Conversational Assistant

A chatbot: you, a prompt, and a model

Architecture introduced 30 Nov 2022

The simplest AI assistant. You type, the app wraps your words together with some standing instructions, the model reads it all and replies. No internet, no memory, no actions — just conversation.

InstructionsDataActionsControl / decisionFeedback / logs⧚crosses a trust boundary

👆 Click any component or flow to inspect its risks & defenses

Follow a request · step 1 of 5

← / → keys

It starts with you typing a question into the chat box.

Scenarios on this architecture

📈

The Crescendo

Every message looks innocent — but together they walk the model past its guardrails

✂️

One Character Past the Guard

A single inserted letter makes the guard and the model read the same text differently

🚪

The Classifier That Waves It Through

The safety guard is itself a trained model — and someone poisoned its lessons

Next: RAG Knowledge Assistant →