Techsplainers by IBM

This episode of Techsplainers explains the concept of multi-agent collaboration. It discusses how multi-agent systems, comprising multiple AI agents, coordinate actions in a distributed system to achieve complex tasks. These tasks, once handled only by large language models, now include customer service triage, financial analysis, technical troubleshooting, and more. The podcast details how agents...

In this episode of Techsplainers , host Alice explains the concept of multi-agent systems. She describes how these systems consist of multiple AI agents working together to complete complex tasks, with each agent maintaining autonomy yet cooperating and coordinating through communication and distributed problem-solving. We also discuss different architectural designs (centralized and decentralized...

This episode of Techsplainers explores vibe coding—using AI to generate software code from natural language prompts, accelerating development while freeing humans for creative work.

This episode of Techsplainers explores vision language models (VLMs)—AI systems that bridge visual and textual understanding to perform tasks from image captioning to visual reasoning.

This episode of Techsplainers examines generative AI—how it creates original content, the technology behind it, and its real-world applications and challenges.

This episode of Techsplainers explores model deployment—the process of moving machine learning models to production environments where they can deliver real business value.

This episode of Techsplainers examines AI Model Lifecycle Management—the methodology and tools needed to manage the complete AI pipeline from data collection to deployment.

This episode of Techsplainers unpacks machine learning pipelines, from data processing and model development to deployment strategies and monitoring in production environments.

This episode of Techsplainers explores the practical components of MLOps pipelines—from data management and model deployment to monitoring, governance, and implementation levels.

This episode of Techsplainers explores MLOps—a set of practices for streamlining machine learning operations, automating deployment, and improving model performance through continuous monitoring.

This episode of Techsplainers investigates notorious ransomware variants, from CryptoLocker to the Colonial Pipeline attack. Learn about ransom payment trends, legal implications, and effective prevention strategies.

This episode of Techsplainers looks at how phishing attacks work and how to protect. Learn to identify various phishing techniques, recognize warning signs, and implement effective prevention strategies.

This episode of Techsplainers covers how social engineering attacks exploit human psychology rather than technical vulnerabilities. Learn about different attack types—from phishing to baiting—and effective strategies to protect yourself and your organization.

This episode of Techsplainers explores what data breaches are, how they occur, and the strategies that can prevent them. Discover the true costs, common attack vectors, and how AI-powered security can dramatically reduce breach impact.

In this episode of Techsplainers , we dive deeper into network observability, comparing it to network performance monitoring and DevOps observability. Learn how observability goes beyond static thresholds and predefined metrics to provide end-to-end visibility, richer context, and predictive analytics for dynamic network environments. We also explore why network observability is critical for indus...

In this episode of Techsplainers , we explore network observability, a proactive approach to understanding and managing complex network environments. Unlike traditional monitoring, which focuses on predefined metrics, network observability provides real-time visibility into network health and performance across on-premises, hybrid, and multicloud infrastructures. We break down its five pillars—met...

In this episode of Techsplainers , we explore the key differences between observability and monitoring and why both are critical for managing complex IT environments. Monitoring focuses on tracking predefined metrics and alerting teams when something goes wrong, while observability goes further by providing context and insights into why issues occur and how to fix them. We discuss how observabilit...

In this episode of Techsplainers , we break down the three pillars of observability: metrics, logs, and traces. We'll explain how they provide the foundation for understanding complex cloud-native systems. Discover what each pillar does, why they matter, and how they complement each other to deliver actionable insights for DevOps teams. We also explore system events, distributed tracing, and emerg...

This episode of Techsplainers explains data quality management (DQM)—a set of practices that ensure data is accurate, complete, consistent, timely, unique, and valid. Learn why high-quality data is critical for business intelligence, regulatory compliance, and AI performance, and explore key techniques like data profiling, cleansing, validation, and monitoring.

This episode of Techsplainers explains what a data fabric is and why it’s critical for modern enterprises. A data fabric is a data architecture that unifies and democratizes data access across hybrid and multicloud environments. It uses AI, metadata, and automation to break down silos, improve governance, and enable self-service data access—accelerating analytics, decision-making, and AI adoption.

This episode of Techsplainers explains what a data lakehouse is and why it’s transforming modern data management. A data lakehouse combines the low-cost, flexible storage of data lakes with the high-performance analytics of data warehouses, enabling unified data systems for advanced analytics and AI. Learn how lakehouses evolved, their architecture, and how they compare to data lakes and warehouse...

This episode of Techsplainers explains what a data lake is, how it evolved, and why it’s a cornerstone of modern data architecture. We cover its role in storing massive amounts of raw data in any format, its cloud-based foundations, and how it supports AI and machine learning workloads. Plus, learn how data lakes compare to warehouses and lakehouses.

This episode of Techsplainers explains what data architecture is, why it matters, and how it shapes modern data strategies. From centralized and decentralized models to frameworks like TOGAF, we explore how a well-designed architecture enables scalability, governance, and advanced use cases like AI and real-time analytics. Done right, data architecture turns raw data into a strategic asset.

In this episode of Techsplainers , host Alice explains the five main types of AI agents: simple reflex agents (like thermostats), model-based reflex agents (like robot vacuums), goal-based agents (like navigation robots), utility-based agents (like self-driving cars), and learning agents (like reinforcement learning systems). Each type is discussed in detail, highlighting its capabilities, applica...

Join us on today's episode of Techsplainers as we delve into the world of AI agents, explaining their functions, capabilities, and operational components. We explore how AI agents leverage advanced natural language processing and tool calling to surpass traditional AI limitations, autonomously performing tasks and learning from experiences. Our discussion covers three key stages of AI agent operat...