AI Document Search chatbot
SleekAI adds an AI chatbot for AI Document Search 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.
Document libraries are write-only by default
Every team with a serious document library has the same artifact: a media folder of PDFs, a download archive, and a search box that does nothing for the content inside the files.
Visitors and staff click through three filenames before guessing which one might have the answer. The library is a write-only store: the team adds documents, nobody reads them, and the content sits in a 200-page PDF for years without ever surfacing the paragraph that matters.
SleekAI changes the contract. The reading shifts from clicking files to asking questions, which is the only reason a document library ever existed in the first place.
Features
Searches long documents
Publish long-form documents as WordPress posts or pages and sync them to the OpenAI Files vector store from the SleekAI admin.
Scoped retrieval
Group documents by purpose so the policy bot only retrieves from the policy set, and the compliance bot only retrieves from the compliance set. Multibot keeps the two scopes from leaking into each other.
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 SleekAI replaces document search
Compliance libraries
Audit teams ask plain-language questions and get the policy paragraph plus the citation. The reading shifts from skimming 60-page PDFs to asking questions, which is what compliance libraries are for in the first place.
Research archives
Universities and policy think tanks index reports and working papers into the vector store.
Legal and HR docs
The bot only retrieves from documents the role is allowed to see, scoped via display conditions and the per-bot document set.
How it works
Map your data
Choose the posts, fields, taxonomies or users the bot should know and reference them in the instruction.
Pair with live grounding
For shorter content that lives in WordPress, ground live from the database.
Set display conditions
Decide which pages, post types, roles or logged-in states show the chatbot.
Pick a model
Store your OpenAI, Anthropic, Google or OpenRouter key once in the shared AI settings, or add a compatible endpoint, and choose the chatbot’s model.
Why a document chatbot earns the archive its keep
Document libraries have always been the most expensive write-only artifact in any organisation. Compliance teams spend weeks producing a policy document, design teams spend days laying it out, the IT team uploads it to the intranet, and then nobody ever reads it again.
The reading layer has always been the bottleneck, because asking a 60-page PDF a question requires either reading the PDF or having the one person who wrote it on call.
AI document search collapses that bottleneck. The library stops being a write-only store and starts being a knowledge surface. A compliance officer can ask a coverage question and get the right paragraph in seconds, instead of paging through the PDF or pinging the policy author.
A new hire can ask the handbook a question and get a cited answer, instead of asking a colleague who would rather not be the human help desk. A research analyst can ask a paper a topical question without re-reading every appendix.
The structural change is bigger than the productivity gain: the library finally becomes interrogable, which means the team can write better documents, because the questions the library doesn’t answer well show up in the log. That feedback loop is what document libraries have always lacked. The redesign of the intranet was never the missing piece. The interrogability of the content was.
Frequently asked questions
What if I don’t want to use OpenAI for retrieval?
For pure WordPress content (posts, ACF, taxonomies), no vector store is needed. The bot grounds live from the database on each request.
Can it cite the page number?
Instruct the bot in the system prompt to cite the document name and page or section heading.
Can I restrict document access by role?
Yes. Group documents into separate vector stores per bot, then restrict each bot to a role via display conditions. The compliance bot can be admin-only, the public docs bot can be open. Roles map to the same WordPress user accounts you already manage; SSO and SAML logins flow through unchanged.
How do I update a document?
Most teams keep the latest version live and archive previous versions with a date suffix for audit trails.
How does retrieval compare to a dedicated RAG tool?
OpenAI Files is a competent general-purpose retrieval surface. For most WordPress sites and document libraries it covers the use case. SleekAI is the right call when keeping everything in WordPress is the priority.
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.
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