Temporal Technologies

Well, this is fun: Temporal just placed number 1 (!) on the GeekWire 200. 🎉 Turns out keeping AI agents running when things get messy is a pretty big deal. We’re proud to be building that foundation from Bellevue (with amazing teammates all over the world). See the list: https://lnkd.in/dYHjrnJA

Temporal’s Rust SDK is now generally available. Rust developers can now write Workflows and Activities, run Workers on Tokio, and connect to Temporal Cloud or a self-hosted Temporal Service through native Rust APIs. Temporal records Workflow progress so execution can continue after a Worker stops. Running Workflows can wait on durable timers, receive Signals and Updates, and answer Queries. The SDK also includes Child Workflows, Continue-As-New, retries, cancellation, and timeouts. Workflow state lives in Rust structs. Workflows and Activities are async functions. Procedural macros define them, and typed method references let Rust check inputs and results. Quickstart: https://lnkd.in/dG-YDGQb API documentation: https://lnkd.in/d2Xu8NU8 GitHub: https://lnkd.in/dNANDHZb Try it and share your feedback in #rust-sdk in the Temporal Community Slack: https://lnkd.in/d3hGBYWy

Experts from Oso have joined Temporal to accelerate our work on AI agent security. Oso has deep experience building permissions for enterprise applications. That experience applies to a question every company is now asking: when an agent moves money, changes a record, or calls another agent, what is it allowed to do, and on whose behalf? Durable Execution already preserves application state and execution history, including approvals and rejections, through failures and retries. That gives developers a foundation for guardrails. The experts joining us will help advance more precise authorization within it, covering identity, access, and policy enforcement as agents call tools, act on business-critical data, and coordinate work across systems. The handoffs are where this matters most. As agents orchestrate work for one another, access decisions have to hold at every step, even when a system crashes and retries. We're working to carry the identity behind each agent's request across those connections, so every service can apply its own access policies. Temporal already connects applications across teams at scale. At Replay 2026, Netflix shared that more than 150 teams there use Temporal across over 500 namespaces, processing more than 7 billion actions each month. AI safety does not stop at the model. It extends into the applications where agents act. We're helping developers put agents to work with the right access and guardrails their company controls. 🎉 Welcome to the Temporal team, Graham Neray,  Nicholas Kucharski, and Gabe Jackson! Read more: https://lnkd.in/dvAgkWuz

Will we see you at AWS re:Invent?

Serverless Workers for Google Cloud Run are now in public preview. Run your Temporal Workflows and Activities on Cloud Run Worker Pools and let Temporal handle the scaling. Based on workflow volume, Temporal automatically scales your Workers up as work arrives and scales to zero when appropriate. Get started: https://lnkd.in/dqqRecJh

AI models are becoming commoditized, and startups are feeling the heat. So where does the real moat live? I look forward to working through this question at SF Tech Week with Google for Startups on October 7th. Join me, Sarah Wang, and Kathryn Van Nuys to see us talk it through live.

"Temporal is the durable execution layer under a large part of Coinbase. Trading workflows, payments and payouts, settlement, regulatory flows such as GDPR deletion, travel rule checks and KYC refresh, and internal platform work such as ETL, backfills, ML-driven notifications and infrastructure provisioning all run on it. We migrated more than 300 namespaces across more than 300 services off a custom, self-hosted Temporal deployment and onto Temporal Cloud. The custom self-hosted stack is retired. The workload mix ran from workflows finishing in seconds to workflows that stay open for days, and traffic was often spiky rather than steady." Big thanks to Ian Y. at Coinbase for the detailed write-up: https://lnkd.in/dAjiSt5S

Mark Mandel, Francesc Campoy, and Melanie Warrick co-hosted the Google Cloud Platform Podcast. Their first episode together, in 2017, started over lunch and asked a simple question: What's AI? Nine years later, they're back on Vibe Check to look at what they thought then, what it is now, and what changed. They're also bringing back Quick, Draw! and handing the original doodles to today's models to see where they've come a long way and where they still fall short.

We know, we *know.* You're wondering when and where you can hang out with us over the next few weeks. Here are those times and places and links: 𝗩𝗶𝗯𝗲 𝗖𝗵𝗲𝗰𝗸: 𝗪𝗵𝗮𝘁'𝘀 𝗔𝗜? 𝟵 𝗬𝗲𝗮𝗿𝘀 𝗟𝗮𝘁𝗲𝗿 with Melanie Warrick and Francesc Campoy Remote | October 7 https://luma.com/bdpkujyb 𝗗𝘂𝗿𝗮𝗯𝗹𝗲 𝗔𝗜 𝗠𝗲𝗲𝘁𝘂𝗽 with speakers from Modal London | October 15 https://luma.com/1wmrl3nz 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗗𝘂𝗿𝗮𝗯𝗹𝗲 𝗠𝗶𝘀𝘀𝗶𝗼𝗻 𝗖𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗲𝘀 with Shubham Londhe and Automation Anywhere India | October 15 https://luma.com/user/aapf 𝗙𝗶𝗹𝗶𝗽𝗶𝗻𝗼𝘀 𝗶𝗻 𝗔𝗜 with Melissa Herrera San Francisco | October 19 https://luma.com/il2mn1sa 𝗗𝘂𝗿𝗮𝗯𝗹𝗲 𝗔𝗜 𝗠𝗲𝗲𝘁𝘂𝗽 with KERNEL and Oodle AI San Francisco | October 21 https://lnkd.in/dQpkbh3k 🍕🍕🍕 For more events, keep an eye on our Luma calendar: https://lnkd.in/gfzT_FnH

Heading to MongoDB.local NYC tomorrow? Catch our CTO, Maxim Fateev, after the opening keynote on a panel discussion with OpenRouter and Cognition on what it takes to run AI agents reliably in production. And, hey: visit the Temporal booth to meet the team and participate in demos! See the full agenda: https://lnkd.in/dz-xnC6E