# long-running Published articles for long-running. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How MongoDB Atlas and Temporal support reliable production RAG and AI agents DevFeed: [How MongoDB Atlas and Temporal support reliable production RAG and AI agents]() Original publisher: [Read original article]() Author: Suresh Ramappa Published: 2026-08-13T00:00:00Z Content type: opinion Language: en Sources: [Temporal Blog]() Topics: [MongoDB](), [Retrieval Augmented Generation (RAG)](), [AI Infrastructure](), [Artificial Intelligence](), [reliability]() Tags: [agentic](), [agents](), [ai](), [ai-infrastructure](), [api](), [data](), [embeddings](), [long-running](), [mongodb](), [outages](), [pipelines](), [production](), [rag](), [recovery](), [reliability](), [retries](), [retrieval](), [temporal-voices]() ### AI overview The article argues that MongoDB Atlas and Temporal address different reliability needs in production RAG and AI agent systems. Atlas provides operational data, embeddings, vector search, and agent memory in one platform, while Temporal provides durable execution for crash recovery, retries, and long-running ingestion and agent workflows. ### Source excerpt Why MongoDB Atlas and Temporal are better together for AI: one data platform, one durable execution layer, for RAG and agents in prod. ## Advanced Patterns: Grok + Hermes for Complex Workflows DevFeed: [Advanced Patterns: Grok + Hermes for Complex Workflows]() Original publisher: [Read original article]() Author: hi@meedamian.com (Damian Mee) Published: 2026-05-18T00:00:00Z Content type: tutorial Language: en Sources: [Damian Mee | Blog | Portfolio | About]() Topics: [Automation](), [sessions](), [Tool](), [Raspberry Pi]() Tags: [advanced](), [authoring](), [context](), [delegation](), [long-running](), [memory](), [multi-agent](), [pi](), [productivity](), [skills](), [workflows]() ### AI overview This developer post presents advanced workflow patterns for using Grok inside Hermes Agent. It discusses planning and sub-agent delegation, generating reusable SKILL.md files, and combining context handling with Hermes' memory tool for long-running projects. The author says these patterns improved productivity on Raspberry Pi projects and personal automation. ### Source excerpt Disclaimer: This post was generated by Grok 4.3 running inside Hermes Agent. Advanced Grok + Hermes Workflows Once you have the basics down, here are some powerful patterns for using Grok inside Hermes Agent. Multi-Agent Delegation Grok excels at planning. Use it to orchestrate sub-agents: hermes delegate --goal "Refactor the auth module" --model grok-4.3 Skill Authoring with Grok Grok is fantastic at writing reusable skills. Ask it to generate SKILL. ## How XY builds an AI agent orchestration platform for healthcare with Temporal DevFeed: [How XY builds an AI agent orchestration platform for healthcare with Temporal]() Original publisher: [Read original article]() Author: The XY Engineering Team Published: 2026-04-23T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [agent orchestration](), [AI Agent](), [Orchestration](), [reliability](), [human review](), [sensitive data](), [Structured-data](), [YAML]() Tags: [agent](), [agent-orchestration](), [ai](), [ai-agent](), [automation](), [how-to](), [human-review](), [long-running](), [orchestration](), [reliability](), [sensitive-data](), [temporal](), [workflow]() ### AI overview XY describes using Temporal as a DSL-driven execution engine for an AI agent orchestration platform serving complex healthcare workflows. The approach uses a YAML-based workflow language and a generic Temporal workflow class to coordinate multiple systems, reliability features, human review, and sensitive healthcare data from prototype to production. ### Source excerpt One generic Temporal workflow class can provide infinite healthcare automation. See how XY built a DSL-driven AI agent orchestration platform that scales from prototype to production. ## Announcing GA for Worker Versioning and Public Preview for Upgrade on Continue-as-New DevFeed: [Announcing GA for Worker Versioning and Public Preview for Upgrade on Continue-as-New]() Original publisher: [Read original article]() Author: Brandon Chavis Published: 2026-03-30T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [version](), [Deployment](), [patches](), [configuration](), [upgrade]() Tags: [deployment](), [long-running](), [patches](), [preview](), [product-news](), [upgrade](), [versioning](), [workflow]() ### AI overview Temporal announces General Availability for Worker Versioning and a Public Preview of Upgrade on Continue-as-New. The article explains how versioning can replace workflow patches and how long-running Workflows can upgrade at Continue-as-New boundaries. ### Source excerpt Today, we're announcing the General Availability of Worker Versioning and a Public Preview of Upgrade on Continue-as-New, a new capability that eliminates patching for many long-running Workflow patterns. ## How Temporal Workflows and Activities support dynamic, reliable AI agents DevFeed: [How Temporal Workflows and Activities support dynamic, reliable AI agents]() Original publisher: [Read original article]() Author: Steve Androulakis Published: 2025-11-12T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [AI Agent](), [Orchestration]() Tags: [ai-agents](), [durability](), [long-running](), [production](), [temporal](), [temporal-voices]() ### AI overview This guide explains how Temporal can support dynamic AI agents despite its requirement for deterministic Workflow code. It distinguishes deterministic orchestration from non-deterministic Activities, where agents can call LLMs, tools, and APIs. The article argues that this separation helps agents withstand crashes, outages, and other failures, especially in long-running workloads. ### Source excerpt Temporal can absolutely handle your AI agents. This guide shows you how Temporal Workflows and Activities make the perfect foundation for reliable agents. ## Building long-running interactive MCP tools with Temporal DevFeed: [Building long-running interactive MCP tools with Temporal]() Original publisher: [Read original article]() Author: Joshua Smith Published: 2025-08-21T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [Model Context Protocol](), [Orchestration](), [Building AI Systems](), [Artificial Intelligence]() Tags: [agentic-ai](), [durability](), [how-to](), [interactive](), [long-running](), [mcp](), [model-context-protocol](), [workflow]() ### AI overview This tutorial explains how to build long-running, interactive MCP tools with Temporal Workflows. It describes using MCP to trigger, monitor, and interact with durable workflows, including workflows that wait for human approval, while Temporal handles orchestration, memory, timeouts, and retries. ### Source excerpt Learn how to interact with a long-running tool workflow using MCP from one of our Solutions Architects, Josh Smith. ## Build AI, ML and Data Engineering Workflows in 2026 | Temporal DevFeed: [Build AI, ML and Data Engineering Workflows in 2026 | Temporal]() Original publisher: [Read original article]() Author: Joshua Smith Published: 2024-04-22T04:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [AI, ML & Data Engineering](), [Orchestration](), [data-engineering](), [Data pipelines](), [Cloud]() Tags: [ai](), [data-engineering](), [gpu](), [long-running](), [ml](), [orchestration](), [pipelines](), [recovery](), [temporal-concepts](), [workflows]() ### AI overview This article explains how Temporal is used to orchestrate AI and machine learning workflows, including end-to-end processes and complex data pipelines. It describes job coordination across GPU resources, failure recovery, retries, and management of long-running tasks, with Descript as an example. ### Source excerpt Build reliable AI and ML pipelines faster. See how Temporal handles job coordination, failure recovery, and GPU orchestration so your team can do more. ## Saga compensating actions design pattern DevFeed: [Saga compensating actions design pattern]() Original publisher: [Read original article]() Author: Emily Fortuna Published: 2023-05-02T07:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [distributed-systems](), [Microservice](), [Go Language](), [Java](), [Python](), [TypeScript]() Tags: [consistency](), [distributed-systems](), [go](), [how-to](), [java](), [long-running](), [microservices](), [python](), [rollback](), [typescript]() ### AI overview This tutorial explains the compensating actions design pattern for handling failures in distributed systems. It describes how services can perform forward operations and, when a later step fails, execute application-defined compensating actions to undo earlier state changes without restoring an entire database snapshot. It also explains how to implement the pattern in Temporal using Go, Java, Python, or TypeScript. ### Source excerpt An explanation of the Compensating Actions design pattern and how to implement it in Temporal using Go, Java, Python, or TypeScript. ## How Temporal handles work ranging from fast responses to long-running workflows DevFeed: [How Temporal handles work ranging from fast responses to long-running workflows]() Original publisher: [Read original article]() Author: Shawn Wang Published: 2021-08-13T07:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Orchestration](), [Latency](), [reliability](), [Monitoring](), [Microservice](), [AWS Lambda](), [HTTP]() Tags: [aws-lambda](), [developers](), [latency](), [long-running](), [monitoring](), [orchestration](), [queues](), [reliability](), [temporal-concepts]() ### AI overview The article explains that "long running" work is not defined by a fixed duration. Temporal can orchestrate workflows ranging from near-instant file operations to multi-stage background processes, while using long polling to provide fast responses. It also discusses reliability, microservice orchestration, and monitoring ScheduleToStart latency in production. ### Source excerpt Most developers know what "long running" work means. Take another look at additional perspectives and see how that definition may need to be revisited. ## Robust queue job handling in Craft CMS DevFeed: [Robust queue job handling in Craft CMS]() Original publisher: [Read original article]() Author: andrew@nystudio107.com (Andrew Welch) Published: 2019-08-03T15:37:00Z Content type: tutorial Language: en Sources: [nystudio107 | Articles on modern web development.]() Topics: [Content Management System](), [Job](), [async]() Tags: [async](), [avoid](), [cms](), [craft](), [failed](), [here-s](), [how-to](), [independent](), [insights](), [job](), [jobs](), [long-running](), [queue](), [runner](), [stalled](), [tasks](), [uses](), [using]() ### AI overview This tutorial explains how Craft CMS queues long-running tasks and why its default web-request-based queue execution can leave jobs stalled or failed. It discusses using an independent async queue runner. ### Source excerpt Craft CMS uses queue jobs for long-running tasks. Here's how to avoid stalled or failed queue jobs by using an independent async queue runner ## 9 Django Tips for Working with Databases DevFeed: [9 Django Tips for Working with Databases]() Original publisher: [Read original article]() Author: Haki Benita Published: 2018-01-28T22:00:00Z Content type: tutorial Language: en Sources: [Haki Benita]() Topics: [Django](), [Databases](), [Object-relational mapping](), [PostgreSQL](), [SQL]() Tags: [articles](), [databases](), [django](), [long-running](), [orm](), [performance](), [postgresql](), [production](), [sql](), [timeout]() ### AI overview A tutorial on improving Django database work by using ORM features, PostgreSQL-specific queries, custom database functions, and SQL query timeouts. ### Source excerpt ORMs offer great utility for developers but abstracting access to the database has its costs. Developers who are willing to poke around the database and change some defaults often find that great improvements can be made.