Real World AI Agent Stories // Zach Wallace // #283

Key takeaways

Efficiency in data integration is crucial to the success of AI applications.
AI agents can significantly reduce the time spent on repetitive tasks, empowering educators and enhancing user experiences.
Collaboration between technical and non-technical teams is essential for developing effective AI solutions.
Risk management and quality assurance frameworks, like eVALs, are necessary when deploying AI in production.
Future trends indicate an increase in the use of agents across various industries, leading to significant organizational changes.

Summary

Transforming Data Integration at Nearpod

Zach Wallace discusses the challenges and solutions in transforming Nearpod's data platform. He explains how the company managed data from disparate sources and improved integration using tools like DBT and Redshift. By establishing a data product exchange and implementing a data mesh concept, they have enhanced their ability to process large-scale data efficiently, moving from traditional ETL processes to real-time updates and reporting.

Understanding AI Agents and Their Applications

The conversation shifts towards AI agents, with Zach elaborating on their role in the edtech and e-commerce sectors. He describes how agents assist in generating personalized content for users while ensuring compliance with local standards and regulations. The vital connection between data platforms and AI performance is underscored, emphasizing the need for quality data to facilitate reliable responses from AI systems.

Challenges and Innovations in AI Production

Zach highlights the complexities of integrating AI into production, especially in highly regulated environments. He addresses the risk management inherent in deploying non-deterministic models and how eVALs are used to ensure the quality and reliability of these AI agents. The importance of collaboration between engineers and other departments is stressed, highlighting the framework developed to assess cost efficiency and monitor agent performance.

Future of Agents and Organizational Shifts

Looking ahead, Zach touches on the potential for agents to revolutionize various industries beyond edtech. As organizations adopt these technologies, the workflow dynamics within teams are expected to evolve, with greater interdisciplinary collaboration. He addresses the balance of risk and innovation when launching new AI features and the future possibilities of scaling these solutions across different sectors.

Show notes

Machine Learning, AI Agents, and Autonomy // MLOps Podcast #283 with Zach Wallace, Staff Software Engineer at Nearpod Inc.

// Abstract

Demetrios chats with Zach Wallace, engineering manager at Nearpod, about integrating AI agents in e-commerce and edtech. They discuss using agents for personalized user targeting, adapting AI models with real-time data, and ensuring efficiency through clear task definitions. Zach shares how Nearpod streamlined data integration with tools like Redshift and DBT, enabling real-time updates. The conversation covers challenges like maintaining AI in production, handling high-quality data, and meeting regulatory standards. Zach also highlights the cost-efficiency framework for deploying and decommissioning agents and the transformative potential of LLMs in education.

// Bio

Software Engineer with 10 years of experience. Started my career as an Application Engineer, but I have transformed into a Platform Engineer. As a Platform Engineer, I have handled the problems described below: - Localization across 6-7 different languages - Building a custom local environment tool for our engineers - Building a Data Platform - Building standards and interfaces for Agentic AI within ed-tech.

// MLOps Swag/Merch

https://shop.mlops.community/

// Related Links

https://medium.com/renaissance-learning-r-d/data-platform-transform-a-data-monolith-9d5290a552ef

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: /dpbrinkm/

Connect with Zach on LinkedIn: https: /zachary-wallace/

Timestamps:

[00:00] Zach's preferred coffee

[00:24] Takeaways

[01:25] Data platform pivot

[04:06] Data integration with DBT

[06:50] Data mesh partial adoption

[08:55] Data product

[10:11] Agent Architectures and Deployment

[15:35] Agent vs LLM

[20:28] AI Agent Analytics

[22:18] Agent Design and Scope

[26:52] DAG Agent Workflow Design

[30:25] Cost Considerations in AI

[35:00] Agent Deployment and Costing

[42:25] AI Evaluation Use Cases

[45:25] Agent vs ML for Contracts

[46:55] Wrap up