Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Stop the Confident BS: Reflective Retrieval Agents and Human-in-the-Loop Interrupts
See how a reflective agent prototype halts for human clarification, preventing hallucinations from poorly defined context and upgrading basic RAG.
We built a reflective agent prototype that evaluates its own retrieved context and halts for human clarification before it hallucinates.
In the live demo, we’ll first break a standard one-prompt RAG setup to show how it confidently gives answers when faced with poorly defined context. Then, we will query our prototype, showcasing the live execution. You will see the agent evaluate its context, hit an uncertainty threshold, trigger a Human-in-the-Loop (HITL) interrupt to ask for missing parameters, and finally generate a factually grounded answer.