Where Knowledge Base retrieval is used

Six AI surfaces call the same Knowledge Base retrieval engine: the Specialist agent’s search_documentation tool, the voice agent’s search_kb tool, Sidekick’s suggested answers, Self-Learning’s gap detection, the in-app editor’s search, and the search box on your public help center. Because it is one shared function, an article that ranks well for one of these ranks well for all six.

The six call sites

1. Specialist agent’s search_documentation tool — the AI agent inside a conversation looks up articles to answer a customer question.
2. Voice agent’s search_kb tool — the same, but in a phone call. Limited to 5 results and short excerpts so the agent can speak the answer naturally.
3. Sidekick’s suggested-answer retrieval — when an agent is replying to a conversation, Sidekick offers relevant articles to insert.
4. Self-Learning’s gap detection — when the system looks for cases where no good answer exists, it retrieves what it would have answered with.
5. Internal /api/kb/search-semantic — used by the in-app editor’s search.
6. Public POST /api/public/kb/:tenantId/search — the search box on your public help center, where market filters and language overlays apply.

Why this matters for authoring

The engine behind all six surfaces is the same hybrid keyword + vector pipeline, so optimizing an article for one surface optimizes it for every surface — including the human-facing help center search. There is no separate tuning per surface; the only per-surface differences are input limits (like the voice agent’s 5-result cap) and the market/language filters that apply on the public search.

For a precise account of how the engine ranks articles, see How the AI picks an article. For what to do about it as an author, see Write articles the AI retrieves well.

See also

• How the AI picks an article
• Write articles the AI retrieves well
• KB search and AI retrieval — concept
• Self-Learning