Embed an AI chatbot anywhere
SleekAI adds an AI chatbot for Embedded Chatbot 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.
Floating widgets are not always the right shape
A floating widget is the right shape for a marketing site, but it is the wrong shape for a 4,000-word install guide. The user is reading; covering the prose with a bubble breaks the very thing they came for. SleekAI’s embedded mode places the chatbot inline with the content.
If a reader is on a Stripe-integration tutorial and asks ‘where do I put the secret key’, the embed already has the post body in its context window and answers from the actual instructions, not a generic webhook tutorial.
Multiple embeds per page are supported, each with its own ID, system prompt, and conversation log. A common pattern is a tutorial bot at the top of a docs page, a feedback bot at the bottom asking what was unclear, and neither knows about the other’s thread.
Page builders are first-class too; the shortcode renders cleanly inside Elementor, Bricks, Beaver Builder, and any builder that accepts a text widget, so you do not need a builder-specific module just to host the embed.
Features
Page-scoped context
Each embed pulls in the post or page it lives on so answers stay tight to the surrounding content.
Multiple per page
Run a tutorial bot at the top and a feedback bot at the bottom with different prompts. Each embed keeps its own ID, transcript, and conversation thread.
Answers from your data
Map post titles, content, post meta, taxonomies or a WP_Query into the instruction, and the bot answers from what your site actually publishes.
Where embedded chatbots fit
Documentation pages
An inline assistant beside the install guide answers configuration questions using the actual page as context, not a generic vendor knowledge base.
Tutorial posts
Help readers run the steps without scrolling away from the article. The embed sees the surrounding code blocks and quotes them back when explaining errors.
Repeat questions
Answer the questions visitors ask every day from the pages and posts where you already answer them.
How an embedded chatbot reads the page
Map your data
Choose the posts, fields, taxonomies or users the bot should know and reference them in the instruction.
Configure the prompt
Each embed has its own system prompt and model, so a docs embed can be terse and technical while a tutorial embed can walk through steps. Prompts live alongside your other SleekAI bots.
Set display conditions
Decide which pages, post types, roles or logged-in states show the chatbot.
Run multiple per page
Place a tutorial bot above the steps and a feedback bot below them. Each has its own ID, transcript, and prompt, so the threads do not bleed into each other.
Where embedded beats floating for content
The shape of the assistant matters more than people admit. A floating widget is good at being available; an embed is good at being part of the page. On a long-form install guide the user is scanning code blocks, copying commands, and matching their terminal output to the screenshots.
They do not want the chat hidden behind a bubble that requires a click and a scroll-back to reference. Inline, the chat sits at the natural breakpoints of the content – between the prerequisites and the steps, after a tricky configuration block, before the troubleshooting section.
That changes who uses it. Floating widgets get clicked by people who could not find what they wanted; embeds get used by people who are already in the flow and have a follow-up. The conversion shape is different too.
Floating chats often produce ‘where do I find X’ messages; embeds produce ‘this command failed with output Y, what does that mean’. The second is far more valuable both for the reader, who gets a real answer, and for your team, who learns where the docs need work.
Frequently asked questions
Can I run multiple embeds on one page?
Yes, and it is a common pattern for documentation. Each embed keeps its own conversation log in the database.
Can it be used with page builders?
Yes. The embed renders client-side so the builder’s preview canvas usually shows a placeholder; it loads fully on the live page.
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.
Can I control where the chatbot appears?
Yes. Display conditions cover post type, post, post status, post template, taxonomy, term, user role, logged-in state and WordPress conditional tags such as front page, archive, search and 404.
Are conversations stored?
Only if you turn on logging for that chatbot. SleekAI then stores each visitor message and each completed reply, which you read and delete on the chatbot’s Logs page, and a retention period can delete old logs.
Can I run more than one chatbot?
Yes. Each chatbot has its own instruction, data, display conditions and styling, so different sections of a site can get different bots.
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