{"podcast":{"title":"Practical AI","slug":"practical-ai","podcast_index_feed_id":444526,"rss_url":"https://feeds.transistor.fm/practical-ai-machine-learning-data-science-llm","website_url":"https://practicalai.show/","image_url":"https://img.transistorcdn.com/WMlp2ug34XB6LDJ3-vnzti_-_y144LUlFW0Xzzn3fss/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8wMTZi/ZWJmNWIwNDdmYTcw/NGJjMTExZjNjZmYy/M2ZjNS5wbmc.jpg","author":"Daniel Whitenack and Chris Benson","episode_count":368,"summary":"Making artificial intelligence practical, productive & accessible to everyone. Practical AI is a show in which technology professionals, business people, students, enthusiasts, and expert guests engage in lively discussions about Artificial Intelligence and related topics (Machine Learning, Deep Learning, Neural Networks, GANs, MLOps, AIOps, LLMs & more). The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the latest advances in AI, while keeping one foot in the real world, then this is the show for you!","last_synced_at":"2026-08-02T15:06:44.156849+00:00","page_url":"https://stenobird.com/podcast/practical-ai"},"episode":{"title":"Building Durable AI Agents","slug":"building-durable-ai-agents","published_at":"2026-07-09T09:00:00+00:00","page_url":"https://stenobird.com/podcast/practical-ai/building-durable-ai-agents","show_page_url":"https://stenobird.com/podcast/practical-ai","url":"https://share.transistor.fm/s/facb92e2","audio_url":"https://pscrb.fm/rss/p/dts.podtrac.com/redirect.mp3/media.transistor.fm/facb92e2/33d1bc96.mp3","summary":"Moving AI agents from experimental demos to production requires applying MLOps principles to handle long-running, complex workflows. This episode explores the infrastructure needed for durability, state management, and scalable agent fleets.","meta_description":"Learn how to build durable, production-ready AI agents using MLOps principles, state management, and scalable agent harnesses.","key_points":["Main idea: Agentic workflows require a shift from simple request-response patterns to durable, long-running execution environments","Practical takeaway: Enterprises should invest in internal agent platforms to manage complex business processes and maintain control over infrastructure","Failure mode: Relying solely on model-specific features creates vendor lock-in and fragility when model availability or regulations change","Technical necessity: Robust systems must implement state management, retries, and observability to handle inevitable failures in multi-step agent loops","Future trend: As LLM performance commoditizes, the competitive advantage will shift toward the quality of the underlying agent harness and runtime"],"chapters":[{"start_ms":60000,"title":"Introduction to Kitaru","summary":"An introduction to Hamza Tahir and ZenML's new project, Kitaru, which focuses on making AI agents durable."},{"start_ms":240000,"title":"The Evolution of MLOps to AgentOps","summary":"Discussing how the principles of DevOps and MLOps are being reinvented to support agentic workflows and software engineering standards."},{"start_ms":480000,"title":"New Workload Challenges","summary":"Exploring the complexities of state management, retries, and replays in modern AI workloads."},{"start_ms":660000,"title":"Scaling Multi-Agent Architectures","summary":"The rise of agent fleets and swarms, and the infrastructure challenges that emerge at scale."},{"start_ms":900000,"title":"The History of AI Evaluation","summary":"Reflecting on the rapid evolution of evaluation methods from manual Python scripts to automated systems."},{"start_ms":1080000,"title":"Decoupling Logic from Models","summary":"Why business value and infrastructure should remain independent of specific LLM providers to ensure business continuity."},{"start_ms":1320000,"title":"Architecting for Durability","summary":"Understanding the different types of agent workloads and how to build resilient, non-fragile agent harnesses."}],"topics":["AI Agents","MLOps","Agentic Workflows","Infrastructure","State Management","ZenML","LLM Orchestration","Software Engineering"],"duration_seconds":2799,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/practical-ai/episodes/building-durable-ai-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/practical-ai/building-durable-ai-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}