Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Empathic AI Clarifying Questions
The talk demonstrates how an Empathic AI Coach generates context‑aware clarifying questions using reinforcement learning with human feedback, improving interaction relevance.
We will be presenting a prototype for an Empathic AI Coach designed to improve AI interactions by focusing on asking insightful clarifying questions before generating responses. Instead of immediately providing a full answer, the AI will first engage with the user to better understand their intent, making conversations feel more natural and interactive. The presentation will explore the motivation behind this approach, emphasizing the need for AI to become more steerable and user-centered. It will showcase how the model generates clarifying questions, leveraging reinforcement learning with human feedback to refine its ability to ask meaningful and contextually relevant inquiries. Additionally, the discussion will cover the technical foundations of this approach and its potential impact on creating AI systems that are more helpful, adaptable, and aligned with human communication patterns.
Related projects
Empathic AI Agent
Toronto
Learn how an empathic AI agent uses Langchain to generate clarifying questions, improving response relevance and reducing hallucinations…
Building Autonomous AI Agents
Toronto
Live demo of autonomous AI agents using the crewAI framework, showing real‑time learning and decision‑making, with code on…
Collaborating Agents
Toronto
The talk explains how blockchain can record AI agents' actions, enabling transparent, auditable collaboration and verifiable decision‑making across…
What would a Personal AI Tutor look like?
Toronto
Explore how Advisory uses Neo4j roadmaps and chat history to create a transparent AI tutoring system that cites…
Ai Agents
Toronto
An overview of designing and deploying AI agents and MCP solutions at CIBC, covering architecture, integration, testing, and…
Building Agentic AI for Intelligent Facility Operations
Toronto
Demonstration of an autonomous AI agent that ingests live building sensor data, identifies energy usage patterns, and automatically…