Write Reliable Software with Temporal

Why It Matters

Temporal’s durable execution lets teams deliver reliable, fault‑tolerant software without writing custom resilience code, dramatically lowering operational risk and development cost in cloud environments.

Key Takeaways

• Temporal provides crash‑proof, long‑running workflows without extra code.
• Deterministic workflow execution ensures repeatable results across failures.
• Activities handle I/O while Temporal persists results for durability.
• Continue‑as‑new creates incremental checkpoints, enabling infinite‑duration agents to run.
• Open‑source MIT license lets you run Temporal on any database.

Summary

The video introduces Temporal’s durable execution model as a way to boost developer productivity when building agentic systems. It explains how Temporal abstracts reliability concerns, allowing developers to write ordinary code that runs to completion despite cloud‑scale failures, flaky services, or regional outages. Key insights include the deterministic nature of workflow code, which guarantees identical outcomes when re‑executed with the same inputs, and the separation of concerns between workflows and activities. Activities perform I/O and external calls, while Temporal’s server persistently records results, enabling automatic retries, failover across data‑center regions, and “continue‑as‑new” checkpoints for long‑running agents. The speaker contrasts traditional ad‑hoc reliability tricks—manual scripts, event‑driven queues, and coarse checkpointing—with Temporal’s approach. Real‑world examples such as debit‑credit transaction handling and the acquisition of Crystal DBA illustrate how Temporal brings database‑style transactional guarantees to any programming language, eliminating the need for custom retry logic or proprietary stored procedures. For developers and enterprises, this means building distributed, cloud‑native applications that are inherently crash‑proof, scalable, and language‑agnostic, reducing operational overhead and accelerating time‑to‑market for complex, long‑lived services.

Original Description

Johann Schleier-Smith is the Technical Lead for AI at Temporal Technologies, working on reliable infrastructure for production AI systems and long-running agent workflows.

Durable Execution and Modern Distributed Systems, Johann Schleier-Smith // MLOps Podcast #364

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps Merch: https://shop.mlops.community/

Big shoutout to ⁨@Temporalio for the support, and to @trychroma for hosting us in their recording studio

// Abstract

A new paradigm is emerging for building applications that process large volumes of data, run for long periods of time, and interact with their environment. It’s called Durable Execution and is replacing traditional data pipelines with a more flexible approach.

Durable Execution makes regular code reliable and scalable.

In the past, reliability and scalability have come from restricted programming models, like SQL or MapReduce, but with Durable Execution this is no longer the case. We can now see data pipelines that include document processing workflows, deep research with LLMs, and other complex and LLM-driven agentic patterns expressed at scale with regular Python programs.

In this session, we describe Durable Execution and explain how it fits in with agents and LLMs to enable a new class of machine learning applications.

#podcast #temporal #aiagents #reliabilityengineering

// Related Links

https://t.mp/hello?utm_source=podcast&utm_medium=sponsorship&utm_campaign=podcast-2026-03-13-mlops&utm_content=mlops-johann

https://t.mp/vibe?utm_source=podcast&utm_medium=sponsorship&utm_campaign=podcast-2026-03-13-mlops&utm_content=mlops-johann

https://t.mp/career?utm_source=podcast&utm_medium=sponsorship&utm_campaign=podcast-2026-03-13-mlops&utm_content=mlops-johann

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Johann on LinkedIn: /jssmith/

Timestamps:

[00:00] Developer Productivity Patterns

[00:42] Durable execution

[11:50] Checkpointing vs Durable Execution

[19:37] Workflow Orchestrator Market Map

[29:04] Serverless Workflow Orchestration

[35:02] Temporal Setup Guide

[40:27] Memory in Agents

[53:11] System Architecture Breakdown

[1:00:03] Wrap up