Home / Services / AI and automation / Knowledge assistants
Knowledge assistants
Where is the latest version of that policy?
An internal assistant that answers staff questions from your policies, manuals, contracts and project files, links every answer to its source, and respects who is allowed to see what.
- An assistant connected to the document sources you choose
- Permission sync with Microsoft Entra ID or Google Workspace
- Access through Teams, Slack or a web app
- A source list and indexing schedule your team controls
- An evaluation set of real questions with expected answers
- Usage reports and a list of unanswered questions
Proof you can check
Our own products, numbers and community record, linked wherever you can check them.
(opens in a new tab)
(opens in a new tab)
(opens in a new tab)- 300,000+sites run Divi Extended (opens in a new tab)
- Platinumsponsor, WordCamp Rajasthan 2026 (opens in a new tab)
- 6 + 1free plugins and a theme on WordPress.org (opens in a new tab)
- 4.7 / 5on Trustpilot, 116 reviews of Divi Extended (opens in a new tab)
What is included
The work, piece by piece.
Connected sources
SharePoint, OneDrive, Google Drive, Confluence, Notion and file servers indexed on a schedule, so answers follow the latest version.
Answers with citations
Each answer names the document and section it came from, so staff can open the source and check it.
Access control
Permissions carried over from the source, so HR files, board papers and client contracts stay with the people cleared to read them.
Where staff already work
Available in Microsoft Teams, Slack, a browser tab or your intranet, with single sign-on.
Across languages
A question asked in one language can find the answer in a document written in another, with the reply in the language of the question.
Gaps and outdated content
Reports of questions with no good answer and of documents that contradict each other, so owners know what to update.
Signs you need this
When teams usually call us.
01
New joiners ask the same questions for months
The answers exist in a handbook or a shared drive, but nobody can find them on their own.
02
Several versions of the same procedure are in circulation
Staff follow whichever copy they saved last, and mistakes trace back to an old file.
03
Senior staff have become the search engine
Experienced people lose part of every day answering questions a document already covers.
How we work
No surprises, start to finish.
Talk to the developers doing the work, by email or call, whenever you need.
01
Talk
Tell us what you need. We ask questions until the scope is clear.
02
Plan and quote
A clear scope with an hourly, fixed or monthly-hours price.
03
Build on staging
Every change is built on a staging site first, never on your live site.
04
Sign off and launch
You review and approve. Then we go live with zero downtime.
05
Care
We stay on for updates, fixes and new features, if you want us to.
Related
Often part of the same project.
- AI copilots for staffAssistants built around one team's daily work
- AI chat for support and leadsAn assistant that answers from your content
- AI strategy and governanceReadiness, use cases, policy and roadmap
- HealthcarePatient booking, reminders and clinic operations
- Professional servicesLaw, accounting, consulting and advisory firms
- Education and trainingAdmissions, learning platforms and student support
For agencies
Your development team for WordPress, under your name.
Agencies around the world send us their builds on WordPress. We do the work, you keep the client, and our name appears nowhere.
White-label
Your brand on everything. No Elicus credit, ever.
NDA-friendly
Happy to sign yours before we see a brief.
Scale on demand
We grow the team to fit the project.
Your terms
Something specific in mind? We'll talk it through.
Questions
Before you ask.
Can it show documents a user should not see?
No. Search runs with the user's own permissions, so a document that person cannot open in SharePoint or Drive never appears in their answers.
What if two documents disagree?
The assistant shows both sources and says they differ, instead of picking one. The conflict is also listed in the content report for the owner to resolve.
Is our content used to train public models?
No. We use providers and settings under which your data is not used for training, and we document that choice. Self-hosted models are an option where policy requires them.
Does it work with scanned PDFs?
Yes. Scanned files go through text recognition when they are indexed. Scans too poor to read are listed so they can be replaced with better copies.
Start a project
Tell us what you’re building.
A few lines is enough. The developers who will do the work read every message.
