Everyone is building AI agents.

OpenAI SDKs, Claude Code, Deep Agent systems, custom workflows, and orchestration frameworks all promise more autonomous AI. But as these systems become more capable, they start running into familiar engineering problems:

• retries
• state management
• orchestration
• context control
• durable execution

This week we're joined by Hamza Tahir, CTO and co-founder of ZenML and creator of Kitaru, to discuss what happens when agents stop being simple chat interfaces and start behaving like long-running distributed systems.

We explore:

• what an agent harness actually is
• durable execution and why it matters
• orchestration vs business logic
• state management for long-running agents
• retries, checkpoints, and human-in-the-loop workflows
• context management and token costs
• open vs closed agent frameworks
• why everyone seems to be rebuilding the same layer of infrastructure

One of the biggest questions we kept coming back to:

What is a meta harness?

If you have an answer, let us know in the comments.

Kitaru
https://github.com/zenml-io/kitaru

ZenML
https://www.zenml.io

Hamza Tahir
https://www.linkedin.com/in/hamzatahir/

Pedro Agentware
https://github.com/Soypete/pedro-agentware

OpenAI Agents SDK
https://platform.openai.com/docs/guides/agents

Temporal
https://temporal.io

DBOS
https://www.dbos.dev

Apache Airflow
https://airflow.apache.org

Prefect
https://www.prefect.io

Domesticating AI is a bi-weekly podcast about practical AI for developers.

We help you brace the feral open-source AI landscape — so you can tame it instead of getting dragged by it.

Subscribe on YouTube, follow on Spotify or Apple Podcasts, and support the show on Patreon.

Keep your AI on a leash.

Links