# Temporal Voices Published articles for Temporal Voices. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## AI safety does not stop at the model DevFeed: [AI safety does not stop at the model]() Original publisher: [Read original article]() Author: Samar Abbas Published: 2026-09-15T00:00:00Z Content type: opinion Language: en Sources: [Temporal Blog]() Topics: [ai safety](), [Agent Harness](), [reliability](), [retry](), [Security]() Tags: [agent](), [agent-harness](), [ai](), [reliability](), [retry](), [safety](), [security](), [temporal-voices]() ### AI overview The article argues that AI safety extends beyond model behavior to the application layer, where companies must control agent authority and enforce approvals, policies, and credential limits. It emphasizes that these controls must remain reliable through crashes, timeouts, and retries, and presents Temporal Agent Harness as an execution-layer control point around an agent SDK. ### Source excerpt Auditing what an agent did is only half the job. Companies also have to control what agents may do, and make those limits hold when systems fail. ## A letter from Samar: a year of achievements, and what's next for us DevFeed: [A letter from Samar: a year of achievements, and what's next for us]() Original publisher: [Read original article]() Author: Samar Abbas Published: 2026-09-14T00:00:00Z Content type: opinion Language: en Sources: [Temporal Blog]() Topics: [reliability](), [Artificial Intelligence](), [OpenAI]() Tags: [agents](), [ai-agents](), [growth](), [openai](), [reliability](), [temporal](), [temporal-voices]() ### AI overview Temporal CEO Samar Abbas reviews a year of company growth, leadership changes, the Series E raise, platform usage, and customer examples. He argues that reliable infrastructure and Durable Execution remain important as AI increases application complexity and expectations. ### Source excerpt Temporal CEO Samar Abbas on a year of record growth, the Series E raise, and why Durable Execution is now core infrastructure for reliable AI agents. ## Automated Worker Versioning with GitHub Actions DevFeed: [Automated Worker Versioning with GitHub Actions]() Original publisher: [Read original article]() Author: Adam Quan Published: 2026-09-09T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [GitHub Actions](), [CI/CD](), [Deployment](), [Orchestration]() Tags: [automation](), [ci-cd](), [ci-cd-pipeline](), [deployment](), [github-actions](), [how-to](), [temporal-voices]() ### AI overview This tutorial explains how to automate Temporal Worker Versioning in a CI/CD pipeline with GitHub Actions and Worker Controller. It covers deterministic Workflow code changes, deployment versions, traffic ramping, pinned and auto-upgrade Workflows, safer rollouts, and rollbacks. ### Source excerpt Learn how to automate Temporal Worker Versioning in CI/CD with GitHub Actions and Worker Controller for safer rollouts, traffic ramping, and rollbacks. ## From dedicated Workers to Serverless Workers: Migrating Temporal Workflows to AWS Lambda DevFeed: [From dedicated Workers to Serverless Workers: Migrating Temporal Workflows to AWS Lambda]() Original publisher: [Read original article]() Author: Garima Gupta Published: 2026-09-09T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [AWS Lambda](), [Serverless](), [Amazon Web Services](), [Deployment](), [Testing](), [SDKs]() Tags: [aws](), [aws-lambda](), [deployment](), [go](), [java](), [kubernetes](), [net](), [python](), [serverless](), [temporal](), [temporal-voices](), [testing](), [typescript](), [versioning]() ### AI overview This guide explains how to migrate Temporal Workers from long-lived processes on Kubernetes to Temporal Cloud Serverless Workers running on AWS Lambda. It focuses on AWS Lambda with Python examples and covers lifecycle changes, invocation scaling, deployment, versioning, and testing. ### Source excerpt Learn to migrate Temporal Workers from dedicated infrastructure to AWS Lambda with Serverless Workers, with guidance on deployment, versioning, and testing. ## Orchestrating Playwright test suites with Temporal for independent retries DevFeed: [Orchestrating Playwright test suites with Temporal for independent retries]() Original publisher: [Read original article]() Author: Simon Emms Published: 2026-09-03T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Playwright](), [Orchestration](), [ci](), [test]() Tags: [browsers](), [ci](), [orchestration](), [playwright](), [retry](), [temporal-voices](), [tests]() ### AI overview This article explores using Temporal to orchestrate Playwright end-to-end test suites as independent, durable units of work. The approach allows failed tests to retry independently while preserving progress instead of restarting the entire CI job. ### Source excerpt Learn how Temporal can orchestrate end-to-end test suites so failed tests retry independently, preserving progress without restarting the entire CI job. ## Using coding agents on a migration: Three practices that mattered DevFeed: [Using coding agents on a migration: Three practices that mattered]() Original publisher: [Read original article]() Author: Chandler Ortman Published: 2026-09-02T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [migration](), [clickhouse](), [AI-assisted coding](), [coding](), [configuration](), [Deployment](), [Environment Variables]() Tags: [cleanup](), [clickhouse](), [coding-agents](), [deployment](), [environment-variables](), [migration](), [prompt](), [pull-requests](), [temporal-voices]() ### AI overview The article examines coding agents used during a migration of Temporal Cloud usage and billing data to ClickHouse. It finds that the agents were most useful for cleanup and removal work, with durable cleanup instructions and exhaustive searches helping make that work practical. ### Source excerpt Three lessons from using coding agents during a ClickHouse migration, from cleanup automation to writing durable instructions that stay useful over time. ## How LlamaIndex uses Temporal to scale reliable document orchestration DevFeed: [How LlamaIndex uses Temporal to scale reliable document orchestration]() Original publisher: [Read original article]() Author: Adrian Lyjak Published: 2026-09-01T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [llamaindex](), [Orchestration](), [RabbitMQ](), [Concurrency]() Tags: [api](), [concurrency](), [llamaindex](), [orchestration](), [rabbitmq](), [scale](), [temporal](), [temporal-voices]() ### AI overview This article explains how LlamaIndex moved document-processing workloads from RabbitMQ to Temporal. It describes the complexity of processing documents page by page and reports that Temporal helped the team improve durability and concurrency while processing tens of millions of pages per day for the Batch API. ### Source excerpt Learn how LlamaIndex moved from RabbitMQ to Temporal to make LlamaParse more durable, improve concurrency, and process tens of millions of pages per day. ## Practices for Using Coding Agents to Build Stable Temporal Applications DevFeed: [Practices for Using Coding Agents to Build Stable Temporal Applications]() Original publisher: [Read original article]() Author: Mason Egger Published: 2026-08-26T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [agentic-coding](), [AI-assisted coding](), [Claude Code](), [coding](), [unit test]() Tags: [agentic-coding](), [ai](), [claude-code](), [coding](), [coding-agents](), [temporal-voices]() ### AI overview The article explains how to use coding agents to build stable, production-ready Temporal applications. It recommends providing the right context, applying guardrails, and aligning with the agent on what to build, while noting that the approach is not limited to Claude Code. ### Source excerpt The tools and habits I've found that lead to stable, production-ready Temporal applications. ## How Temporal Adds Durability to AWS Agentic AI Workloads DevFeed: [How Temporal Adds Durability to AWS Agentic AI Workloads]() Original publisher: [Read original article]() Author: Rahman Syed Published: 2026-08-20T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Amazon Web Services](), [Artificial Intelligence](), [Agent Framework](), [Amazon Bedrock](), [Strands Agents](), [AWS Lambda]() Tags: [agent-framework](), [agentic](), [ai](), [amazon-bedrock](), [aws](), [aws-lambda](), [cloud](), [iam](), [temporal-voices]() ### AI overview This developer article explains how Temporal adds a durability layer to AWS-based agentic AI systems. It presents a loan-underwriting example and describes using Amazon Bedrock, Strands Agents, and AWS Lambda to build recoverable, scalable workloads. ### Source excerpt AWS gives developers the best-in-class tools for building agentic AI -- models, an agent framework, and compute to run it all on. As those systems grow more complex with more tools, more agents, and longer-running steps that wait on human-intervention, keeping the whole thing consistent and recoverable becomes its own design challenge. This is the layer Temporal adds. ## Using an AI Agent to Convert STL Meshes into Editable CAD DevFeed: [Using an AI Agent to Convert STL Meshes into Editable CAD]() Original publisher: [Read original article]() Author: Shy Ruparel Published: 2026-08-18T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [AI Agent](), [stl](), [3D](), [audit trail](), [retry]() Tags: [3d](), [agent](), [ai-agent](), [audit-trail](), [generate](), [model](), [retry](), [stl](), [temporal-voices]() ### AI overview The article describes using an AI agent to convert triangulated STL meshes into editable CAD and explains why validation mattered more than an autonomous agentic loop. Temporal provided durable execution, retries, progress preservation, and an audit trail, but did not improve the agent's geometric judgment. ### Source excerpt Shy Ruparel tried an AI agent to turn STL files into editable CAD. What worked was less glamorous: generate candidates, measure them, and validate. ## 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. ## Label your agent steps DevFeed: [Label your agent steps]() Original publisher: [Read original article]() Author: Lanie Hei Published: 2026-08-12T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [observability](), [Tooling](), [Large Language Model](), [Code]() Tags: [agent](), [debugging](), [how-to](), [llm](), [observability](), [temporal-voices](), [workflows]() ### AI overview This tutorial explains how to use Temporal's Activity and Workflow summary fields to label agent steps, making complex executions easier to scan, debug, and understand in the Temporal UI. It demonstrates the approach with a coding-agent loop involving planning, editing, testing, evaluation, CI, and recovery. ### Source excerpt Learn how to label Activities, Workflows, and Timers in Temporal to make agent execution easier to scan, debug, and understand in the Temporal UI. ## Running out of runway: Migrating Temporal Cloud's billing store to ClickHouse DevFeed: [Running out of runway: Migrating Temporal Cloud's billing store to ClickHouse]() Original publisher: [Read original article]() Author: Paul Oh Published: 2026-08-11T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [clickhouse](), [Cloud](), [data](), [Databases]() Tags: [clickhouse](), [cloud](), [control-plane](), [cost](), [data](), [database](), [databases](), [parallel](), [results](), [table](), [temporal-voices]() ### AI overview Temporal Cloud migrated its billing store to ClickHouse after its previous warehouse had limited capacity. The migration provided three to five years of projected headroom, reduced steady-state costs by about 70%, and delivered usage data to customers roughly 30 minutes sooner. Temporal validated billing accuracy by running both databases in parallel for six weeks. ### Source excerpt How Temporal Cloud migrated its billing store to ClickHouse, gaining years of headroom, cutting steady-state costs by about 70%, and improving data freshness. ## Durable, flexible multi-agent systems DevFeed: [Durable, flexible multi-agent systems]() Original publisher: [Read original article]() Author: Melanie Warrick Published: 2026-08-06T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [Multi Agent Systems](), [Orchestration](), [systems](), [Langgraph](), [Persistence](), [Google]() Tags: [agents](), [distributed-system](), [google-adk](), [langgraph](), [multi-agent](), [orchestration](), [persistence](), [temporal-voices]() ### AI overview This article describes a multi-agent delivery fleet built with Google ADK and LangGraph, using Temporal for orchestration, persistence, retries, and resumability. It explains how to keep human oversight durable when agents or workers disconnect or when workflows wait for human responses. ### Source excerpt Running a multi-agent delivery fleet on Google ADK and LangGraph, and what it takes to make the human in the loop durable. ## I spent two months screen-sharing to ship one integration. So I rebuilt it on Temporal. DevFeed: [I spent two months screen-sharing to ship one integration. So I rebuilt it on Temporal.]() Original publisher: [Read original article]() Author: Stephen Montague Published: 2026-08-06T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [proxy](), [networking](), [legacy application](), [Messaging](), [on-prem](), [retry](), [Cloud]() Tags: [legacy-application](), [messaging](), [networking](), [on-prem](), [proxy](), [retry](), [software](), [temporal-voices]() ### AI overview The article explains how to connect a cloud application to a firewalled on-premises edge site using an egress-only proxy and a single outbound Temporal connection. It describes the operational difficulties of a legacy, one-way integration and the need for bidirectional messaging, retry handling, and testing. ### Source excerpt How to durably reach a firewalled edge site with no inbound ports: an egress-only proxy that hot-reloads config over a single outbound Temporal connection. ## How HeyGen runs millions of AI workflows on Temporal DevFeed: [How HeyGen runs millions of AI workflows on Temporal]() Original publisher: [Read original article]() Author: Jiajun Zhao Published: 2026-08-06T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Orchestration](), [jobs](), [GPU](), [Cloud]() Tags: [cloud](), [gpu](), [jobs](), [orchestration](), [scale](), [temporal-voices]() ### AI overview HeyGen replaced an internal job-queue system with Temporal to coordinate video-generation workflows across many services, task queues, worker deployments, and a multi-cloud GPU fleet. The article explains the operational problems in the former system and the platform capabilities used to scale workflow execution. ### Source excerpt HeyGen replaced a brittle job-queue system with Temporal, coordinating millions of daily workflow runs across a multi-cloud GPU fleet. ## Ignition: Flashing 2,300 conference badges with Temporal DevFeed: [Ignition: Flashing 2,300 conference badges with Temporal]() Original publisher: [Read original article]() Author: Shy Ruparel Published: 2026-08-04T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [distributed-systems](), [ESP32](), [Embedded Software Dev](), [Hardware](), [Espressif]() Tags: [conference](), [distributed-systems](), [esp32](), [espressif](), [firmware](), [flashing](), [hardware](), [retries](), [temporal-voices](), [workflow]() ### AI overview The article explains how Temporal powered Ignition, a workflow system used to flash firmware onto 2,300 ESP32 conference badges over two days. It describes the operational challenges of coordinating USB hubs, laptops, workers, retries, device tracking, and validation across the assembly process. ### Source excerpt How Temporal powered Ignition, the workflow system that flashed 2,300 conference badges in two days using durable execution and retries. ## The bot that lied to cricket fans with a straight face: Temporal x San Francisco Unicorns DevFeed: [The bot that lied to cricket fans with a straight face: Temporal x San Francisco Unicorns]() Original publisher: [Read original article]() Author: Shubham Londhe Published: 2026-08-04T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Bot](), [trust](), [data]() Tags: [cricket](), [execution](), [gemini](), [temporal-voices](), [trust](), [whatsapp]() ### AI overview A Temporal developer advocate describes building a WhatsApp bot for San Francisco Unicorns cricket fans. Gemini handled conversation while Temporal managed reminders, live-score polling, and durable execution; a live-score failure highlighted the importance of trust and reliable data. ### Source excerpt How a WhatsApp bot for San Francisco Unicorns cricket fans lied about a live score at 3 AM, and what durable execution with Temporal taught us about trust. ## Introducing Deputy: Better signal and control for software supply chains DevFeed: [Introducing Deputy: Better signal and control for software supply chains]() Original publisher: [Read original article]() Author: Kent Gruber Published: 2026-08-03T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [supply-chain-security](), [Application Security](), [Command-line interface](), [Open Source]() Tags: [application-security](), [cli](), [open-source](), [software](), [supply-chain](), [supply-chain-security](), [temporal-voices]() ### AI overview Temporal introduces Deputy, an open-source, CLI-first security toolchain for inventorying, scanning, triaging, and controlling dependencies across repositories, container images, VM disk images, SBOMs, and other targets. It provides a customizable policy layer for local use, CI, and download-time controls. ### Source excerpt Meet Deputy, Temporal's open-source, CLI-first toolchain for inventorying, scanning, triaging, and controlling dependencies across your supply chain. ## Orchestration powered by Temporal at Zscaler: Wrap, don't rewrite DevFeed: [Orchestration powered by Temporal at Zscaler: Wrap, don't rewrite]() Original publisher: [Read original article]() Author: Abhishek Mitra Published: 2026-07-22T00:00:00Z Content type: opinion Language: en Sources: [Temporal Blog]() Topics: [Orchestration](), [Automation](), [Ansible](), [opentofu](), [Terraform](), [argocd](), [GitOps](), [Provisioning]() Tags: [ansible](), [automation](), [aws-cloudformation](), [bash](), [ci](), [cli](), [gitops](), [infrastructure-as-code](), [orchestration](), [provisioning](), [temporal-voices]() ### AI overview The article describes how Zscaler designed a durable orchestration contract above eight heterogeneous automation engines, including Ansible, Terraform, OpenTofu, Helm, ArgoCD, Crossplane, Kubernetes Cluster API, AWS CloudFormation, and Jenkins. The approach aims to coordinate existing tools without rewriting them. ### Source excerpt How one durable contract above eight automation engines changed Zscaler's architecture without changing the engines ## I had two weeks, an 8-foot keyboard, and a Wordle Workflow DevFeed: [I had two weeks, an 8-foot keyboard, and a Wordle Workflow]() Original publisher: [Read original article]() Author: Shy Ruparel Published: 2026-07-21T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Development](), [keyboard](), [Figma]() Tags: [conference](), [figma](), [game](), [keyboard](), [temporal-voices](), [usb]() ### AI overview Temporal describes building and presenting a Wordle clone driven by Temporal Workflows, using an 8-foot USB-C keyboard and holographic fans to demonstrate durable execution at AI Engineer World's Fair. ### Source excerpt A Wordle clone, an 8-foot keyboard, and a holographic fan display made Temporal's Durable Execution visible at AI Engineer World's Fair. ## Why I needed Durable Execution to read a toy manual DevFeed: [Why I needed Durable Execution to read a toy manual]() Original publisher: [Read original article]() Author: Shy Ruparel Published: 2026-07-13T00:00:00Z Content type: opinion Language: en Sources: [Temporal Blog]() Topics: [Artificial Intelligence](), [Software](), [Python]() Tags: [ai](), [cleanup](), [japanese](), [ocr](), [pipeline](), [retries](), [temporal-voices](), [translation]() ### AI overview Shy Ruparel describes building Toku Solutions, an AI pipeline that translates Japanese collectible toy manuals into editable static sites. Durable Execution handles OCR, retries, and cleanup so processing does not have to restart from the beginning. ### Source excerpt Shy Ruparel built an AI pipeline to translate Japanese toy manuals. Durable Execution keeps OCR, retries, and cleanup from starting over. ## Dogfooding the Billable Actions metric: How granular observability improved our metering validation DevFeed: [Dogfooding the Billable Actions metric: How granular observability improved our metering validation]() Original publisher: [Read original article]() Author: Eric Chen Published: 2026-06-25T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [observability](), [dashboards](), [Cloud](), [API](), [Server](), [Time Series](), [benchmarking]() Tags: [account](), [api](), [cloud](), [cost](), [count](), [dashboard](), [dashboards](), [dogfooding](), [metric](), [observability](), [optimization](), [query](), [raw](), [server](), [temporal-voices](), [time-series](), [validation](), [visibility]() ### AI overview Temporal describes how its Billable Actions metric and OpenMetrics per-type breakdowns provide more granular cost visibility. Internally, the company uses the metric with a canary account and validation dashboards to verify metering accuracy, troubleshoot discrepancies, and identify optimization opportunities. ### Source excerpt See how Temporal uses the Billable Actions metric internally to validate metering, troubleshoot discrepancies, and improve cost observability. ## How we built it: Running Replay on Temporal DevFeed: [How we built it: Running Replay on Temporal]() Original publisher: [Read original article]() Author: Ian Douglas Published: 2026-06-24T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [Web app](), [Cloud](), [API](), [Database](), [Encryption](), [Software]() Tags: [api](), [cloud](), [database](), [developer](), [developers](), [encryption](), [software](), [temporal-voices]() ### AI overview Temporal used Workflows and Activities to build and operate a custom registration and ecommerce system for Replay 2026. The system handled payments, coupons, attendee records, email, sensitive-data encryption, check-in, badges, workshops, and notifications, with integrations for payment processing, email, databases, and analytics. ### Source excerpt See how Temporal used Workflows and Activities to run Replay registration, from payments and coupons to long-lived ticket state and check-in. [Next page]()