion lift comes from showing the right asset at the right moment in the conversation, instead of the same gated PDF banner that sits in the sidebar regardless of what the reader is asking.
Features
Archive-aware
The bot reads the full library of posts, not just the most recent 10. A site with 800 articles gets the deep cuts recommended when they actually answer a reader’s question, not just the homepage features.
Lead magnet weaving
Map your downloadable resources as variables and the prompt tells the bot when to surface them. The right ebook shows up in the middle of a relevant conversation instead of cluttering every sidebar with the same banner.
Course module suggestions
LearnDash, Tutor LMS, and LifterLMS modules are all custom post types. Tick them in the variable mapper and the bot can recommend the specific lesson that goes deeper on whatever the reader just asked about.
Where a content-aware bot fits
Editorial archives
Large blogs with 500-plus posts use the bot as a smart search.
Lead magnet libraries
Marketing sites with 8-20 gated assets use the bot to recommend the right one based on the conversation. Download rates climb when the resource matches the visitor’s actual question.
Course catalogs
Online education sites recommend specific modules from LearnDash or Tutor LMS. The reader picks the lesson that fits their current skill, which lifts both course discovery and enrollment.
From archive to personalized recs
Map the archive
Tick post types like post, lead-magnet, and lesson in the variable mapper.
Set the recommendation prompt
Add tone guidance and an instruction to disclose gated or paid content honestly.
Scope display
Show the widget on blog post pages, category archives, and resource library pages. Hide it on checkout, account, and admin-adjacent areas where it would distract from completing a task.
Map your data
Choose the posts, fields, taxonomies or users the bot should know and reference them in the instruction.
The compounding value of unread content
Content marketing teams almost always overproduce. The pipeline is calibrated to keep weekly cadence, which means articles ship faster than they can ever be promoted. The result is an archive where 80 percent of posts get 5 percent of the traffic, and most of the rest get only the share of organic Google decides to throw at them.
The math is depressing if you let it be. A team that publishes 2 posts a week for 3 years has 312 articles in the library; if only 50 get meaningful traffic, the other 262 represent something like 1,300 hours of writing time sitting dormant.
The way out is to stop treating the archive as a chronological feed and start treating it as a queryable library. Most CMS navigation cannot do that. A chatbot trained on the archive can. SleekAI’s approach moves content marketing closer to how readers actually search. Lead magnets show up at the moment they fit, not as a generic gated banner.
Course modules get recommended after the reader has signaled what skill they want to deepen. The economics flip. The same archive that was generating diminishing returns suddenly has every post available to drive an engaged second session. The ROI of a 2-year-old article goes up, not down, because the bot keeps surfacing it whenever it actually fits a reader’s need.
Frequently asked questions
Can it recommend posts behind a paywall or membership?
It can mention them if you let it. Map the membership-restricted CPT as variables and the bot can recommend the gated article along with the upgrade link. For honest framing, the prompt should tell the bot to disclose that the resource is members-only so readers know what to expect before they click.
Will the bot keep recommending the same posts?
Only if the data points there. If you want to surface evergreen pillar content reliably, give those posts a custom field tag in postmeta and weight them in the system prompt.
How does this compare to a related-posts plugin?
Related-posts plugins match by shared tags or categories at the post level; the recommendation does not change with the reader. A chatbot recommends based on what the reader just asked, which can be very different from the page they landed on. Both have a role; the bot is closer to a personalized sidebar than a replacement for category navigation.
Can it recommend external content as well?
The bot reads what you map. Most teams keep the bot scoped to first-party content to control quality; if you want to reference external sources, the system prompt should tell it to cite them with a clear disclaimer that they are not your work.
How does it handle multilingual content?
The bot’s reply language is set by the prompt or by the model’s detection of the user’s language; both work well in practice.
Which AI providers does it support?
OpenAI, Anthropic, Google and OpenRouter, plus custom OpenAI-compatible endpoints. You bring your own API key and the provider bills you directly.
Where does the chatbot get its answers?
From the WordPress data you map into its instruction: post titles and content, post meta, ACF and Meta Box fields, taxonomies, terms, users and user meta, or a WP_Query. Values resolve on every request.
Can it act on a visitor’s behalf?
No. A chatbot answers questions.
Related pages
Pricing
Explore our flexible licensing options tailored to your needs. Upgrade your license anytime to access more features, or opt for a lifetime license for ongoing value, including lifetime updates and lifetime support. Our hassle-free upgrade process ensures that our platform can grow with you, starting from whichever plan you choose.
…or get the Bundle Deal
and save €250
The Bundle (unlimited sites)
Pay once, own it forever
Elevate your WordPress site with our exclusive plugin bundle that includes all of our premium plugins in one package. Enjoy lifetime updates and lifetime support. Save significantly compared to buying plugins individually.
What’s included
SleekAI
SleekByte
SleekMotion
SleekPixel
SleekView
SleekRank
SleekTrack