Techsplainers by IBM

Explore Think 2026: https://www.ibm.biz/think2026event

This episode of Techsplainers introduces OpenRAG, IBM's open-source framework that connects large language models to enterprise data sources. We explore how OpenRAG builds bridges between powerful AI and organizational knowledge through Retrieval-Augmented Generation (RAG), enabling AI systems to ground their responses in actual company information rather than relying solely on training data. The discussion covers OpenRAG's flexible deployment options—from fully self-hosted architectures to hybrid cloud implementations—and highlights its modular design that allows organizations to customize components based on their specific needs. We examine real-world applications including enterprise knowledge assistants, customer support automation, regulatory compliance tools, research document analysis, data exploration interfaces, and collaborative knowledge systems. The episode concludes with practical guidance on getting started with OpenRAG, emphasizing its accessibility for both experimentation and enterprise-scale deployment.

Find more information at https://www.ibm.com/think/topics/openrag
Find more episodes at https://www.ibm.biz/techsplainers-podcast

Narrated by Matt Finio

Explore Think 2026: https://www.ibm.biz/think2026event

This episode of Techsplainers explores data retrieval, the essential process of accessing information from various data sources. We examine how this field has evolved beyond simple database queries to encompass complex AI-driven techniques. The discussion covers traditional approaches like SQL and indexing alongside modern methods including vector search, natural language processing, and retrieval augmented generation (RAG). We highlight how agentic RAG elevates retrieval capabilities through intelligent decision-making components like semantic caching, routing agents, and query planning. Real-world examples demonstrate impressive efficiency gains across healthcare, financial services, and e-commerce, while we also address challenges including data quality, security concerns, and vendor lock-in. As organizations manage ever-expanding data volumes and AI workloads, sophisticated data retrieval becomes increasingly critical to business success.

Find more information at https://www.ibm.com/think/topics/data-retrieval

Find more episodes at https://www.ibm.biz/techsplainers-podcast

Narrated by Matt Finio

Explore Think 2026: https://www.ibm.biz/think2026event

This episode of *Techsplainers* explores multi-agent collaboration, where multiple AI agents work together as a coordinated team to accomplish complex tasks. We explain how these systems have evolved beyond traditional LLMs to create autonomous workflows for research, support, analysis, and operations. The discussion covers key collaboration models including rule-based, role-based, and model-based approaches, and examines leading frameworks like IBM's Bee Agent, LangChain, and OpenAI's Swarm. We also highlight Watsonx Orchestrate as an enterprise solution for orchestrating AI-enabled workflows through interconnected components. Throughout the episode, we use the analogy of drone teams searching disaster sites to illustrate how independent agents can coordinate effectively without centralized control to tackle complex challenges that would overwhelm a single agent.

Find more information at https://www.ibm.com/think/topics/multi-agent-collaboration
Find more episodes at https://www.ibm.biz/techsplainers-podcast

Narrated by Matt Finio

This episode of Techsplainers explores data governance, the essential framework that ensures organizational data is properly managed, protected, and utilized. Amanda explains how data governance serves as an ""air traffic control system"" for information, defining policies and procedures for data collection, storage, and usage throughout its lifecycle. The discussion covers the four key components of governance frameworks: program goals and roles, data standards and policies, auditing procedures, and supporting tools. We examine how effective governance delivers tangible benefits including enhanced data value, balanced access, compliance with regulations like GDPR and HIPAA, and responsible AI development. The episode also addresses common implementation challenges such as lack of sponsorship, inconsistent architecture, and evolving AI requirements, before concluding with best practices including automation, creating a comprehensive data catalog, and continuous improvement. As the final installment in our data for AI series, this episode demonstrates how governance provides the structure that enables everything from AI-ready data to synthetic data creation.

Find more information at https://www.ibm.com/think/topics/data-governance

Find more episodes at https://www.ibm.biz/techsplainers-podcast

Narrated by Amanda Downie

This episode of Techsplainers explores synthetic data - artificially generated information designed to mimic real-world data while preserving statistical properties and patterns. Amanda explains how synthetic data has become critical for AI development by addressing issues of data scarcity, privacy concerns, and training needs. The discussion covers the three types of synthetic data (fully synthetic, partially synthetic, and hybrid) and various generation techniques including statistical methods, GANs, transformer models, VAEs, and agent-based modeling. We examine the significant benefits of synthetic data - customization flexibility, improved efficiency, enhanced privacy protection, and data enrichment - while also addressing challenges like bias propagation, model collapse, accuracy-privacy tradeoffs, and verification needs. The episode concludes with real-world applications across automotive, finance, healthcare, and manufacturing industries, demonstrating how synthetic data is becoming essential for AI development.

Find more information at https://www.ibm.com/think/topics/synthetic-data
Find more episodes at https://www.ibm.biz/techsplainers-podcast

Narrated by Amanda Downie