# Temporal

Read current articles covering Durable Execution, Temporal Cloud, workflow examination, and open-source news. Stay in the know about Temporal Technologies.

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 to aggregate test results across teams with Temporal Nexus

DevFeed: [How to aggregate test results across teams with Temporal Nexus](<https://devfeed.tech/articles/how-to-aggregate-test-results-across-teams-with-temporal-nexus-146865.md>)

Original publisher: [Read original article](<https://temporal.io/blog/how-to-aggregate-test-results-across-teams-with-temporal-nexus>)

Author: Brooks Newberry

Published: 2026-11-20T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>), [Remote Procedure Call (RPC)](<https://devfeed.tech/topics/rpc.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [aggregate](<https://devfeed.tech/tags/aggregate.md>), [collect](<https://devfeed.tech/tags/collect.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [format](<https://devfeed.tech/tags/format.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [nexus](<https://devfeed.tech/tags/nexus.md>), [release](<https://devfeed.tech/tags/release.md>), [release-engineering](<https://devfeed.tech/tags/release-engineering.md>), [report](<https://devfeed.tech/tags/report.md>), [results](<https://devfeed.tech/tags/results.md>), [teams](<https://devfeed.tech/tags/teams.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

Temporal's Release Engineering team built a shared report format and Nexus Operation to collect test evidence from cloud validation and open source test Workflows while leaving tests and verdicts with their owners. Producers call a named Operation through an allowed Temporal Endpoint using their existing Temporal connections; a direct gRPC write API would require a reachable service and separate authentication and access controls. The synchronous handler validates and stores reports, keyed by (source, business_id), then returns the record ID. That key makes retries after a lost response return the same record, but repeated submissions can replace contents, and older payloads are not rejected by timestamp. Each report and result uses pass, warn, fail, or skipped; a test failure can coexist with successful ingestion. The team reads reports through a separate gRPC API. Nexus access is limited to explicitly allowed Namespaces in the same Cloud Account, and the synchronous database work must finish within ten seconds; Temporal recommends asynchronous Operations for uncertain database latency or availability. Reports support release decisions but do not automatically determine readiness,

### Source excerpt

How Temporal's Release Engineering team used a Nexus Operation and a shared report format to collect test results from many teams in one place.

## Security that compounds

DevFeed: [Security that compounds](<https://devfeed.tech/articles/security-that-compounds-141985.md>)

Original publisher: [Read original article](<https://temporal.io/blog/security-that-compounds>)

Author: Kent Gruber

Published: 2026-11-18T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Agentic SOC](<https://devfeed.tech/topics/agentic-soc.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [policy-as-code](<https://devfeed.tech/topics/policy-as-code.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [controls](<https://devfeed.tech/tags/controls.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [risks](<https://devfeed.tech/tags/risks.md>), [scale](<https://devfeed.tech/tags/scale.md>), [security](<https://devfeed.tech/tags/security.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>)

### AI overview

Temporal's security team uses a versioned repository of security boundaries, decisions, and tests as shared context for people and agents. Agents help triage reports, review designs, answer customer questions, assess dependency alerts, and run cross-repository campaigns; people make consequential decisions and approve merges. Deterministic hooks and policy code enforce controls outside the model: Deputy applies supply-chain policy across laptops, CI, and download time, while Camper tracks campaigns as Temporal Workflows and coordinates pull requests. The team checks agent claims against cited sources and tests, and treats incoming reports as untrusted. The article reports that one September vulnerability fix was merged and released in under 24 hours, with a reproducer and regression test. It also notes limits: agents can be wrong, and most investigations still run as long-lived agent sessions; moving them onto Temporal Workflows remains planned work.

### Source excerpt

See how Temporal's security team combines AI agents, shared security knowledge, and deterministic controls to investigate risks and scale security work.

## Temporal Cloud on Azure is now in Public Preview

DevFeed: [Temporal Cloud on Azure is now in Public Preview](<https://devfeed.tech/articles/temporal-cloud-on-azure-is-now-in-public-preview-141982.md>)

Original publisher: [Read original article](<https://temporal.io/blog/azure-publicpreview>)

Author: Ben Echols

Published: 2026-11-18T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Azure](<https://devfeed.tech/topics/azure.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [apis](<https://devfeed.tech/tags/apis.md>), [applications](<https://devfeed.tech/tags/applications.md>), [australia](<https://devfeed.tech/tags/australia.md>), [availability](<https://devfeed.tech/tags/availability.md>), [aws](<https://devfeed.tech/tags/aws.md>), [azure](<https://devfeed.tech/tags/azure.md>), [azure-deployment](<https://devfeed.tech/tags/azure-deployment.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [customers](<https://devfeed.tech/tags/customers.md>), [managed](<https://devfeed.tech/tags/managed.md>), [openai](<https://devfeed.tech/tags/openai.md>), [platform](<https://devfeed.tech/tags/platform.md>), [preview](<https://devfeed.tech/tags/preview.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [public](<https://devfeed.tech/tags/public.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

Temporal Cloud on Azure is in Public Preview for production workloads in Central US and Australia East, with access requiring approval for capacity planning. Azure teams use the same programming model and all eight SDKs available across Azure, AWS, and Google Cloud. Temporal operates the control plane and persistence layer; customers deploy and operate Workers in their own environment, which can connect privately through Azure Private Link. The service tracks progress and recovers interrupted work, while RBAC and SAML SSO manage access. Cross-cloud replication and failover are available for supported region pairs within the same geography. Microsoft Agent Framework and Microsoft Foundry integrations are still in development. To request access, contact a Temporal account team or support with the preferred region, use case, and expected workload; existing pre-release customers are onboarded first.

### Source excerpt

Your choice of cloud reflects what your business needs, from enterprise requirements to access to compute for AI. As those needs change, you should be able to build reliable applications and agents wherever you need to grow. Today, we're extending that choice with the Public Preview of Temporal Cloud on Azure. Azure teams can now use our managed service to build on the Temporal platform used by more than 4,300 paying customers, including OpenAI, Netflix, and NVIDIA.

## Building a reliable AI agent with OSCAR

DevFeed: [Building a reliable AI agent with OSCAR](<https://devfeed.tech/articles/building-a-reliable-ai-agent-with-oscar-141983.md>)

Original publisher: [Read original article](<https://temporal.io/blog/building-a-reliable-ai-agent-with-oscar>)

Author: Loïc Ortola

Published: 2026-11-18T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-loop](<https://devfeed.tech/tags/agentic-loop.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-decisions](<https://devfeed.tech/tags/ai-decisions.md>), [building](<https://devfeed.tech/tags/building.md>), [community](<https://devfeed.tech/tags/community.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [retries](<https://devfeed.tech/tags/retries.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

OSCAR turns an emailed refund request into an action across the marketplace backend and Stripe, using an LLM to interpret the complaint and tools to check orders, update status, issue refunds, and reply. The initial Spring AI prototype can complete the flow, but a Stripe outage or process restart can leave partial work stranded, with no recovery or visibility into the agent's decisions. The Spring AI/Temporal integration runs model calls and external tools as Activities, adding retries and durable resumption while preserving the agent's business logic; Temporal's UI records inputs, results, retries, and failures, though individual retry attempts need Worker logs or extra instrumentation. Workflows can also pause without polling for human approval, resume after a process restart, and branch on the decision or a timeout. Temporal does not solve context growth, prompt or tool quality, or security: backend tools must independently validate and authorize actions, since agent instructions are not a security boundary.

### Source excerpt

Learn how to take a Spring AI agent from prototype to production with Temporal, adding durable execution, retries, observability, and human approval.

## Temporal is named to the 2026 AI 100 as teams ask more of their AI infrastructure

DevFeed: [Temporal is named to the 2026 AI 100 as teams ask more of their AI infrastructure](<https://devfeed.tech/articles/temporal-is-named-to-the-2026-ai-100-as-teams-ask-more-of-their-ai-infrastructure-131442.md>)

Original publisher: [Read original article](<https://temporal.io/blog/temporal-named-to-2026-ai-100>)

Author: Preeti Somal

Published: 2026-11-12T00:00:00Z

Content type: news

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [applications](<https://devfeed.tech/tags/applications.md>), [banks](<https://devfeed.tech/tags/banks.md>), [bessemer-venture-partners](<https://devfeed.tech/tags/bessemer-venture-partners.md>), [building-with-ai](<https://devfeed.tech/tags/building-with-ai.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [failure](<https://devfeed.tech/tags/failure.md>), [failures](<https://devfeed.tech/tags/failures.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [production](<https://devfeed.tech/tags/production.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

Temporal says its Durable Execution layer stores workflow state and execution history, then resumes from the last completed step after a failure. This is intended to support long-running AI agents that depend on multiple systems, while taking retry and recovery code off developers' hands. Temporal says it works with the OpenAI SDK, Pydantic SDK, and others, allowing teams to change models or frameworks without changing the underlying layer. The company also cites large payload storage and protections for downstream systems and GPU costs as areas of recent engineering work. These are company claims in an announcement of Temporal's No. 34 ranking in the inaugural 2026 AI 100; the text does not provide independent performance evidence.

### Source excerpt

Temporal joins the inaugural 2026 AI 100. Why reliability and Durable Execution matter as AI agents run for weeks and must survive failures in production.

## DOOM, durably: running DOOM as a Temporal Workflow

DevFeed: [DOOM, durably: running DOOM as a Temporal Workflow](<https://devfeed.tech/articles/doom-durably-running-doom-as-a-temporal-workflow-131441.md>)

Original publisher: [Read original article](<https://temporal.io/blog/running-doom-as-a-temporal-workflow>)

Author: Chris Smith

Published: 2026-11-11T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [recording](<https://devfeed.tech/topics/recording.md>), [Web app](<https://devfeed.tech/topics/webapp.md>)

Tags: [crashes](<https://devfeed.tech/tags/crashes.md>), [death](<https://devfeed.tech/tags/death.md>), [doom](<https://devfeed.tech/tags/doom.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [games](<https://devfeed.tech/tags/games.md>), [resume](<https://devfeed.tech/tags/resume.md>), [rewind](<https://devfeed.tech/tags/rewind.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

DOOM's deterministic, tic-based engine makes its input stream sufficient to rebuild game state, much like a Temporal Workflow history. The Workflow records player `ticcmd`s as durable Updates, uses Queries to render frames without growing history, and runs external effects such as leaderboard writes as retryable Activities. A Worker can recover after a crash by replaying recorded inputs; Continue-as-New bounds history by carrying forward a roughly 25 KB DOOM save snapshot, and Temporal Reset can rewind to before later inputs. The browser and Worker run the same engine and compare checksums. In multiplayer, using the Workflow as lockstep arbiter caused noticeable input lag because each tic made a cloud round trip; moving real-time coordination to a web server reduced latency, while the Workflow periodically records batches and remains the source of truth. Inputs not yet recorded can be lost in a server crash. Engine builds are pinned to preserve deterministic replay.

### Source excerpt

See how DOOM runs as a Temporal Workflow, using deterministic inputs, replay, and Durable Execution to survive crashes, resume games, and even rewind death.

## Who needs workflows when you have agents?

DevFeed: [Who needs workflows when you have agents?](<https://devfeed.tech/articles/who-needs-workflows-when-you-have-agents-128938.md>)

Original publisher: [Read original article](<https://temporal.io/blog/who-needs-workflows-when-you-have-agents>)

Author: Tao Guo

Published: 2026-11-10T00:00:00Z

Content type: opinion

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [about](<https://devfeed.tech/tags/about.md>), [accounts-payable](<https://devfeed.tech/tags/accounts-payable.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adapting](<https://devfeed.tech/tags/adapting.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agents](<https://devfeed.tech/tags/agents.md>), [auditability](<https://devfeed.tech/tags/auditability.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [gives](<https://devfeed.tech/tags/gives.md>), [long-running](<https://devfeed.tech/tags/long-running.md>), [needs](<https://devfeed.tech/tags/needs.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [running](<https://devfeed.tech/tags/running.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The article argues that enterprise agents can remain adaptive while deterministic workflows handle exact business transactions, with Temporal providing durable execution between them. It says Temporal preserves workflow state and audit history, manages retries and recovery across failures, and lets processes resume through long pauses, restarts, and human approvals. Temporal Nexus connects agents and workflows through service contracts in both directions, including work that completes hours or days later. In the accounts payable example, an agent reviews invoices and prepares a batch, while a Temporal Workflow executes and monitors approved payments, resuming after provider outages or redeployments. The article presents this as an architectural approach for reliability and auditability; it does not provide comparative performance measurements.

### Source excerpt

See how Temporal gives AI agents a durable backbone for long-running enterprise workflows that require reliability, recovery, and auditability.

## Securing self-hosted Temporal cross-cluster replication with mTLS

DevFeed: [Securing self-hosted Temporal cross-cluster replication with mTLS](<https://devfeed.tech/articles/securing-self-hosted-temporal-cross-cluster-replication-with-mtls-128937.md>)

Original publisher: [Read original article](<https://temporal.io/blog/securing-self-hosted-temporal-cross-cluster-replication-with-mtls>)

Author: Adam Quan

Published: 2026-11-10T00:00:00Z

Content type: tutorial

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Self-hosted](<https://devfeed.tech/topics/self-hosted.md>), [on-prem](<https://devfeed.tech/topics/on-prem.md>), [Single sign-on (SSO)](<https://devfeed.tech/topics/sso.md>)

Tags: [certificates](<https://devfeed.tech/tags/certificates.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cross](<https://devfeed.tech/tags/cross.md>), [failover](<https://devfeed.tech/tags/failover.md>), [mtls](<https://devfeed.tech/tags/mtls.md>), [replication](<https://devfeed.tech/tags/replication.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

The walkthrough secures self-hosted Temporal cross-cluster replication with mTLS across three paths: client-to-Frontend, internode service traffic, and inter-cluster replication. It uses a shared self-signed CA for two independent clusters, with separate server and client identities; certificates must cover the hostnames peers use, and private keys stay within their own cluster. Configure each cluster's TLS sections and matching replication metadata, then verify cluster health, register both peers, create a global Namespace, confirm Workflow state replicates, and test failover. The approach extends to more clusters. The demo is educational: production requires certificate rotation, separate CAs by environment, least-privilege client certificates, correct immutable shard and failover settings, and replication-lag monitoring. Application-level token authentication is identified as a follow-up topic.

### Source excerpt

Learn how to secure self-hosted Temporal cross-cluster replication with mTLS, including certificates, cluster configuration, failover, and testing.

## How I built an AI prospecting agent on Temporal to take the admin off BDRs

DevFeed: [How I built an AI prospecting agent on Temporal to take the admin off BDRs](<https://devfeed.tech/articles/how-i-built-an-ai-prospecting-agent-on-temporal-to-take-the-admin-off-bdrs-125693.md>)

Original publisher: [Read original article](<https://temporal.io/blog/ai-prospecting-agent-temporal-kepler>)

Author: Jeff Long

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [acme](<https://devfeed.tech/tags/acme.md>), [added](<https://devfeed.tech/tags/added.md>), [admin](<https://devfeed.tech/tags/admin.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alert](<https://devfeed.tech/tags/alert.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [api](<https://devfeed.tech/tags/api.md>), [i](<https://devfeed.tech/tags/i.md>), [outreach](<https://devfeed.tech/tags/outreach.md>), [prospecting](<https://devfeed.tech/tags/prospecting.md>), [send](<https://devfeed.tech/tags/send.md>), [take](<https://devfeed.tech/tags/take.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>)

### AI overview

Kepler uses Temporal to automate prospecting administration while leaving reps in control of sending. It watches for signals from Common Room, Reo.dev and the open web via Exa; Claude qualifies them, identifies and verifies contacts, and checks suppression and account rules. It creates Salesforce campaigns and drafts Outreach steps and call briefs for rep review. A rulebook tailors messages by sender, reader and prospect familiarity; models draw only on sourced approved facts, while code checks flag risky wording and references to tracking activity. Temporal Workflows and retryable Activities manage long scans, waits and recovery; because Activities can run at least once, writes check existing state and hold uncertain cases. The author reports Kepler is live for BDRs and commercial reps but makes no performance claims. Custom development took longer than off-the-shelf tools, with control over cross-system checks and messaging rules as its stated benefit.

### Source excerpt

Jeff Long, former BDR, built Kepler, an AI prospecting agent on Temporal that spots signals, vets contacts, and drafts outreach for reps to edit and send.

## Your agent harness shouldn't be a black box

DevFeed: [Your agent harness shouldn't be a black box](<https://devfeed.tech/articles/your-agent-harness-shouldn-t-be-a-black-box-125694.md>)

Original publisher: [Read original article](<https://temporal.io/blog/your-agent-harness-shouldnt-be-a-black-box>)

Author: Melanie Warrick

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [actor](<https://devfeed.tech/tags/actor.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-architecture](<https://devfeed.tech/tags/agent-architecture.md>), [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [failure](<https://devfeed.tech/tags/failure.md>), [harness](<https://devfeed.tech/tags/harness.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [memory](<https://devfeed.tech/tags/memory.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [tool](<https://devfeed.tech/tags/tool.md>)

### AI overview

A generated agent harness can work while hiding what the model sees, what it retains, which tools it can use, and what happens after failure. The article shows an Amazon Bedrock AgentCore setup whose configuration selects a model, tools, skills, and memory; its demo used a TypeScript loop built with Strands Agents. AgentCore session IDs group conversations, with runtime history kept for 15 minutes to 8 hours, while long-term memory strategies extract episodes, facts, summaries, or preferences into a vector store, taking 2-3 minutes and consuming tokens. Temporal can record completed model calls and tool invocations as Activity results in Event History so a Workflow can resume, but wrapping an entire agent run in one Activity does not separately preserve its internal steps; retries may repeat work, and external actions need idempotency or state checks. The article distinguishes agent frameworks for the reasoning loop, AgentCore for managed execution and supporting services, and Temporal for orchestration and durable recovery. It recommends reviewing traces, permissions, memory inputs, retry boundaries, and resource and model usage, and testing recovery by restarting after completed,

### Source excerpt

Understand the choices inside your AI agent harness, from memory and tool access to failure recovery, with Amazon Bedrock AgentCore and Temporal.

## Measuring Temporal Workflow health with OpenTelemetry and Parseable

DevFeed: [Measuring Temporal Workflow health with OpenTelemetry and Parseable](<https://devfeed.tech/articles/measuring-temporal-workflow-health-with-opentelemetry-and-parseable-119223.md>)

Original publisher: [Read original article](<https://temporal.io/blog/measuring-temporal-workflow-health-with-opentelemetry-and-parseable>)

Author: Praveen K B

Published: 2026-11-05T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>)

Tags: [alert](<https://devfeed.tech/tags/alert.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [backlog](<https://devfeed.tech/tags/backlog.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [community](<https://devfeed.tech/tags/community.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [custom](<https://devfeed.tech/tags/custom.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [delay](<https://devfeed.tech/tags/delay.md>), [health](<https://devfeed.tech/tags/health.md>), [onboarding](<https://devfeed.tech/tags/onboarding.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [queue](<https://devfeed.tech/tags/queue.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [time](<https://devfeed.tech/tags/time.md>), [worker](<https://devfeed.tech/tags/worker.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

The excerpt describes combining Temporal SDK metrics with Parseable lifecycle records and traces to explain Workflow duration beyond a simple Completed status. In a controlled Temporal Cloud onboarding run, verifyIdentity failed twice and succeeded on its third attempt; Parseable preserved each attempt and the Workflow's domain milestones. Metrics help locate Task Queue waiting and Worker slot pressure, while lifecycle records expose attempt status and duration, and traces show timing and parent-child relationships. The guidance pairs Schedule-to-Start latency with slot availability, host utilization, and poller behavior; it also tracks backlog age, retries, and Workflow Run duration. It recommends low-cardinality labels for dashboards and retaining execution IDs for targeted investigation. Backlog values are approximate, and the validation was not a production benchmark.

### Source excerpt

A customer can complete onboarding and still be unhappy with the experience. A Workflow's Completed status tells you it finished, but not where it spent its time. Onboarding might have taken five minutes or 50 because an Activity waited for a Worker, an identity provider timed out, or a Task Queue received Tasks faster than Workers could process them. We built a simple onboarding Workflow that runs on Workers connected to Temporal Cloud and sent its telemetry to Parseable.

## Durable Execution means deciding what survives failure

DevFeed: [Durable Execution means deciding what survives failure](<https://devfeed.tech/articles/durable-execution-means-deciding-what-survives-failure-117163.md>)

Original publisher: [Read original article](<https://temporal.io/blog/durable-execution-means-deciding-what-survives-failure>)

Author: Muhammad Abu Bakkar Bin Akmal

Published: 2026-11-04T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Persistence](<https://devfeed.tech/topics/persistence.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [ReAct agent Python](<https://devfeed.tech/topics/react-agent-python.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [community](<https://devfeed.tech/tags/community.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [failure](<https://devfeed.tech/tags/failure.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [progress](<https://devfeed.tech/tags/progress.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [retries](<https://devfeed.tech/tags/retries.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Temporal can restore Workflow progress after Worker restarts by replaying Event History, but application policy still determines retries, business status, cancellation, and what counts as success. In the Kubernetes scan, six analyzers run concurrently but are awaited in slice order, so failures are not observed fail-fast; the review also flags status cleanup and ambiguous database-record/Workflow-start outcomes. Analysis results are persisted before the optional assessment, allowing them to survive an assessment failure. In the AI recommendation loop, proposals carry prior feedback and budget across rounds, with explicit exits for consensus, approved score, repeated concerns, or round limit. Only accepted decisions should be cached; unresolved results can be structurally valid. The excerpt recommends defining start and ID reuse semantics, making external effects retry-safe through stable keys and deduplication, putting replay-sensitive configuration in Workflow input, and testing business outcomes and Worker-loss recovery. Its reviewed tests did not cover the listed failure scenarios or a live Nexus end-to-end path.

### Source excerpt

See how Temporal preserves progress across failures in Kubernetes analysis and AI agent Workflows, while keeping retries and recovery explicit.

## Durable Digest: October highlights

DevFeed: [Durable Digest: October highlights](<https://devfeed.tech/articles/durable-digest-october-highlights-117162.md>)

Original publisher: [Read original article](<https://temporal.io/blog/durable-digest-october-highlights>)

Author: Temporal Technologies

Published: 2026-11-03T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Learning](<https://devfeed.tech/topics/learning.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-application](<https://devfeed.tech/tags/ai-application.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [approach](<https://devfeed.tech/tags/approach.md>), [building](<https://devfeed.tech/tags/building.md>), [digest](<https://devfeed.tech/tags/digest.md>), [examples](<https://devfeed.tech/tags/examples.md>), [explore](<https://devfeed.tech/tags/explore.md>), [highlights](<https://devfeed.tech/tags/highlights.md>), [october](<https://devfeed.tech/tags/october.md>), [practical](<https://devfeed.tech/tags/practical.md>), [product](<https://devfeed.tech/tags/product.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

October's Temporal update pairs Cloud pricing and product releases with practical reliability patterns. Temporal Cloud now offers pay-as-you-go pricing with no monthly base fee. Poller autoscaling is Generally Available and adjusts Worker poller counts as demand changes; Nexus features, moving Namespaces across Projects, and Temporal Proxy are in Pre-Release. The examples cover adding Durable Execution to StackAI's document indexing pipeline, carrying task-scoped signed permissions across services with Nexus, coordinating shared-resource access, and managing document approvals. Community discussions also surfaced trade-offs in Task Queue Fairness between dispatch throughput and accuracy at low dispatch rates, and explained that deleting closed executions can leave history for later cleanup.

### Source excerpt

Explore October's product updates and practical examples of building reliable applications with Temporal.

## You don't need to build a new reliability system for every AI Framework

DevFeed: [You don't need to build a new reliability system for every AI Framework](<https://devfeed.tech/articles/you-don-t-need-to-build-a-new-reliability-system-for-every-ai-framework-109248.md>)

Original publisher: [Read original article](<https://temporal.io/blog/ai-framework-integrations>)

Author: David Hyde

Published: 2026-10-30T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [google-adk](<https://devfeed.tech/topics/google-adk.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [mastra](<https://devfeed.tech/topics/mastra.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [adk](<https://devfeed.tech/tags/adk.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-framework](<https://devfeed.tech/tags/ai-framework.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [execution](<https://devfeed.tech/tags/execution.md>), [framework](<https://devfeed.tech/tags/framework.md>), [google](<https://devfeed.tech/tags/google.md>), [google-adk](<https://devfeed.tech/tags/google-adk.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-agents](<https://devfeed.tech/tags/openai-agents.md>), [openai-agents-sdk](<https://devfeed.tech/tags/openai-agents-sdk.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

Temporal's GA integrations let agents built with frameworks such as Google ADK, OpenAI Agents SDK, Strands, and LangGraph run with durable execution without rewriting their agent code. Workflows coordinate long-running steps, while Activities perform model calls and other side effects; Temporal records progress and reuses recorded Activity results during replay after a Worker restart or deployment. The integrations centralize retries and timeouts in Temporal, keep clients and credentials on Workers, and carry trace context. Human input can be awaited without polling or holding a Worker open. Token streaming through Workflow Streams is available where supported and remains in Public Preview for Python and TypeScript. Upgrading existing integrations may involve breaking package or import changes; release notes identify cases that may require Worker Versioning.

### Source excerpt

Temporal integrations for Google ADK, OpenAI Agents SDK, AWS Strands, LangGraph, and more are GA. Here to add Durable Execution to your agents.

## See what's happening. Control what happens next.

DevFeed: [See what's happening. Control what happens next.](<https://devfeed.tech/articles/see-what-s-happening-control-what-happens-next-106826.md>)

Original publisher: [Read original article](<https://temporal.io/blog/production-controls>)

Author: Hien Phan

Published: 2026-10-29T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [control-plane](<https://devfeed.tech/topics/control-plane.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Error Handling](<https://devfeed.tech/topics/error-handling.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [administration](<https://devfeed.tech/tags/administration.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [attention](<https://devfeed.tech/tags/attention.md>), [automated](<https://devfeed.tech/tags/automated.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [change](<https://devfeed.tech/tags/change.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-migration](<https://devfeed.tech/tags/cloud-migration.md>), [control](<https://devfeed.tech/tags/control.md>), [execution](<https://devfeed.tech/tags/execution.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [production](<https://devfeed.tech/tags/production.md>), [recover](<https://devfeed.tech/tags/recover.md>), [settings](<https://devfeed.tech/tags/settings.md>), [stalled](<https://devfeed.tech/tags/stalled.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-concepts](<https://devfeed.tech/tags/temporal-concepts.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Temporal's production controls help operators find stalled Workflows, pause execution during an investigation, and change how pending work proceeds. Task Issues Detection flags Workflow Task failures or timeouts in the Web UI; a successful task clears the flag. Workflow Pause stops dispatching new Workflow and Activity Tasks, including retries, but in-flight attempts, timers, and timeouts continue; it is in Pre-release. Public Preview Activity Operations can change supported settings for pending Activities or reset retry state; changed settings apply on the next attempt, and these operations are not recorded in Event History. Workflow Update Options can change routing subject to Event History compatibility, while Workflow Reset can replay steps after a selected point, with possible external side effects. The excerpt also describes a Public Preview Cloud CLI extension and a Pre-release migration path for eligible self-hosted workloads, subject to requirements and account-team review.

### Source excerpt

Learn how Temporal's production controls help you find stalled Workflows, pause execution, adjust Activity settings, and recover from production issues.

## Serverless Workers: the fastest way to start, and nothing to rethink as you grow

DevFeed: [Serverless Workers: the fastest way to start, and nothing to rethink as you grow](<https://devfeed.tech/articles/serverless-workers-the-fastest-way-to-start-and-nothing-to-rethink-as-you-grow-105564.md>)

Original publisher: [Read original article](<https://temporal.io/blog/serverless-workers-lambda-cloud-run>)

Author: Brandon Chavis

Published: 2026-10-28T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Serverless](<https://devfeed.tech/topics/serverless.md>), [AWS Lambda](<https://devfeed.tech/topics/aws-lambda.md>), [Cloud Run](<https://devfeed.tech/topics/cloud-run.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [Google Cloud Platform (GCP)](<https://devfeed.tech/topics/google-cloud.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-apps](<https://devfeed.tech/tags/ai-apps.md>), [apps](<https://devfeed.tech/tags/apps.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-run](<https://devfeed.tech/tags/cloud-run.md>), [compute](<https://devfeed.tech/tags/compute.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [google](<https://devfeed.tech/tags/google.md>), [google-cloud](<https://devfeed.tech/tags/google-cloud.md>), [google-cloud-run](<https://devfeed.tech/tags/google-cloud-run.md>), [jobs](<https://devfeed.tech/tags/jobs.md>), [lambda](<https://devfeed.tech/tags/lambda.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [scale](<https://devfeed.tech/tags/scale.md>), [scale-up](<https://devfeed.tech/tags/scale-up.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [workers](<https://devfeed.tech/tags/workers.md>), [zero](<https://devfeed.tech/tags/zero.md>)

### AI overview

Temporal Serverless Workers pair Durable Execution with on-demand compute in your cloud account: Temporal Cloud persists progress, coordinates work, and retries failures, while workers run on AWS Lambda, Google Cloud Run Worker Pools, or Amazon Bedrock AgentCore Runtime. Standalone Activities provide durable background jobs with configurable retries and timeouts, status and result visibility, and identifiers for finding or canceling jobs. Workflows coordinate multiple Activities and preserve state while waiting, so applications can span days without continuously running compute; existing Activities can be reused as Workflow steps. Lambda targets event-driven or highly scalable workloads. Cloud Run Worker Pools run containers, including workloads needing longer execution times. AgentCore Runtime is aimed at agentic applications and provides optional agent services such as identity, tools, memory, and observability, while Temporal coordinates execution. The excerpt says Lambda and Cloud Run are in Public Preview and AgentCore support is in Pre-release as of October 2026.

### Source excerpt

Temporal Serverless Workers pair Durable Execution with on-demand compute on AWS Lambda and Google Cloud Run, so jobs and AI apps scale up and down to zero.

## Temporal JWT token authentication

DevFeed: [Temporal JWT token authentication](<https://devfeed.tech/articles/temporal-jwt-token-authentication-102710.md>)

Original publisher: [Read original article](<https://temporal.io/blog/temporal-jwt-token-authentication>)

Author: Adam Quan

Published: 2026-10-27T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [JSON Web Tokens](<https://devfeed.tech/topics/jwt.md>), [Keycloak](<https://devfeed.tech/topics/keycloak.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [Single sign-on (SSO)](<https://devfeed.tech/topics/sso.md>), [Secure token management](<https://devfeed.tech/topics/secure-token-management.md>), [OpenID connect (OIDC)](<https://devfeed.tech/topics/oidc.md>), [gRPC](<https://devfeed.tech/topics/grpc.md>), [client library](<https://devfeed.tech/topics/client-library.md>)

Tags: [authentication](<https://devfeed.tech/tags/authentication.md>), [configure](<https://devfeed.tech/tags/configure.md>), [jwt](<https://devfeed.tech/tags/jwt.md>), [keycloak](<https://devfeed.tech/tags/keycloak.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [refresh](<https://devfeed.tech/tags/refresh.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [sso](<https://devfeed.tech/tags/sso.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>), [token](<https://devfeed.tech/tags/token.md>), [token-authentication](<https://devfeed.tech/tags/token-authentication.md>), [worker](<https://devfeed.tech/tags/worker.md>)

### AI overview

The article outlines JWT authentication for self-hosted Temporal using Keycloak. It assigns machine clients such as Workers a client-credentials flow and human UI or CLI users an interactive login, with Keycloak roles mapped to Temporal's `permissions` claim (for example, `temporal-system:admin`). Temporal's default ClaimMapper reads those claims and its Authorizer checks permissions; the frontend needs JWT verification keys, while the internal frontend remains available for internal cluster traffic. The UI is configured with Keycloak discovery, client credentials, callback URL, and scopes. CLI requests pass a bearer token through `TEMPORAL_GRPC_META_AUTHORIZATION`; SDK clients pass it in `rpc_metadata`. Since tokens expire, the Python example refreshes them in the background by updating client metadata before expiry, avoiding a token request on every API call. The demonstration omits TLS, so tokens sent over the network are vulnerable to interception.

### Source excerpt

Learn how to configure JWT authentication for self-hosted Temporal with Keycloak, including SSO, Worker access, role mapping, and token refresh.

## Introducing Temporal Proxy

DevFeed: [Introducing Temporal Proxy](<https://devfeed.tech/articles/introducing-temporal-proxy-102711.md>)

Original publisher: [Read original article](<https://temporal.io/blog/temporal-proxy>)

Author: Luke Knepper

Published: 2026-10-27T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Secrets Management](<https://devfeed.tech/topics/secrets-management.md>), [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>), [payload](<https://devfeed.tech/topics/payload.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-kms](<https://devfeed.tech/tags/aws-kms.md>), [azure](<https://devfeed.tech/tags/azure.md>), [backends](<https://devfeed.tech/tags/backends.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [control](<https://devfeed.tech/tags/control.md>), [custom](<https://devfeed.tech/tags/custom.md>), [data](<https://devfeed.tech/tags/data.md>), [encryption](<https://devfeed.tech/tags/encryption.md>), [keys](<https://devfeed.tech/tags/keys.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [payload](<https://devfeed.tech/tags/payload.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>), [teams](<https://devfeed.tech/tags/teams.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

Temporal Proxy centralizes encryption of Temporal Workflow payloads in a component teams deploy and operate in their own environment. Applications connect to it over authenticated mTLS; it encrypts payloads with short-lived AES-256-GCM data keys protected by customer-controlled keys through AWS KMS, Google Cloud KMS, Azure Key Vault, or custom backends. Temporal Cloud stores ciphertext and protected data keys but cannot decipher them; the proxy decrypts values for Workers within the customer environment. To reduce accidental bypass, the text recommends making the proxy the required connection, keeping Cloud credentials with it, and blocking direct application and Worker connections. Configure encryption for application payloads, error messages, and stack traces; Search Attributes remain unencrypted, and existing stored data is not encrypted retroactively. The text says the product is in Public Preview, fully supported, and recommended for production.

### Source excerpt

Temporal Proxy centralizes payload encryption with keys you control, so Temporal Cloud can't read sensitive data and teams skip custom encryption libraries.

## Culture is the execution layer: how Temporal is growing without losing itself

DevFeed: [Culture is the execution layer: how Temporal is growing without losing itself](<https://devfeed.tech/articles/culture-is-the-execution-layer-how-temporal-is-growing-without-losing-itself-102709.md>)

Original publisher: [Read original article](<https://temporal.io/blog/culture-is-the-execution-layer-how-temporal-is-growing-without-losing-itself>)

Author: Kate Caulfield

Published: 2026-10-27T00:00:00Z

Content type: opinion

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>)

Tags: [company](<https://devfeed.tech/tags/company.md>), [culture](<https://devfeed.tech/tags/culture.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [developers](<https://devfeed.tech/tags/developers.md>), [execution](<https://devfeed.tech/tags/execution.md>), [growth](<https://devfeed.tech/tags/growth.md>), [mental-models](<https://devfeed.tech/tags/mental-models.md>), [messy](<https://devfeed.tech/tags/messy.md>), [people](<https://devfeed.tech/tags/people.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>)

### AI overview

Temporal's SVP of People argues that culture becomes an execution system as a company scales: it guides the many decisions employees make when leaders are unavailable. Temporal describes four growth phases in 18 months and calls its current hypergrowth stage the "messy middle," where slower results, onboarding gaps, more meetings, and longer decisions are expected signs of systems built for a smaller company. To help people navigate this, the company names phase shifts, defines behaviors and anti-behaviors for its four values, and has written down the mental models leaders use to resolve tensions between values. The excerpt presents this explicit guidance and investment in managers as ways to support execution and employee growth through change.

### Source excerpt

Temporal's SVP of People speaks on the messy middle between growth phases, and how mental models and manager investment help people grow with the company.

## Introducing the Temporal Product Edition -- October 2026

DevFeed: [Introducing the Temporal Product Edition -- October 2026](<https://devfeed.tech/articles/introducing-the-temporal-product-edition-october-2026-100724.md>)

Original publisher: [Read original article](<https://temporal.io/blog/october-2026-temporal-product-edition>)

Author: Hien Phan

Published: 2026-10-26T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Maintainability](<https://devfeed.tech/topics/maintainability.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [applications](<https://devfeed.tech/tags/applications.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [build](<https://devfeed.tech/tags/build.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [cloud-run](<https://devfeed.tech/tags/cloud-run.md>), [labs](<https://devfeed.tech/tags/labs.md>), [launches](<https://devfeed.tech/tags/launches.md>), [nexus](<https://devfeed.tech/tags/nexus.md>), [october](<https://devfeed.tech/tags/october.md>), [october-2026](<https://devfeed.tech/tags/october-2026.md>), [product](<https://devfeed.tech/tags/product.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [workers](<https://devfeed.tech/tags/workers.md>)

### AI overview

Temporal's first Product Edition previews five launches aimed at making mission-critical applications and agents easier to build and operate. Standalone Nexus Operations lets apps and agents call reusable Nexus services through the Temporal SDK, with durable handling of failures and waits. Temporal Proxy centralizes encryption using customers' keys in their own environment, keeping protected values unreadable to Temporal Cloud. Serverless Workers run code on AWS Lambda or Google Cloud Run with demand-following capacity while Temporal tracks progress and retries; Amazon Bedrock AgentCore Runtime is listed as pre-release. Production controls help teams inspect work, investigate repeated failures, pause executions, and adjust retries and timeouts for pending steps; the post also covers moving workloads to Temporal Cloud. Temporal Labs offers early open source experiments and direct feedback opportunities, but projects may change or lose investment and are not supported product commitments.

### Source excerpt

Temporal's first Product Edition delivers five launches in five days, from Nexus and Proxy to Serverless Workers and Labs, for durable apps and agents.

## Introducing Standalone Nexus Operations

DevFeed: [Introducing Standalone Nexus Operations](<https://devfeed.tech/articles/introducing-standalone-nexus-operations-100725.md>)

Original publisher: [Read original article](<https://temporal.io/blog/standalone-nexus-operations>)

Author: Keith Tenzer

Published: 2026-10-26T00:00:00Z

Content type: release

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [gRPC](<https://devfeed.tech/topics/grpc.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [resource oriented design typescript](<https://devfeed.tech/topics/resource-oriented-design-typescript.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [also](<https://devfeed.tech/tags/also.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [await](<https://devfeed.tech/tags/await.md>), [backend](<https://devfeed.tech/tags/backend.md>), [billing](<https://devfeed.tech/tags/billing.md>), [built-in](<https://devfeed.tech/tags/built-in.md>), [call](<https://devfeed.tech/tags/call.md>), [net](<https://devfeed.tech/tags/net.md>), [nexus](<https://devfeed.tech/tags/nexus.md>), [operations](<https://devfeed.tech/tags/operations.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [retries](<https://devfeed.tech/tags/retries.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [services](<https://devfeed.tech/tags/services.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [tracking](<https://devfeed.tech/tags/tracking.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Standalone Nexus Operations lets existing backends, tools, and agents call shared Nexus services through the Temporal SDK while keeping their surrounding application logic in place. After Temporal accepts an operation, it tracks it independently of the original request and retries delivery after temporary connection failures within the operation's timeout. Callers start an operation with an ID, then can retrieve its result later; result() waits for completion or throws an error if it fails. The article's payment example leaves order flow and payment-outcome handling to the backend while Temporal manages delivery and operation tracking, including across disconnects or restarts. Public Preview is announced for November 1; the article points to SDK guides for Go, Java, .NET, Python, and TypeScript.

### Source excerpt

Standalone Nexus Operations lets apps and agents call durable Nexus services directly through the Temporal SDK, with retries and tracking built in.

## From film school to AI: Melanie Warrick's path to developer advocacy at Temporal

DevFeed: [From film school to AI: Melanie Warrick's path to developer advocacy at Temporal](<https://devfeed.tech/articles/from-film-school-to-ai-melanie-warrick-s-path-to-developer-advocacy-at-temporal-95451.md>)

Original publisher: [Read original article](<https://temporal.io/blog/from-film-school-to-ai-melanie-warricks-path-to-developer-advocacy-at-temporal>)

Author: Jap Singh

Published: 2026-10-22T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [developer-relations](<https://devfeed.tech/topics/developer-relations.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [Bootcamp](<https://devfeed.tech/topics/bootcamp.md>)

Tags: [advocacy](<https://devfeed.tech/tags/advocacy.md>), [ai](<https://devfeed.tech/tags/ai.md>), [career](<https://devfeed.tech/tags/career.md>), [code](<https://devfeed.tech/tags/code.md>), [curiosity](<https://devfeed.tech/tags/curiosity.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [data-scientist](<https://devfeed.tech/tags/data-scientist.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-advocate](<https://devfeed.tech/tags/developer-advocate.md>), [developer-relations](<https://devfeed.tech/tags/developer-relations.md>), [developers](<https://devfeed.tech/tags/developers.md>), [devrel](<https://devfeed.tech/tags/devrel.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [film](<https://devfeed.tech/tags/film.md>), [learning](<https://devfeed.tech/tags/learning.md>), [school](<https://devfeed.tech/tags/school.md>), [storytelling](<https://devfeed.tech/tags/storytelling.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>)

### AI overview

Melanie Warrick's path to AI developer advocacy at Temporal drew on film, consulting, coding study, and hands-on engineering. Film production taught her to carry projects from idea to completion and to tell stories--skills she now uses to make technical topics accessible. After a women-only Python bootcamp, she worked in data science and machine learning, including putting AI into production, and held engineering and developer relations roles. At Temporal she hosts Vibe Check, a live series where guests build with AI and explore technical questions in real time. Her practical advice is to stay curious and use AI to learn, not just to reach an answer: when implementing Temporal, asking the tool to explain its steps and checking what she did not understand took about three hours instead of an estimated 30 minutes, but helped her retain the knowledge. She also recommends consistent visible work and taking on ambiguous problems.

### Source excerpt

Follow Melanie Warrick's path from film school to AI and developer advocacy at Temporal, shaped by curiosity, storytelling, and a drive to keep learning.

## I built an AI writing assistant

DevFeed: [I built an AI writing assistant](<https://devfeed.tech/articles/i-built-an-ai-writing-assistant-92863.md>)

Original publisher: [Read original article](<https://temporal.io/blog/i-built-an-ai-writing-assistant>)

Author: Jap Singh

Published: 2026-10-21T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-writing](<https://devfeed.tech/tags/ai-writing.md>), [brand-voice](<https://devfeed.tech/tags/brand-voice.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [content](<https://devfeed.tech/tags/content.md>), [context](<https://devfeed.tech/tags/context.md>), [draft](<https://devfeed.tech/tags/draft.md>), [editor](<https://devfeed.tech/tags/editor.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [team](<https://devfeed.tech/tags/team.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>), [workflows](<https://devfeed.tech/tags/workflows.md>), [writing](<https://devfeed.tech/tags/writing.md>)

### AI overview

Jap Singh built an AI writing assistant around Temporal's Voices of Temporal workflow: it helps engineers develop a topic into a focused idea, then switches to Editing Mode for draft feedback. To limit excessive rewriting and preserve writer control, it uses an interactive redline that explains flagged edits, offers alternatives, and calls out details to verify; writers choose what to accept. The assistant began as a Claude Project, was adapted as a ChatGPT Project, and later became a Claude Skill. Projects provide a dedicated workspace, while the Skill can bring guidance into an existing conversation; the same prompt may behave differently across Claude and ChatGPT and needs platform-specific adjustments. Singh's account recommends starting from the team's workflow, defining where assistance and human judgment belong, and testing edge cases.

### Source excerpt

See how Jap Singh built an AI writing assistant around real team workflows, with separate modes for brainstorming and editing.

## A conversation with StackAI's CTO: how Temporal cut indexing failures from 20% to below 0.1%

DevFeed: [A conversation with StackAI's CTO: how Temporal cut indexing failures from 20% to below 0.1%](<https://devfeed.tech/articles/a-conversation-with-stackai-s-cto-how-temporal-cut-indexing-failures-from-20-to-below-0-1-87148.md>)

Original publisher: [Read original article](<https://temporal.io/blog/how-stackai-used-temporal-cut-indexing-failures-from-20-percent-to-below-1-percent>)

Author: Hien Phan

Published: 2026-10-14T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>)

Tags: [caching](<https://devfeed.tech/tags/caching.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [error-handling](<https://devfeed.tech/tags/error-handling.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [stackai](<https://devfeed.tech/tags/stackai.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [temporal-voices](<https://devfeed.tech/tags/temporal-voices.md>)

### AI overview

StackAI migrated its document indexing pipeline incrementally from Celery to Temporal, adding durable stages, targeted retries, parser fallbacks, caching, and separate scaling for parsing workers. The team reports indexing errors falling from approximately 20% to below 0.1%. Temporal and accompanying pipeline optimizations together reduced parsing costs to roughly one-tenth of their previous level.

### Source excerpt

A conversation with Frank Hidalgo, former CTO of StackAI, now part of Asana and Hien Phan: how Temporal cut indexing failures from 20% to below 0.1%.

[Next page](<https://devfeed.tech/sources/temporal-blog.md?cursor=WyIyMDI2LTEwLTE0VDAwOjAwOjAwKzAwOjAwIiwgImRiODE1MTAwLWY2N2UtNDA4Ni1hNmFkLWVmZDQzZjE1YTUzZiJd>)