RAG Knowledge Assistant

A chatbot that looks things up in your documents

Architecture introduced 22 May 2020

This assistant doesn't rely only on what the model already knows — it searches a library of your documents, grabs the most relevant pages, and hands them to the model to answer from. Great for accuracy; it also means the model now reads content other people wrote.

InstructionsDataActionsControl / decisionFeedback / logs

👆 Click any component in the diagram to inspect its risks & defenses

Follow a request · step 1 of 5

← / → keys

You ask a question — say, 'What's our refund window?'

Scenarios on this architecture

🌀

The Refund That Never Existed

A support chatbot invents a policy — and the company is held to it

☠️

Poisoning the Well

An attacker edits the wiki; the assistant cites the lie back to everyone

🧲

Poison the Vector, Not the Words

An attacker crafts a gibberish passage whose embedding sits near thousands of questions — so it's retrieved everywhere

Next: Tool-Using Agent →