Techsplainers by IBM

This episode of Techsplainers explores just-in-time access, an identity security model that grants users temporary permissions only when they need them and removes that access automatically when the task is complete. Building on the principle of least privilege, the episode explains why time matters just as much as scope when controlling access to sensitive systems. The discussion looks at the risks created by standing privileges, including how stolen credentials can give attackers ongoing access to critical environments and make lateral movement easier. It breaks down the typical JIT workflow and compares three common implementation models: broker-and-remove, ephemeral accounts and temporary elevation. Along the way, listeners learn how JIT fits into broader identity security practices like privileged access management, zero trust, and zero standing privileges. The episode also examines why JIT is increasingly important for nonhuman identities and AI agents, which often operate at higher speed and scale than human users. Find more information at https://www.ibm.com/think/topics/just-in-time-access Find more episodes: https://www.ibm.biz/techsplainers-podcast Narrated by Dan Nosowitz

This episode of Techsplainers introduces the principle of least privilege, a core cybersecurity concept that limits users, applications and machine identities to only the access they need, only for as long as they need it. The episode explains how least privilege fits within identity and access management, reducing the blast radius of compromised credentials while ensuring that legitimate users have the access they need when they need it. The discussion also explores why least privilege has become more urgent as nonhuman identities like service accounts and AI agents multiply across modern environments. Finally, it looks at the operational side of enforcement, including privileged access management, identity governance and different access control models. Find more information at https://www.ibm.com/think/topics/principle-of-least-privilege Find more episodes: https://www.ibm.biz/techsplainers-podcast Narrated by Dan Nosowitz

This episode of Techsplainers explores how artificial intelligence is changing customer relationship management by helping organizations organize customer data, automate business processes and create more timely, relevant interactions across sales, marketing and service. It explains how AI moves CRM beyond recordkeeping and into prediction, personalization and operational insight. The episode looks at the rise of AI in CRM, tracing the shift from early database-style systems to modern platforms that use machine learning, natural language processing and generative AI to interpret customer behavior at scale. It covers the benefits most specific to AI-powered CRM, including predictive analytics, lead scoring, sentiment analysis, marketing personalization, workflow automation and the ability to manage unstructured data such as emails, transcripts and support notes. It also highlights practical use cases across business intelligence, customer service, sales optimization, customer service, sales optimization, process improvement and data management, while addressing the importance of accurate data, privacy and customer trust. As the final episode in the week’s series on improving customer experience with AI, it brings the focus inward to the systems that help connect every stage of the customer relationship. Find more information at https://www.ibm.com/think/topics/ai-crm Find more episodes: https://www.ibm.biz/techsplainers-podcastNarrated by Amanda Downie

This episode of Techsplainers explores how AI agents are changing customer service by moving beyond simple question answering into autonomous, goal-oriented support. It explains what makes AI agents different from standard chatbots and assistants, including their ability to retain memory, reason across multiple steps, use external tools and take action within connected systems. The episode follows how these agentic systems work in real customer service environments, from handling customer queries and retrieving knowledge base content to managing order tracking, identifying sentiment, summarizing conversations and automating administrative tasks. It also looks at how networks of specialized agents can work together across workflows to speed up service resolution and improve continuity across channels. Along the way, the discussion connects AI agents to the broader customer experience themes explored earlier in the week, including onboarding, response time and personalized support. Real-world examples such as Camping World and Avid Solutions show how agentic systems can improve engagement, reduce delays and streamline customer-facing operations. The episode also highlights four best practices for deployment: aligning agents with service strategy, equipping them with the right data and tools, integrating them into enterprise systems and helping human teams build the skills to work effectively alongside them. Find more information at https://www.ibm.com/think/topics/ai-agents-in-customer-service Find more episodes: https://www.ibm.biz/techsplainers-podcastNarrated by Amanda Downie

This episode of Techsplainers explores how artificial intelligence helps companies accelerate customer service response times across chat, email, social platforms and support portals. It explains why first response time is such an important measure of the support experience and how delayed replies can quickly affect customer trust, satisfaction and retention. The episode looks at both traditional and AI-enabled approaches to faster service, from knowledge bases and service level agreements to chatbots, automated first replies and intelligent self-service. It also examines how AI can classify incoming requests, detect customer intent, route tickets to the right team, assist agents with suggested responses and summarize conversations during handoffs. As the discussion moves into more advanced use cases, it covers workflow automation and agentic AI systems that can complete service tasks across multiple tools, reducing the time between a customer request and actual resolution. Along the way, the episode highlights the broader business benefits of AI-supported response acceleration, including improved availability, stronger customer satisfaction, increased support capacity, more consistent service and lower operational costs. Find more information at https://www.ibm.com/think/insights/accelerate-customer-service-response-time-ai Find more episodes: https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

"This episode of Techsplainers explores how artificial intelligence can speed up and improve the customer onboarding process, helping organizations move new customers from sign-up to success with less friction and more relevance. It explains how AI supports onboarding through intelligent automation, real-time personalization, conversational assistance and data-driven insights. The episode follows the onboarding journey step by step, showing how AI can simplify account creation, showing how AI can simplify account creation, tailor welcome messages, guide setup and configuration, support early product adoption and monitor engagement for signs of risk. It also looks at how onboarding teams can use AI to identify bottlenecks, improve activation rates and refine the process over time using measurable performance data. Along the way, the discussion highlights the broader benefits of AI-enabled onboarding, including faster time to value, improved customer satisfaction, stronger retention and greater operational efficiency. It also emphasizes an important limit: AI works best when it enhances a clear customer journey rather than trying to fix a broken one. For organizations trying to scale while keeping the experience personal, AI offers a way to make onboarding more consistent, more adaptive and more effective from the very beginning. Find more information at https://www.ibm.com/think/insights/using-ai-to-accelerate-customer-onboarding-process Find more episodes: https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores how AI is changing customer experience across the full customer journey, from product recommendations and virtual assistants to omnichannel support and virtual assistants to omnichannel support and real-time personalization. It explains how technologies like machine learning, natural language processing, predictive analytics and automation help businesses analyze customer behavior, respond faster and create more relevant interactions at scale. The episode follows the role AI plays behind the scenes, showing how companies can use it to connect touchpoints, improve CRM systems and better understand customer sentiment across reviews, chats and social channels. It also looks at the practical upside: improved efficiency, stronger personalization and more timely support. At the same time, it addresses the real challenges. Businesses still need to balance automation with empathy, connect AI tools to existing systems without adding friction, and build customer trust through transparency and reliable performance. Real-world examples from Wimbledon, Starbucks, Boots UK and Amazon help show how different organizations are applying AI to customer engagement today, while future trends point toward more immersive experiences, conversation intelligence and growing attention to AI ethics. Find more information at https://www.ibm.com/think/topics/ai-customer-experience Find more episodes: https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores immutable backups and why they are a core part of modern data protection. It explains how immutable backups create read-only copies of data that cannot be altered or deleted during a defined retention period, helping organizations defend against ransomware, accidental deletion, corruption and insider threats. The episode walks through the difference between traditional backups, immutable backups and immutable snapshots, showing how each fits into a layered recovery strategy. It also examines the technical building blocks behind immutable backups, including WORM storage, retention locks, partitioning, air gapping, continuous data protection, encryption, access controls and AI-based threat detection. Along the way, the discussion highlights the growing role immutable backups play in cyber resilience, disaster recovery and compliance across industries such as healthcare, finance and education. Listeners will also hear practical guidance on deployment choices, backup types, regular testing and integration with broader security operations. The result is a clear look at how immutable backups help organizations preserve data integrity and maintain reliable recovery options when systems are under attack. Learn more in https://www.ibm.com/think/topics/immutable-backups Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Matt Finio

This episode of Techsplainers explores immutable snapshots and why they are becoming an important part of modern infrastructure and cyber resilience strategies. It explains immutable snapshots as read-only, point-in-time copies of data that cannot be changed during their retention period, making them useful against malware, insider threats and accidental deletion. The episode walks through how immutable snapshots differ from immutable backups, why snapshots often provide more granular recovery points, and how supporting technologies such as WORM, copy-on-write, retention policies, metadata and management APIs work together to preserve clean restore points. It also looks at the financial and operational impact of breaches across hybrid environments, where data protection has become more complex and more costly. Along the way, listeners hear how immutable snapshots support disaster recovery, cyber recovery, data integrity, compliance and digital forensics. The discussion also covers real-world use cases in regulated industries and best practices for aligning snapshot policies with business recovery goals. Learn more in https://www.ibm.com/think/topics/immutable-snapshots Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Matt Finio

This episode of Techsplainers explores unified storage and how it brings file, block and object storage together under a single platform. It walks listeners through the core idea behind unified storage, then explains how each storage type works, where each one fits best and why most enterprise environments need more than one approach at the same time. The episode follows the operational challenges that arise when these storage types are managed in separate silos, including wasted capacity, added administrative overhead and fragmented visibility. It then examines the practical benefits of unification, from better capacity allocation and deduplication efficiency to simpler management and support for hybrid cloud and multicloud environments. Along the way, the discussion also covers the tradeoffs. Unified storage can involve up-front migration costs, potential vendor lock-in, performance considerations for mixed workloads and the risk of creating a broader single point of failure. By the end, listeners get a clear view of where unified storage fits, where it may be unnecessary and why it can be a useful approach for organizations balancing flexibility, efficiency and scale. Learn more in https://www.ibm.com/think/topics/unified-storage Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Matt Finio

This episode of Techsplainers explores network attached storage, or NAS, and explains why this long-standing storage approach still matters in modern infrastructure strategies. It walks through how NAS provides centralized file storage over a local network, making it easier for teams to share files, manage backups and maintain control over data. The episode follows NAS from the basics to the bigger picture, covering core components like HDDs, SSDs, controllers, operating systems and file-sharing protocols. It also explains the difference between scale-up and scale-out NAS, and compares enterprise NAS with smaller business or consumer setups. Along the way, clear comparisons between NAS, DAS and SAN architectures. The discussion also looks at where NAS fits today, including cloud integration, edge use cases and support for some AI workflows. Finally, it addresses the tradeoffs, the benefits, and the real-world use cases that keep NAS relevant. Learn more in https://www.ibm.com/think/topics/network-attached-storage Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Matt Finio

This episode of Techsplainers explores what data storage is and why it remains a foundational part of modern computing. It explains how storage differs from memory, how computers retain data over time, and why the growth of AI and IoT systems is increasing pressure on storage systems to scale efficiently. The episode walks through the main types of data storage: file, block and object storage, showing where each fits best in real-world environments. It also examines major storage architectures, including direct-attached storage, network-attached storage and storage area networks, highlighting the tradeoffs between simplicity, performance, cost and scalability. From SSDs and flash to cloud, hybrid cloud, AI and edge storage, the discussion follows how storage technologies are evolving to support new workloads. It also covers the growing role of storage in cybersecurity and compliance, including encryption, immutable snapshots, cyber resilience and recovery testing requirements in regulated industries. Finally, it introduces software-defined, virtualized and intelligent storage approaches that help organizations manage data more efficiently at scale. Learn more in https://www.ibm.com/think/topics/data-storage Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Matt Finio

This episode of Techsplainers explores NVMe, or Non-Volatile Memory Express, the protocol designed to help systems get more performance out of modern non-volatile storage like flash memory and SSDs. As the final episode in this data storage series, it connects the dots between storage media, system architecture and real-world performance. The episode explains why older storage protocols were built for mechanical hard drives and how that created bottlenecks once flash storage became much faster. It then breaks down how NVMe uses the PCIe bus, reduces overhead and supports far more parallel commands than earlier approaches, helping lower latency and improve throughput for demanding workloads. Listeners will hear where NVMe matters most, from enterprise databases and AI workloads to everyday laptops and desktops, and how it differs from NAND flash itself. The discussion also introduces NVMe over Fabrics, which extends NVMe principles into networked storage environments. By closing out the storage series with NVMe, the episode highlights a central takeaway from the broader run: storage performance depends on layers working together, from architecture and protection to media and protocol. Learn more in https://www.ibm.com/think/topics/nvme Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Elly Trickett "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores NAND flash memory, the non-volatile memory technology that underpins many modern storage devices, from USB drives and smartphones to enterprise solid-state drives. As the storage series moves deeper into the hardware layer, the episode explains how NAND flash fits into the broader story of performance, density and storage design. The discussion breaks down how NAND flash stores data without moving parts, why that enables faster access than traditional hard disk drives, and what makes it different from volatile memory like DRAM. It also examines the major types of NAND flash, including SLC, MLC, TLC and QLC, and explains the tradeoffs among speed, endurance, cost and capacity. The episode also introduces 3D NAND, showing how vertical stacking helped increase density and scale. Listeners will learn why NAND flash is foundational to modern flash storage, how it connects to broader storage architecture decisions and why it sets the stage for technologies like NVMe. Along the way, the episode also covers the limitations of NAND flash, including wear over time and the engineering required to manage it effectively. Learn more in https://www.ibm.com/think/topics/nand-flash Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Elly Trickett "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores hybrid cloud storage, the approach organizations use to manage data across both on-premises infrastructure and cloud environments. It explains why many businesses no longer treat storage as a single-location decision and instead use hybrid models to balance performance, cost, compliance and scalability. The episode walks through how hybrid cloud storage works, including storing active data locally, moving older or less frequently used information to the cloud, and using cloud environments for backup, disaster recovery and large-scale analytics. It also looks at the role of policy-based data movement, orchestration and visibility in keeping data accessible across environments without creating new silos. Listeners will hear how hybrid cloud storage supports practical use cases like archiving, resilience and modernization, while also introducing the challenges that come with it, including latency, governance and security. The discussion connects hybrid cloud storage to the broader storage series, showing how it brings together ideas around performance, protection and data placement in a more flexible architecture. Learn more in https://www.ibm.com/think/topics/hybrid-cloud-storage Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Elly Trickett "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores immutable storage, the storage approach that protects data by preventing it from being changed or deleted for a defined period of time, or in some cases permanently. Positioned within a broader data storage series, the episode explains how immutable storage differs from standard backup storage and why that distinction matters when organizations face ransomware, data corruption or strict compliance requirements. The discussion walks through the core idea of write once, read many, or WORM, and shows how immutable storage helps preserve trusted copies of information for recovery, audits and long-term archiving. It also looks at the practical mechanics behind retention periods and legal holds, along with the tradeoffs organizations need to consider when deciding what data should be locked and for how long. Listeners will hear how immutable storage supports cyber resilience, why it matters in regulated industries and where it fits among other storage approaches like flash, edge and AI storage. The episode also points toward the broader challenge of managing protected data across multiple environments. Learn more in https://www.ibm.com/think/topics/immutable-storage Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Elly Trickett "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores AI storage and shows how storage infrastructure changes when it is designed around modern AI workloads. Building on earlier discussions of data storage, storage architectures, flash, intelligent storage and edge storage, the episode shifts the focus to the demands created by model training, inference and large-scale data pipelines. The episode explains why AI workloads need more than raw capacity. It examines the need for high throughput, low latency and scalable infrastructure that can support accelerators, large datasets and constant data movement. It also looks at how AI environments rely on file, object and block storage in different ways, depending on the workload and access pattern. Listeners will also hear how data tiering, versioning, metadata, security and governance all shape effective AI storage strategies. Real-world examples from healthcare and retail help connect these ideas to practical use cases. The result is a clear overview of why AI storage is not a separate world from traditional storage, but a specialized approach built on the same foundations. Learn more in https://www.ibm.com/think/topics/ai-storage Find more information at https://www.ibm.com/think/podcasts/techsplainers Narrated by Elly Trickett "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores infrastructure automation as the broader goal behind infrastructure as code practices. It explains how automation allows organizations to provision, configure and manage infrastructure through repeatable, code-driven workflows instead of manual processes, making it possible to operate complex hybrid and multicloud environments with greater speed and reliability. The episode breaks infrastructure automation into three core functions: provisioning, configuration management and workflow orchestration. It also shows how organizations typically build toolchains that combine products such as Terraform, Ansible, Kubernetes and Jenkins to automate different stages of the infrastructure lifecycle. Along the way, it explains why guardrails, policy as code and developer self-service are essential for scaling automation safely. Listeners will also hear how infrastructure automation improves consistency, reduces risk, optimizes costs and strengthens governance across modern environments. The discussion also highlights the growing influence of AI through predictive analytics, intelligent autoscaling and automated root cause analysis. Find more information at https://www.ibm.com/think/topics/infrastructure-automation Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Alice Gomstyn "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores how Terraform is used to implement infrastructure as code, focusing on the practical mechanics that turn infrastructure from a manual process into a repeatable engineering discipline. It explains how Terraform’s declarative model lets teams define the end state of infrastructure in human-readable files, then automatically plan and apply changes based on dependencies and current state. The episode follows Terraform’s core workflow of write, plan and apply, showing how configuration files, state files, providers and modules work together to support consistent provisioning across cloud, on-premises and SaaS environments. It also examines why version control, reusable modules and execution plans are so central to the IaC model, helping teams standardize deployments, collaborate more effectively and reduce drift between environments. Along the way, the discussion highlights where Terraform fits alongside tools like Ansible and why its main strength is provisioning and lifecycle management at infrastructure level. The result is a clear, focused deep dive into Terraform’s role as one of the defining tools for modern IaC practices. Find more information at https://www.ibm.com/think/topics/terraform Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Alice Gomstyn "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores edge storage and why storing data closer to where it is created has become increasingly important in modern IT environments. As part of a larger data storage series, the episode explains how edge storage works in locations such as factories, retail stores, hospitals, vehicles and telecom networks, where fast response times and local data access matter. The discussion walks through the main reasons organizations use edge storage, including lower latency, reduced bandwidth demands and better resilience when connectivity is limited or inconsistent. It also looks at how edge storage fits into broader storage strategies rather than replacing centralized systems entirely. Real-world applications, from video analytics to industrial automation, help show how local storage can support faster decision-making and more efficient operations. The episode also addresses challenges, including security, management complexity and the need to coordinate data across many distributed sites. Overall, it gives listeners a clear view of the benefits, tradeoffs and practical role of edge storage in a connected world. Find more information at https://www.ibm.com/think/topics/edge-storageFind more episodes at https://www.ibm.com/think/podcasts/techsplainers. Narrated by Dan Segal "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores intelligent storage and how modern storage systems are evolving beyond passive data repositories. Building on a broader look at modern storage, this episode explains how intelligent storage uses analytics, automation and AI-driven insights to help organizations manage performance, capacity and resilience more effectively. The episode follows the logical flow of intelligent storage, beginning with how these systems collect telemetry and analyze workload behavior, then moving into how they support predictive maintenance, automated tiering and more efficient infrastructure use. It also examines why intelligent storage matters in environments shaped by hybrid cloud, cybersecurity threats and AI workloads that place new demands on performance and flexibility. Along the way, listeners learn how intelligent storage can help reduce manual administration, improve resource allocation and strengthen cyber resilience through anomaly detection and recovery-supporting features. The episode also addresses key challenges, including integration, governance and the need for human oversight when automation is involved. Find more information at https://www.ibm.com/think/topics/intelligent-storageFind more episodes at https://www.ibm.com/think/podcasts/techsplainers. Narrated by Dan Segal "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores flash storage, a foundational technology behind many of today’s fast, responsive digital systems. The episode explains what flash storage is, how it differs from traditional hard disk drives, and why its solid-state design helps reduce latency and improve application performance. It walks through the basics of non-volatile memory, SSDs, and enterprise flash systems, showing how data is stored on memory chips rather than spinning disks. Listeners are guided through the main advantages of flash storage, including speed, durability, energy efficiency and compact physical design, while also getting a clear explanation of its tradeoffs. The episode notes that flash cells wear down over time and explains how modern systems use techniques like wear leveling and error correction to manage endurance. It also introduces different flash types and shows why organizations choose different options depending on workload needs, cost targets and performance goals. The conversation closes by connecting flash storage to broader data storage strategy and to related topics like NAND flash memory and NVMe, setting up later episodes in the series. Find more information at https://www.ibm.com/think/topics/flash-storage Find more episodes at https://www.ibm.com/think/podcasts/techsplainers. Narrated by Dan Segal "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores the differences between object storage, file storage and block storage, helping listeners understand how each model organizes, stores and retrieves data. The episode explains how file storage uses familiar folders and files, why block storage is often chosen for databases and performance-sensitive workloads, and how object storage supports massive volumes of unstructured data with metadata-rich, API-based access. The discussion follows a clear comparison of how each storage model works, where it fits and what tradeoffs come with it. Listeners learn why file storage is intuitive for shared content and collaboration, why block storage gives applications more direct and efficient access to data, and why object storage is a strong fit for scale, archives, media libraries and cloud-native systems. The episode also highlights the benefits and limitations of each model around usability, latency, scalability and management. Rather than treating these as either-or technologies, the episode shows how many organizations use all three together to support a range of workloads across modern IT environments. Find more information at https://www.ibm.com/think/topics/object-vs-file-vs-block-storageFind more episodes at https://www.ibm.com/think/podcasts/techsplainers. Narrated by Dan Segal "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers introduces data storage and explains why it is one of the foundational parts of modern computing. The episode explores how storage records, organizes and protects digital information so it can be retrieved and used later, whether that data lives on a personal device, in a data center or across cloud environments. It follows storage from everyday use cases like apps, photos and media to enterprise needs such as archiving, backup and disaster recovery. Listeners are guided through how data storage works, including the difference between RAM and long-term storage, and the three major storage models: file storage, block storage and object storage. The discussion also breaks down core architectures such as DAS, NAS and SAN, along with common storage media and deployment options including HDDs, SSDs, cloud storage, hybrid cloud storage, AI storage and edge storage. It also highlights the benefits of scalability, flexibility and resilience, while addressing challenges tied to security, compliance, cost and growing data demands. Find more information at https://www.ibm.com/think/topics/data-storageFind more episodes at https://www.ibm.com/think/podcasts/techsplainers. Narrated by Dan Segal "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores provisioning through the lens of infrastructure as code, explaining why it is such a foundational part of modern IT operations. It breaks down provisioning as the process of setting up infrastructure and making resources available for systems and users, from servers and networks to applications, cloud services and devices. The episode also clarifies a common source of confusion by separating provisioning from configuration. Provisioning creates and allocates the underlying resource, while configuration tailors that resource for a specific workload or user need. From there, it examines several major types of provisioning, including server, network, application, cloud and device provisioning, showing how each supports a functioning IT environment. The discussion then shifts to automated provisioning and why it has become essential in DevOps-era organizations. It highlights how infrastructure as code helps automate provisioning through scripts and templates, reducing manual effort while improving speed, scalability, consistency and compliance. The episode also addresses the tradeoff of automation: while it reduces human error, mistakes in code can scale quickly if not reviewed carefully. Find more information at https://www.ibm.com/think/topics/provisioning Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Alice Gomstyn "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores infrastructure as code, the DevOps practice of automating infrastructure provisioning and management through configuration files rather than manual processes. It explains how IaC treats infrastructure like software, allowing teams to write, version, test and deploy infrastructure with the same rigor they apply to application code. The episode walks through the four-stage IaC workflow of write, version, provision and deploy, showing how configuration files, version control systems and automation engines work together to create repeatable, scalable infrastructure management. It also breaks down key implementation choices, including declarative versus imperative approaches and mutable versus immutable infrastructure, helping listeners understand the different ways organizations structure their IaC strategies. Along the way, the discussion highlights the major benefits of IaC, including faster provisioning, greater consistency, better security and compliance, accelerated development cycles, lower costs and protection against knowledge loss. It also shows how IaC fits directly into DevOps and CI/CD pipelines by ensuring environments stay aligned from development through production. The result is a practical introduction to one of the most important operating models in modern infrastructure. Find more information at https://www.ibm.com/think/topics/infrastructure-as-code. Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Alice Gomstyn "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers introduces IT infrastructure as the foundation of modern digital business. It explains how hardware, software and networking work together to support the systems organizations depend on every day, from servers and storage to operating systems, business applications and employee devices. The episode walks through the difference between traditional on-premises infrastructure and cloud infrastructure, highlighting how virtualization made modern cloud computing possible and helped pave the way for services like IaaS, PaaS, SaaS and hybrid cloud. It also explores why infrastructure has become a strategic business enabler, powering cloud computing, process automation, AI, generative AI and real-time analytics. Listeners will also hear how modern IT infrastructure supports innovation, improves security, and keeps evolving to support new developments in DevOps and AIOps. As the first episode in an IaC-focused week, it provides the essential foundation for understanding what infrastructure teams are actually managing and automating. Find more information at https://www.ibm.com/think/topics/infrastructure Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Alice Gomstyn "AI tools may be used to transcribe this episode and support selected stages of the production process. All AI-assisted content is reviewed by the production team before publication."

This episode of Techsplainers explores streaming analytics, the real-time analytics layer that helps organizations continuously ingest, process and analyze streaming data as it is generated. The episode explains how streaming analytics differs from traditional batch-based approaches by delivering insights with minimal latency, enabling businesses to act on events while they are still unfolding. Listeners are guided through why streaming analytics matters in modern business environments shaped by IoT, SaaS applications, financial transactions, social media and other continuous data sources. The discussion breaks down the four major components of a streaming analytics workflow—data ingestion, data processing and analysis, governance, and consumption—while also clarifying the subtle distinction between streaming analytics and real-time analytics. The episode highlights the growing connection between streaming analytics and AI, including support for AI agents, chatbots, recommendation engines, fraud detection models and predictive maintenance systems that depend on fresh, contextualized data. It also examines key benefits such as faster decision-making, better customer experiences, improved operational efficiency and stronger security, alongside the challenges of data integration, quality, governance, scalability and low-latency delivery. Major technologies such as Apache Kafka, Apache Flink, Spark Structured Streaming, Confluent and Iceberg are also introduced. Find more information at https://www.ibm.com/think/topics/streaming-analytics Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Ian Smalley

This episode of Techsplainers explores event-driven architecture, a software design approach built around detecting, publishing and responding to events as they happen. The episode explains how EDA differs from more traditional architectures by focusing on real-time data in motion instead of static data stored for later analysis. It walks through the core building blocks of an event-driven system—event producers, brokers and consumers—and shows how those components work together to support fast, asynchronous communication across distributed environments. Listeners are introduced to key architectural models, including publish-subscribe and event streaming, along with the event processing patterns that power everything from immediate reactions to advanced pattern detection. The discussion also highlights why EDA is so valuable in cloud-native and microservices environments, where loose coupling improves scalability, resilience and flexibility. Real-world applications include suspicious activity detection, predictive maintenance, dynamic pricing and inventory optimization. The episode also covers the practical challenges teams face, such as event ordering, eventual consistency, observability and duplicate handling. Find more information at https://www.ibm.com/think/topics/event-driven-architectureFind more episodes https://www.ibm.biz/techsplainers-podcastNarrated by Ian Smalley

This episode of Techsplainers explores Apache Kafka, the open-source event-streaming platform that has become a cornerstone of modern real-time data systems. The episode explains how Kafka helps organizations publish, store, process and consume streams of events with high throughput, low latency and strong reliability. Listeners are introduced to the concept of event streaming through familiar examples, from customer orders and website clicks to IoT sensor updates, before learning how Kafka differs from traditional message queues by retaining records for replay and independent consumption. The discussion then breaks down Kafka’s core architecture, including topics, partitions, brokers, offsets and replication, along with Kafka’s shift away from ZooKeeper toward KRaft for simpler cluster management. The episode also covers Kafka’s four primary APIs, its leading use cases in real-time data pipelines, streaming applications, microservices, cloud-native systems and IoT, and its broader ecosystem integrations with tools like Spark, Flink and Cassandra. Finally, it examines how Kafka compares with RabbitMQ and why Kafka is increasingly valuable in AI-driven systems that depend on live, continuously moving data. Find more information at https://www.ibm.com/think/topics/apache-kafka Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Ian Smalley

This episode of Techsplainers explores data streaming platforms and how they help organizations continuously capture, process, analyze and deliver data in real time or near-real time. The episode explains why these platforms have become essential as businesses shift from slower batch-based workflows to real-time decision-making powered by live data from applications, databases, sensors, logs and digital interactions. Listeners are guided through the business context behind this shift, including the rise of big data, event-driven architectures and the need for faster analytics, AI responsiveness and operational agility. The episode also examines how data streaming platforms support AI use cases such as fraud detection, recommendation engines, predictive maintenance and AI agents that depend on current context. From there, the discussion breaks down the four core architectural layers of a data streaming platform—source and ingestion, processing, destination and serving, and governance and management—while highlighting key characteristics such as scalability, fault tolerance, low latency and high throughput. The episode also reviews major open-source and managed technologies, including Apache Kafka, Apache Flink, Apache Spark, Confluent, Amazon Kinesis, Google Cloud Dataflow and Azure Stream Analytics. Find more information at https://www.ibm.com/think/topics/data-streaming-platform Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Ian Smalley

This episode of Techsplainers explores real-time data streaming and why it has become essential for modern enterprises that need immediate insight from fast-moving information. The episode explains how real-time streaming differs from traditional batch processing by handling data as it arrives, often within milliseconds, rather than waiting for scheduled runs. Listeners are guided through the main business benefits of this approach, including faster decision-making, improved operational efficiency, smarter data retention, decision-making, improved operational efficiency, smarter data retention, stronger risk management and more personalized customer experiences. The episode also highlights real-world applications across retail, banking, manufacturing and AI-driven systems that depend on current, continuously updated information. From there, the discussion breaks down the core components of streaming architecture—ingestion, processing and destination—and clarifies the close relationship between real-time data streaming and event streaming. It also reviews common technologies, such as Apache Kafka, Apache Flink and Spark Streaming, while addressing practical implementation challenges like cost, fault tolerance, observability, security and governance. Find more information at https://www.ibm.com/think/topics/real-time-data-streaming Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Ian Smalley

This episode of Techsplainers explores Crew AI, an open-source Python framework that enables the creation of collaborative AI teams with specialized roles and responsibilities. Developed by Joao Moura, Crew AI implements a manager-worker hierarchy where a coordinator agent delegates tasks to specialized workers based on their defined capabilities. We examine how this structured approach to collaboration allows AI teams to tackle complex, multifaceted projects by leveraging the complementary skills of different agents. The discussion details Crew AI's key components, including its role definition system, task delegation framework, structured collaboration protocol, tool integration capabilities, and memory management features. We highlight practical applications across content creation, product development, data analysis, and customer service, where role-based collaboration can deliver more comprehensive and nuanced results than single-agent approaches. While acknowledging current limitations in handling highly specialized tasks and the dependence on underlying language models, the episode emphasizes Crew AI's significance as a flexible, intuitive framework for organizing AI collaboration around clearly defined roles and responsibilities. Find more information at https://www.ibm.com/think/topics/crew-ai Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores LangChain, an open-source framework that's revolutionizing how developers build applications powered by large language models. Created by Harrison Chase in 2022, LangChain provides modular components that help connect AI models to external data sources, tools, and reasoning capabilities. We break down LangChain's key components—models, prompts, memory, chains, agents, and tools—explaining how they work together to overcome the inherent limitations of language models. The discussion highlights popular applications, including retrieval-augmented generation systems that connect AI to private data, conversational agents that can use external tools, document analysis solutions, and personal assistants. While emphasizing LangChain's flexibility and growing ecosystem, we also address its limitations and alternatives like Haystack, LlamaIndex, and Semantic Kernel. Whether you're a developer looking to build AI applications or simply interested in how modern AI systems work, this episode provides a comprehensive introduction to one of the most important frameworks in today's AI development landscape. Find more information at https://www.ibm.com/think/topics/langchain Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores LangGraph, an open-source framework that extends LangChain to enable stateful, cyclic workflows for large language model applications. Built by the team behind LangChain, LangGraph provides developers with the tools to create AI agents capable of complex reasoning and multi-step processes that can adapt based on intermediate results. We break down the key components of LangGraph—nodes, edges, state management, conditional logic, and cycle detection—explaining how they work together to enable more human-like problem-solving approaches. The discussion highlights practical applications including the ReAct pattern for combining reasoning with action-taking, multi-agent systems where specialized AI agents collaborate, iterative refinement workflows for creative tasks, and tree-of-thought reasoning for complex problem solving. While acknowledging the challenges of designing and debugging graph-based workflows, the episode emphasizes how LangGraph's ability to maintain state throughout complex processes opens up new possibilities for sophisticated AI applications that can plan, backtrack, and adapt to changing conditions. Find more information at https://www.ibm.com/think/topics/langgraph Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores Langflow, an innovative open-source visual programming tool that makes building AI applications with large language models more accessible and intuitive. Unlike traditional coding approaches, Langflow provides a drag-and-drop interface for designing LangChain workflows, allowing both developers and non-technical users to create sophisticated AI applications. We examine Langflow's key components—its comprehensive component library, interactive visual canvas, real-time testing capabilities, Python code export functionality, and built-in debugging tools. The discussion highlights how Langflow democratizes AI development through its visual approach, enabling rapid prototyping, educational opportunities, cross-functional collaboration, and easy experimentation with AI concepts. While acknowledging limitations for extremely complex applications and the continued importance of understanding fundamental concepts, the episode emphasizes Langflow's value in lowering barriers to entry for AI application development and bridging the gap between technical and business teams. Find more information at https://www.ibm.com/think/topics/langflow Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores MetaGPT, an innovative open-source framework that orchestrates multiple AI agents to function as a virtual software development team. Created by DeepWisdom AI, MetaGPT transforms simple requirements into working applications by simulating specialized roles like product managers, architects, programmers, and testers—each played by large language models configured for specific tasks. We examine how MetaGPT's Standard Operating Procedures guide these agents through the entire software development lifecycle, from requirement analysis and system design to implementation and testing. The discussion highlights the framework's structured approach to collaborative AI, including its multi-agent system, communication protocols, and execution environment. While acknowledging current limitations in handling complex systems and the continued need for human oversight, the episode emphasizes MetaGPT's significance in advancing AI-powered software development and providing a glimpse into how autonomous agent systems might transform creative and technical workflows in the future. Find more information at https://www.ibm.com/think/topics/metagpt Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Amanda Downie

This episode of Techsplainers explores AutoGen, Microsoft Research's innovative open-source framework that enables multiple AI agents to collaborate through conversation. Unlike traditional single-agent systems, AutoGen creates teams of specialized AI assistants that can communicate with each other to tackle complex problems. We examine how AutoGen configures diverse agents with different roles and expertise, establishes a structured dialogue system between them, and integrates external tools and APIs to expand their capabilities. The discussion highlights practical applications across software development, data analysis, education, and content creation, where agent collaboration produces more comprehensive solutions than individual AI systems could achieve alone. While emphasizing AutoGen's unique approach to multi-agent conversation and autonomous collaboration, we also address the framework's current limitations and the continued importance of human oversight in maximizing its effectiveness. Find more information at https://www.ibm.com/think/topics/autogen Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers explores AgentGPT, an open-source framework that democratizes the creation of autonomous AI agents. We examine how this technology allows users without coding expertise to create goal-oriented agents that can break down complex tasks into manageable steps and execute them using various tools. The discussion covers the key components of AgentGPT's architecture, including its language model foundation, memory system, tool integration layer, and execution engine. We highlight practical applications across research, content creation, process automation, and personal assistance, while acknowledging limitations related to model accuracy, tool integration, and security considerations. The episode also explores how AgentGPT relates to the communication protocols discussed in previous episodes, showing how these technologies work together to create more capable AI systems. As the field evolves, we can expect improvements in customization, reasoning capabilities, multi-agent collaboration, and safety mechanisms. Find more information at https://www.ibm.com/think/topics/agentgpt Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers explores BabyAGI, an open-source framework that demonstrates how autonomous AI agents can create, prioritize, and execute tasks to achieve specific goals. Developed by Yohei Nakajima in 2023, BabyAGI showcases a simplified approach to building self-directing AI systems using large language models. We break down the four-step loop that powers BabyAGI: task creation, where the system generates new tasks based on objectives and previous results; task prioritization, which determines the most efficient execution order; task execution, leveraging language models to complete each task; and result storage, using vector databases to maintain context across tasks. The discussion examines how this recursive approach enables continuous refinement toward objectives and highlights BabyAGI's place within the growing ecosystem of autonomous agent frameworks, including variations like AgentGPT, BabyBeeAGI, and TaskWeaver. While acknowledging current limitations such as loop tendencies and the need for human oversight, the episode emphasizes BabyAGI's significance as an important step toward more autonomous AI systems capable of handling complex, open-ended tasks. Find more information at https://www.ibm.com/think/topics/babyagi Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers explores ChatDev, a groundbreaking research framework that simulates a collaborative software development team composed entirely of large language model agents. Developed by researchers at Tsinghua University and the University of Hong Kong, ChatDev assigns specialized roles like product manager, architect, programmer, and tester to different AI agents, enabling them to work together through structured conversations to build complete software applications. We examine how ChatDev implements a waterfall methodology that progresses through requirement analysis, design, coding, testing, and documentation phases, with different agents taking the lead at each stage. The discussion highlights how this multi-agent approach allows for more complex reasoning, specialized expertise, and human-like collaboration compared to single-agent systems. While acknowledging current limitations in handling large-scale projects and specialized domains, the episode emphasizes ChatDev's significance as an innovative exploration of how AI might transform software development through simulated teamwork and specialization. Find more information at https://www.ibm.com/think/topics/chatdev Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers explores AutoGPT, a groundbreaking autonomous AI agent that represents a significant evolution beyond traditional chatbots. Unlike conventional AI assistants that respond to one prompt at a time, AutoGPT can independently work toward complex goals through a series of self-determined steps. We examine how this experimental open-source application leverages GPT-4's capabilities to break down objectives into manageable tasks, make decisions, evaluate its own performance, and adjust its approach accordingly. The discussion covers AutoGPT's key components—goal setting, memory systems, reasoning engines, tool integration, and feedback loops—that enable it to function with minimal human supervision. While highlighting exciting applications in content creation, software development, and business analysis, we also address important limitations, including reasoning loops, hallucinations, and the need for careful goal setting. This emerging technology offers a glimpse into the future of AI systems that can operate with greater independence and tackle increasingly complex tasks. Find more information at https://www.ibm.com/think/topics/autogpt Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers explores artificial superintelligence (ASI), a hypothetical AI system with intellectual capabilities that far exceed human intelligence. We examine how ASI differs from today's narrow AI systems and even from artificial general intelligence (AGI), positioning it as the ultimate frontier in AI development. The discussion covers the technological building blocks that would be necessary to create ASI, including advanced large language models, multisensory AI, complex neural networks, and neuromorphic computing. We explore both the awe-inspiring potential benefits of ASI—from solving complex medical problems to enabling interstellar travel—and the profound risks it might pose, including control issues, economic disruption, and alignment challenges. The episode concludes by examining today's AI applications as precursors that hint at what true superintelligence might one day achieve, while emphasizing the vast gap between current technology and true ASI. Visit the IBM Guide to AI: https://www.ibm.com/think/topics/ai-guideFind more information at https://www.ibm.com/think/topics/artificial-superintelligence Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Teaggane Finn Episode 180: What is artificial superintelligence?

This episode of Techsplainers explores artificial general intelligence (AGI), the hypothetical AI that can match or exceed human cognitive abilities across any task. We explain how AGI differs from today's narrow AI systems and clarify the distinctions between AGI, strong AI (which focuses on consciousness), and artificial superintelligence (which exceeds human capabilities). The discussion covers various frameworks for defining AGI, from the Turing Test to Gary Marcus's benchmark tasks, and examines the ongoing debate about whether today's large language models qualify as AGI. We also explore different technological approaches to achieving AGI and expert predictions about when this milestone might be reached. Throughout the episode, we highlight how AGI remains both a technological challenge and a philosophical question about the nature of intelligence itself. Visit the IBM Guide to AI: https://www.ibm.com/think/topics/ai-guideFind more information at https://www.ibm.com/think/topics/artificial-general-intelligence Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Teaggane FinnEpisode 179: What is artificial general intelligence (AGI)?

This episode of Techsplainers explores the concept of strong artificial intelligence (strong AI), also known as artificial general intelligence (AGI). Host Teaganne Finn explains that unlike today's specialized AI systems that excel at specific tasks, strong AI would possess human-like intelligence, self-awareness, and the ability to solve unlimited problems across domains. The episode examines how we might test for strong AI, from Alan Turing's famous ""Imitation Game"" to John Searle's Chinese Room Argument, which challenges whether simulation of understanding equals true comprehension. Listeners learn the key differences between today's weak/narrow AI systems and theoretical strong AI, along with current trends in cybersecurity, content creation, and prediction that represent steps toward more advanced AI. While true strong AI remains hypothetical, deep learning applications in self-driving cars, speech recognition, and even code generation demonstrate remarkable progress in specialized AI capabilities. Visit the IBM Guide to AI: https://www.ibm.com/think/topics/ai-guideFind more information at https://www.ibm.com/think/topics/strong-ai Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Teaggane Finn Episode 178: What is strong AI?

This episode of Techsplainers examines the benefits, challenges, and ethical considerations of artificial intelligence. Host Teaganne Finn explores how AI automates repetitive tasks, enhances decision-making, and reduces errors, while also addressing significant risks related to data security, model manipulation, and algorithmic bias. The episode delves into the critical importance of AI ethics and governance, highlighting key values including explainability, fairness, robustness, accountability, and privacy compliance. Listeners learn about the distinction between current ""weak AI"" systems designed for specific tasks and theoretical "strong AI" or artificial general intelligence that would match human capabilities across domains. As AI continues to transform industries and daily life, understanding these dimensions helps organizations implement responsible AI and enables individuals to make informed decisions about AI-powered tools. Visit the IBM Guide to AI: https://www.ibm.com/think/topics/ai-guideFind more information at https://www.ibm.com/think/topics/artificial-intelligence Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Teaggane Finn Episode 177: Part 2: What is artificial intelligence

This episode of Techsplainers introduces the concept of artificial intelligence (AI), tracing its evolution from Alan Turing's 1950 question ""Can machines think?"" to today's sophisticated systems. Host Teaganne Finn breaks down how AI works through machine learning, deep learning, and generative AI, explaining the difference between supervised learning with labeled data and more advanced approaches that learn from unstructured information. The episode explores how modern generative AI systems operate in three phases—training foundation models, tuning for specific applications, and continuous improvement—while also introducing autonomous AI agents that can design their own workflows. Finally, listeners discover real-world AI applications across industries, from customer service chatbots and fraud detection to personalized marketing and predictive maintenance. Find more information at https://www.ibm.com/think/topics/artificial-intelligence Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Teaggane Finn

This episode of Techsplainers explores the Model Context Protocol (MCP), a standard introduced by Anthropic that enables AI models to interact with external tools, data, and functions. Building on our earlier discussions of agent-to-agent communication protocols, we examine how MCP serves a complementary purpose by connecting individual models to resources outside their training data. The discussion covers MCP's four key capabilities: tool calling, file access, resource access, and prompt templates, along with its JSON-RPC implementation. We highlight MCP's strong security features, including sandboxing, permission management, and auditability, which create a controlled environment for model-tool interactions. The episode explains how MCP works alongside agent communication protocols like A2A, creating a layered approach where AI systems can leverage both individual capabilities and collaborative potential. As this standard continues to evolve, we can expect more specialized tool libraries and deeper integration with multi-agent frameworks. Find more information at https://www.ibm.com/think/topics/model-context-protocol Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers explores the Agent-to-Agent (A2A) Protocol and its significant merger with the previously discussed Agent Communication Protocol (ACP) under the Linux Foundation umbrella. We examine how A2A was initially developed by Google to standardize communication between AI agents, enabling them to exchange information and coordinate tasks across different frameworks and platforms. The discussion highlights key principles of A2A including its simplicity, language model optimization, extensibility, and standardization features. We explain the strategic rationale behind the ACP-A2A merger, which combines ACP's REST-based simplicity with A2A's language model focus to create a unified industry standard. The episode also covers practical implications for developers, including migration paths from ACP to A2A, and concludes by exploring the future evolution of the protocol, which will likely include enhanced security models, scalability improvements, and specialized extensions for different industries and use cases. Find more information at https://www.ibm.com/think/topics/agent2agent-protocol Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker

This episode of Techsplainers introduces the Agent Communication Protocol (ACP), an open standard originally developed by IBM's BeeAI that enables AI agents to communicate across different frameworks and organizations. We explain why agent interoperability is a critical challenge in today's AI landscape and how ACP addresses it with four key features: REST-based communication, SDK-optional design, offline discovery capabilities, and async-first approach. Through a real-world example of manufacturing and logistics companies, we demonstrate how ACP eliminates the need for costly custom integrations between agent systems. This standardized protocol represents a fundamental shift from siloed agent systems to interconnected networks of AI collaborators that can discover, understand, and work together regardless of who built them or what technology stack they run on. We also briefly mention that ACP has recently merged with A2A under the Linux Foundation umbrella, with the core concepts remaining relevant during this transition. Find more information at https://www.ibm.com/think/topics/agent-communication-protocol Find more episodes https://www.ibm.biz/techsplainers-podcast Narrated by Cole Stryker