Profile
A knowledge base is never finished, and it goes out of date because keeping it current is nobody's job.
Meanwhile your tickets show exactly which questions people do ask and which answers are missing.
The Knowledge Base Manager puts the two side by side: which questions keep coming back without an article, and which articles are never used.
What it does, step by step
- Analyse ticketsWhich topics keep coming back, and in what wording.
- Find the gapsQuestions asked often with no article to answer them.
- Write a draftBased on how your team currently answers the question in tickets.
- Flag outdated articlesArticles nobody opens any more, or that refer to something that no longer exists.
- Submit for publicationA person reviews and publishes. It does not publish anything itself.
Works with these systems
Zendesk- Freshdesk
Jira Service Management
Confluence
SharePoint- Help centre
Teams
Slack
- APIs
- Databases
Is your system not listed? We can connect any system, even if there is no standard integration. View all integrations.
What runs automatically and what does not
You stay in control.
Not every decision should be made automatically. For each workflow, we set out:
- What can happen automatically.
- What is put forward for approval first.
- When a person is brought in.
- What information is stored.
- How actions are logged.
Is this a fit for your organisation?
A good fit if
- Support teams with an existing knowledge base.
- Organisations where the same questions keep coming back.
- Situations where the knowledge base lags behind the product.
Less of a fit if
- Organisations without a ticketing system: then there is no source to draw on.
- New products with no history.
What it can deliver
- A knowledge base that grows with what people actually ask.
- Less time spent by support staff writing the same answer over and over.
- Insight into which articles do nothing.
Directions, not promises. As soon as there is evidence from a client project, it will appear here as a substantiated result.
Frequently asked questions
Does the AI publish articles in the knowledge base itself?
No. It writes a draft and submits it. A knowledge base is the source other answers rely on. If unchecked text gets in there, one mistake multiplies.
Where does it get the content for a new article?
From how your own team currently answers the question in tickets. That is usually the best material there is, because it has been tested on real customers.
How does it know an article is out of date?
From usage and from contradiction: an article nobody opens any more, or one whose content no longer matches how questions are answered now. It flags it. It deletes nothing.
Does this work alongside a support assistant?
Yes, and that is the logical combination. The knowledge base is the source the support assistant answers from, so the better it is, the more the assistant can handle on its own.
How to put this to work
- 1A short callTogether we look at your process and your systems, and whether this task is the best place to start.
- 2Set up on your rulesIntegrations with your own systems, and agreeing what may run automatically and what a person approves.
- 3Measure and adjustFirst alongside your team, only then on its own. We look at what it delivers and adjust.