# Building Durable AI Agents

Page: https://stenobird.com/podcast/practical-ai/building-durable-ai-agents
Text version: https://stenobird.com/podcast/practical-ai/building-durable-ai-agents.md
Podcast: [Practical AI](https://stenobird.com/podcast/practical-ai)
Published: 2026-07-09T09:00:00+00:00
Episode link: https://share.transistor.fm/s/facb92e2
Audio file: https://pscrb.fm/rss/p/dts.podtrac.com/redirect.mp3/media.transistor.fm/facb92e2/33d1bc96.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/practical-ai/episodes/building-durable-ai-agents
Duration seconds: 2799

## Resource

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.

## Highlights
- 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

## Topics

AI Agents, MLOps, Agentic Workflows, Infrastructure, State Management, ZenML, LLM Orchestration, Software Engineering

## Chapters
- 1:00 — Introduction to Kitaru: An introduction to Hamza Tahir and ZenML's new project, Kitaru, which focuses on making AI agents durable.
- 4:00 — The Evolution of MLOps to AgentOps: Discussing how the principles of DevOps and MLOps are being reinvented to support agentic workflows and software engineering standards.
- 8:00 — New Workload Challenges: Exploring the complexities of state management, retries, and replays in modern AI workloads.
- 11:00 — Scaling Multi-Agent Architectures: The rise of agent fleets and swarms, and the infrastructure challenges that emerge at scale.
- 15:00 — The History of AI Evaluation: Reflecting on the rapid evolution of evaluation methods from manual Python scripts to automated systems.
- 18:00 — Decoupling Logic from Models: Why business value and infrastructure should remain independent of specific LLM providers to ensure business continuity.
- 22:00 — Architecting for Durability: Understanding the different types of agent workloads and how to build resilient, non-fragile agent harnesses.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/practical-ai/episodes/building-durable-ai-agents/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/practical-ai/building-durable-ai-agents.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.