Skip to content

Knowledge base

AI

A knowledge base is the set of content an AI assistant checks to answer: catalog, FAQ, guides, shipping and return policies. It decides what the assistant knows about the brand and its products.

How it works

Content is imported into the base: a sync with the site, files, web pages. It's split into passages and indexed.

When a question comes in, the system finds the relevant passages and passes them to the LLM, which writes the answer from them. That's how RAG (retrieval-augmented generation) works.

The base has to keep up with the brand. If the return policy changes, the base has to change the same day, or the assistant keeps giving the old one. And when the information isn't there, a well-configured assistant says so or hands over, instead of making it up.

Why it matters in e-commerce

Answer quality depends on the base first. A shopper who doesn't get an answer hesitates, and often leaves without buying.

An up-to-date base also takes load off customer service. Questions about shipping, returns or product care get answered without waiting for an advisor.

Further reading: The 6-step checklist to launch your AI shopping assistant

Real-life example

A skincare brand imports its product pages, FAQ and routine guides into the base. A shopper asks whether a serum can be used in the morning with sunscreen. The routine guide covers it, so the assistant gives the brand's recommendation. If no content mentions it, the assistant says so and offers to pass the question to an advisor.

 

  • 90%

    answer rate among engaged shoppers

  • 81.8%

    of conversations handled by AI at Caudalie

Common confusion

Adding a document to the knowledge base doesn't retrain the model. In most AI assistants, the document is looked up at question time. Changes take effect quickly, and they're just as easy to undo.

The iAdvize approach

A knowledge base that flags its own gaps

The knowledge base behind the iAdvize AI Shopping Assistant combines the catalog with content the brand imports (FAQ, product content). It sends alerts on gaps spotted in real conversations. When the assistant can't answer, the request goes to an advisor or becomes a ticket.

 

Frequently asked questions

What goes into a knowledge base?

The catalog, FAQ, shipping and return policies, size, care and how-to guides. Anything customer service explains over and over belongs there.

How often should it be updated?

Every time a policy, collection or set of terms changes. Unanswered questions also show what's missing.

What happens when the information isn't in the base?

The assistant should say so instead of making something up. With iAdvize, the request then goes to an advisor or becomes a ticket in the customer service tool (Zendesk, Gorgias, Salesforce).