Kai answers only from what you connect, so this is where its quality is actually decided. Open AI agents and choose Add content to see the sources.
Help Articles — your help center. The best place to start, because one article both answers the question inside the AI and stands on its own for someone reading it.
News & Changelogs — what you've shipped. Worth connecting because “is this available yet” is a question help centers rarely answer.
Snippets are text written for Kai and not published anywhere. This is where things go that are true but not worth a public article: current pricing edge cases, the wording you use for a known issue, internal policy on refunds.
They're also the fastest fix for a wrong answer. Writing a three-line snippet takes a minute; writing a good article takes longer and can wait until you know the question is common.
A snippet can also be long. One snippet can hold a whole checklist, runbook or troubleshooting guide, with Markdown headings and lists, and you edit it right in Gleap whenever it changes. That makes it the place for a private document you want to maintain inside Gleap: nothing to upload, nothing published. Tag it internal to keep it out of customer-facing answers (Keep internal content out of customer answers).
Four sources exist so you don't have to rewrite what's written.
Websites — crawls any public site and uses what it finds. The usual first move for a product whose documentation lives outside Gleap. A crawl is a snapshot that refreshes on a schedule, not a live sync.
Notion — connects your workspace, for teams whose real documentation lives there. Choose Sync content when you import and edits made in Notion reach Kai automatically; this is the way to keep an external knowledge base continuously up to date.
Files — PDF, Word, PowerPoint, Excel and Markdown, converted to text on upload. Good for manuals and spec sheets nobody will ever port into articles. An upload is a copy: changes to the original file don't flow through.
YouTube — analyses a video or a whole playlist. If your onboarding is a video series, this makes it answerable in text.
Code Repositories — connect a GitHub repository so your code can serve as context. This is what lets an AI answer questions about behaviour nobody wrote down.
API Data Sources — let Kai call an API of yours during a conversation to look up live, customer-specific data, such as an order, a booking or an account status. Nothing is imported or indexed: Kai reads the data at the moment it needs it. They're for per-customer lookups, not for keeping documentation in sync.
The same picker also offers API actions and MCP servers. Those aren't knowledge — they let the AI do something rather than know something. If you want an answer, add a source; if you want an action, add a tool.
Publish help articles for the questions you already answer most often, and add snippets for everything that's true but not publishable. That combination covers more real questions than any amount of connected material, because it's written to answer rather than to describe.
