What if an AI could remember you—not just your last question, but your preferences, past conversations, and unique personality? In this episode, host Robert is joined by AI Engineer Terresa Pan to discuss EchoStar, a groundbreaking hierarchical memory system for AI. Terresa explains how different "memory banks" (episodic, semantic, and procedural) work together to create an AI with a genuine, long-term memory, allowing it to truly listen, adapt, and build an evolving relationship with its user.

Ever wondered how AI can seamlessly juggle text, images, and data analysis all at once? On this episode of AI in Action, we're unlocking the secrets behind Google's Agent Development Kit with expert Teresa Pan. She's here to discuss how ADK's unique approach to 'artifacts' is transforming the way developers build sophisticated AI agents. We'll explore her fascinating applications, from an AI-powered research assistant to a creative LinkedIn content generator. Stay tuned for a look under the hood of next-generation AI!

AI is evolving rapidly, moving beyond information processing to tackle complex tasks. Today, we explore the "Grand Code Agent," an AI by Teresa Pan that showcases this shift. Forget rigid commands; this agent uses Python code to interact with tools, retrieve financial data, visualize information from PDFs and images, and even generate memes. We'll delve into how this "code-first" approach, powered by the SmolAgents framework, offers greater flexibility, efficiency, and even self-debugging capabilities, changing how AI gets things done. Join us for a behind-the-scenes look at this fascinating technology.

This episode discusses an AI Multi-Agent Simulation Project, exemplified by an "AI Debate Simulator." It utilizes Large Language Models (LLMs), grounded by Retrieval-Augmented Generation (RAG) with a Pinecone vector database, to simulate discussions among AI personas representing various individuals. The system allows users to configure simulations with different participants and topics, observe the multi-round interactions, review the knowledge sources used, and pose follow-up questions. Built using Langchain, LangGraph, and Streamlit, the application features a user interface for setup and review, and leverages backend services like Google Generative AI for language processing and Pinecone for knowledge storage.

The podcast introduces an AI-powered staffing platform called Interactive SmartMatch made by Terresa Pan, an AI engineer and consultant.

The platform aims to improve internal efficiency by using AI to optimally match consultants to projects based on skills, availability, and project needs.

Key features include automatic extraction of project requirements, a human-in-the-loop verification process, real-time consultant matching with a scoring system, and the use of technologies like Google Gemini, LangChain, and Supabase for its functionality.

For more information, visit Terresa Pan's AI Agent Garden

OpenAI’s O3 and O3-mini are impressive feats of engineering, pushing the boundaries of what’s currently possible. But the journey toward Artificial General Intelligence isn’t a sprint to saturate existing benchmarks. It’s a marathon requiring us to constantly refine our understanding of intelligence itself and, crucially, to evolve the yardsticks we use to measure it. The focus needs to shift towards challenges like ARC and Frontier Math, pushing researchers beyond memorization and towards genuine problem-solving. Only then can we truly gauge how far we’ve come and how much further we have to go on the path to creating truly intelligent machines.

This episode discusses a Medium article by AI engineer and social media strategist Terresa Pan. It outlines three key strategies for creating successful short-form videos: Tagging thinking, Establishing a clear stance, and Incorporating personal experiences. Tagging involves using numerous relevant keywords to maximize reach, while a defined stance—taking a side on an issue—builds a strong brand identity and loyal following. Finally, integrating personal experiences creates unique and engaging content that resonates with viewers. The article also advises on adopting a specific posture, suggesting that "strong" creators should appear vulnerable, and "weak" creators should maintain positivity and authenticity.

This episode discusses a Medium article by AI engineer and social media strategist Terresa Pan, titled "The Art of Product Storytelling." It focuses on enhancing product presentation in short videos. It offers seven key approaches to visually showcasing products: using the product, exaggeration, comparison, similarity, using intermediaries, highlighting material qualities, and employing metaphors. The article also emphasizes the importance of strategic lighting to improve the visual appeal of the product. Specific examples are provided for each technique to illustrate practical application in short video formats. The overall goal is to make products more captivating and memorable to viewers.

This episode discusses a Medium article by AI engineer and social media strategist Terresa Pan. It explores narrative aesthetics in short videos, focusing on the manipulation of space to enhance storytelling. It examines how spatial elements like lighting, depth, and arrangement contribute to character identity, evoke emotions, and create a sense of realism. The article details techniques for controlling spatial depth and using elements like mirrors and dynamic foreground objects to build atmosphere. Finally, it discusses the strategic movement of characters within and between spaces to advance the narrative.

This episode discusses a Medium article by AI engineer and social media strategist Terresa Pan discusses narrative aesthetics in short-form video. The core concept is manipulating time to control audience emotion, achieved through pacing and storytelling techniques. Pan details various methods, including altering narrative time versus story time, employing repetition and contrast, and utilizing visual and auditory elements like color, framing, and sound design. She emphasizes the importance of creating conflict and utilizing varied perspectives and tones to engage viewers. Ultimately, the article offers a framework for crafting compelling short videos by skillfully managing the experience of time.