Download all docs

Recipe: Support Assistant

This recipe builds a searchable support assistant with a markdown knowledge base, vector search, an agent, and a lightweight frontend.

Elements

ElementRole
documentStores support articles as markdown pages.
vectorStores embeddings for semantic retrieval.
triformerAnswers user questions with retrieved context.
viewProvides an internal support console or customer-facing search UI.
slack, http, or websocketConnects the assistant to the outside world.

Flow

  1. Create a document element for the knowledge base.
  2. Import markdown pages into the document.
  3. Vectorize the document.
  4. Create a triformer agent.
  5. Attach relevant prompts, tools, and data sources.
  6. Create a view for search, answer display, and escalation controls.
  7. Add an io element if the assistant needs to receive messages from Slack, HTTP, or realtime clients.

Why Triform Helps

The document stays editable as markdown, the search index is generated from the same content, and the assistant can discover its available actions through the API. You get a working operational app rather than a pile of disconnected services.

Next Pages