Replay 2026
| title | author | length |
|---|---|---|
| Hit Replay on Replay 2026 | 02m | |
Brief on Replay 2026 shows Temporal claiming crash proof, reliable, and durable by default and demoing stateful workflows, agents, tools, data in a single… | ||
| How OpenAI Uses Codex to Change How We Build | Dominik Kundel | 47m |
OpenAI reports 80% of employees use Codex weekly and uses it to gather context from Gmail, Slack, Calendar, Linear, Sentry, Figma and Notion so agents can run… | ||
| Opening Keynote | Samar Abbas, Amjad Masad | 56m |
Temporal unveils concrete features: Workflow Streams for real-time, durable LLM and tool output; Standalone Activities as a durable job primitive (public… | ||
| Building Agentic Consumer Products with Temporal | Jeremy Stribling | 32m |
Cursor builds cloud agents that run each job in a dedicated VM per agent and orchestrates them with Temporal Cloud workflows, using worker activities on AWS… | ||
| Temporal, OpenAI, and the Future of Agentic AI | Venkat Venkataramani | 14m |
OpenAI runs a Temporal-backed durable orchestration framework that powers agent workflows, infrastructure control planes, data pipelines, and billing processes… | ||
| Agents: Building Production AI Agents with Temporal | Lam Tran | 25m |
Retool turns its Temporal-based workflow engine into a production AI agent system that runs LLM calls and tool executions as Temporal activities with workflows… | ||
| Path to Temporal GA | Rob Zienert | 44m |
Six-year adoption path turns Temporal from an off-road experiment into a paved-road, funded platform: starts inside Spinnaker, reduced failures to a thousandth… | ||
| From Adoption to Production at Scale | Kshitij Wadhwa | 43m |
OpenAI moves a high‑throughput image pipeline onto Temporal Cloud, routing 1 billion images per week and growing 60x in a year by building a platform layer: an… | ||
| Bridging the CHASM @ Replay 2026 | A Deep Dive Into Temporal's Server's State Machine SDK | Roey Berman, Yichao Yang | 44m |
Temporal’s internal CHASM server-side state-machine SDK provides concrete abstractions — components, fields, archetypes, tasks — and an outbox-style task model… | ||
| How We Reliably Send a Million Messages Per Request | Parth Naagori | 29m |
A bulk messaging system moves from a queue-of-microservices to Temporal workflows, then hits namespace action limits at ~55,000 requests in a minute (≈900 RPS)… | ||
| Supercharging Cloud Orchestration with Temporal Open Source | Vivek Gupta, Joseph Gilbert | 40m |
Capital One replaces choreographed Lambdas with a durable execution platform built on self-hosted Temporal on Fargate, fronted by an NLB, using RDS Postgres +… | ||
| Standalone Activities Announcement @ Replay 2026 | Durable Job Processing with Standalone Activities | Phil Prasek, Dan Davison, Edward Zhu | 37m |
Standalone Activities runs a single durable job without a workflow by creating a server‑persisted activity execution that handles retries, backoff timers… | ||
| How to Leverage Temporal for Agentic Orchestration and Workflows | Anant Agarwal | 38m |
Instacart runs Temporal on self-hosted clusters at ~56 million workflows/day, across 45 namespaces and peaks around 200k actions/sec in a single namespace… | ||
| Free Your Mind, Your App Will Follow | Tom Wheeler | 38m |
A retail order system is rebuilt step‑by‑step on Temporal showing concrete wins: replacing homegrown retry tables, cron jobs, and queues with crash‑proof… | ||
| Announcing New AI Capabilities | Johann Schleier Smith, Ethan Ruhe | 43m |
Temporal ships durable orchestration for agentic apps: a six‑step returns agent that calls LLMs, checks order history, inventory, waits durably for human… | ||
| Powering AI Agents with Temporal and Kgoose | Catherine Zhang | 45m |
Block builds KGoose (Goose as a service) on Temporal with DynamoDB for data and MCP for tools, migrating from sync to async to avoid timeouts and support… | ||
| Meet The Temporal Swift SDK | Franz Busch | 10m |
Temporal Swift SDK is production-ready with a 1.0 release and wraps the Temporal core SDK via a C bridge while letting you bring-your-own gRPC client for mTLS… | ||
| Scaling AV Simulation with Temporal | Jeremy Cook, Matt Tescher | 40m |
NVIDIA runs millions of AV simulations per day on GPUs using a purpose-built TestStudio that uses Temporal for orchestration. The system scales from an initial… | ||
| From Nothing to Everything: One Single Alert to Managing Datacenters | Jeff Ferland | 23m |
Starts from a single Temporal workflow that turns a “GPU fell off PCIe bus” alert into a JIRA ticket and grows into one persistent workflow per server that… | ||
| From Bottlenecks to Self-Service: Workflow-as-a-Service with Temporal Nexus | Zhihao Wang | 44m |
Duolingo turns Temporal Nexus into a company-wide workflow-as-a-service platform: a gateway microservice + JSON-schema portal lets engineers trigger validated… | ||
| CHASM: A High Level Analysis of Temporal's New State Machine SDK | Paul Nordstrom | 39m |
CHASM is a new Temporal programming model that exposes reusable, active application state machines (called cats) — queues, semaphores, maps, bloom filters and… | ||
| Temporal's Director of Eng and Principal Software talk High Availability in Temporal | Liang Mei, Sergey Bykov | 31m |
Claims 99.99% uptime and regional resilience by combining an in-cell architecture with asynchronous replication and managed failover, plus a replication stack… | ||
| Murmur: A Coordinated Flock of Coding Agents, Powered by Temporal | Kayvon Beykpour, Aaron Wasserman | 33m |
Murmur runs a fleet of coding agents where each agent gets a sandboxed VM per agent with a hermetic replica of the dev environment (GCP, microservices… | ||
| Closing Keynote | Maxim Fateev, Preeti Somal, Cornelia Davis | 01h 03m |
Product roadmap and operational wins for 2026 with concrete rollouts: Task Queue Priority & Fairness is live in preview with 20+ customers and lets workflows… | ||
| Running Agents on Async Task Queues While Keeping them Real-Time | Ryan Stevens | 11m |
ZoomInfo moves agent execution off FastAPI web pods onto Temporal task queues, keeping the browser SSE UX by publishing LLM tokens to a Redis token stream with… | ||
| CHASM: Deep Dive into Temporal Server's State Machine SDK | Roey Berman, Yichao Yang | 44m |
CHASM is an internal server-side state-machine SDK that already powers Standalone Activities, Nexus, callbacks, and the scheduler and ships a reusable… | ||
| Beyond the State Machine: Scaling Order Orchestration | Roman Kuskov | 29m |
Booking.com moves its Order Orchestration from AWS Step Functions to Temporal and proves specifics: a 75% cost reduction on a tested workflow, performance… | ||
| Durable, But At What Cost? | Jonathan Grahl | 10m |
Lovable starts using Temporal six months ago and finds opaque billing: only ~60% of cost shows in basic metrics, while activity heartbeats consume ~30% of the… | ||
| Lessons Learned from Building Fast Infra for Agents to Access the Internet | Catherine Jue | 09m |
Open-source stack aims to give AI agents fast, reliable cloud browsers with sub-150ms boot by moving from Docker containers (10–40s cold starts) to Unikraft… | ||
| Lessons learned using Temporal to run Temporal Cloud | Manu Srivastava, Xinyi Chen | 33m |
Temporal Cloud runs its control plane on Temporal, processing about 1.8 billion actions/month, with ~11,000 commits, 30+ contributors and 600 workflow/activity… | ||
| How Affirm Uses Temporal as a Batch Data Plane | Andrew Danks, Alan Xu | 12m |
Affirm replaces fragile Kubernetes pod-operator runs inside Airflow with Temporal as a batch data plane, using an ephemeral worker controller that scales user… | ||
| Streaming Messages from Temporal Workers | Eric Ziegler | 35m |
Architecture sends real-time notifications and streaming LLM tokens from Temporal workflows to users via SSE, using Redis pub/sub for low-latency fan-out… | ||
| Agentic Ambient Active Listening | James Gibbons | 16m |
Abridge runs an ambient clinical listener that ingests 500 ms audio chunks into Kafka, uses Flink to window and transcribe, and drives decision logic in… | ||
| Augmented Data Processing at Massive Scale with Temporal | Michael Bishoff, Aditya Chaturvedi | 16m |
Scale AI faces large intermediary payloads and brittle linear pipelines so it builds a generic run card activity that always reads from and writes to a… | ||
| From Normalizing Complexity to Recognizing the Price | Shabnam Emdadi | 41m |
Most teams normalize Monday morning threads about stuck payouts, manual retries, and broken cleanup jobs and end up building five independent background jobs… | ||
| Temporal at Scale: Lessons in Migration and Security | Ian Yap, David Nicholas | 32m |
A 12-person team coordinates a zero-downtime migration of 300+ namespaces and services from a custom self-hosted Temporal stack to Temporal Cloud, reusing an… | ||
| Orchestrating Data Pipelines at Scale with Temporal | Zainab Merchant, Madhav Sodhani | 41m |
Fivetran runs over 5 million daily syncs on Temporal workflows, migrates from regionally fragmented schedulers to a worker-pool model, and cuts job startup… | ||
| How We Built a Voice Agent with Temporal | Eliot Miller | 36m |
Built a live phone agent that reuses a text-based Temporal agent, adds Deepgram STT and Cartesia/ElevenLabs TTS, and speeds LLMs with Grok and Cerebras plus… | ||
| Breaking Changes Without Breaking Things | Satnam Dhanoa, Hassan Nawaz | 40m |
Alaska Airlines moves from rolling Kubernetes deploys to rainbow deployments on Azure Container Apps, packaging services and Temporal workers into a single… | ||
| We Built 2,000 Custom Electronic Badges for Our Developer Conference, Replay (Here's How) | Shy Ruparel, Melanie Warrick | 35m |
Temporal builds and ships 2,000 hackable conference badges with custom PCB, joystick, monochrome display, IR multiplayer games, Doom, a MicroPython Tamagotchi… | ||
| Reliable Migration Of 4+ Million CPU Cores of Compute to Kubernetes | Ankit Rajesh Methwani, Puneeth Reddy Poddutoori | 20m |
LinkedIn uses Temporal to automate a region-by-region migration of 2,300+ stateless services, successfully moving 3+ million CPU cores, 10 PB memory and ~3,000… | ||
| A Conversation with Platform Teams @ Replay 2026: Scaling Temporal Across the Enterprise | Jack Burns, Jonathan Jaegerman, Slava Vitebski, Alban Preldakaj, Cornelia Davis | 43m |
Platform teams describe how Temporal moves from prototype to enterprise: successful rollouts use Temporal Cloud only with automated namespace and Okta… | ||
| Engineering AI Applications: A Conversation with AI Leaders | Dan Kador, Ertan Dogrultan, Reggie Gomez, Ethan Ruhe | 33m |
Panelists describe running AI in production for healthcare, coding platforms, and finance: 250 enterprise health systems, a coding agent that runs long-lived… | ||
| Announcing Priority & Fairness for Temporal | David Reiss, Rahul Kekre | 44m |
Temporal ships Task Queue Priority & Fairness that reorders async matches so critical work runs first and prevents noisy tenants from starving others. Priority… | ||
| Smarter Workflows, Leaner Costs: Inside Yum! Brands' Temporal Evolution | Yeshwanth Kumar Pentakota | 24m |
Yum! Brands runs ~40 million Temporal workflows per month (about a billion actions) and reduces cloud spend by using Temporal Workflow Update to eliminate a… | ||
| Building Privilege Access on Temporal | Hugh Neale | 05m |
Thand is an open-source distributed just-in-time privileged access management system built on Temporal that stores all state inside workflows so ephemeral… | ||
| Building the Next Generation on Temporal | Alban Preldakaj | 33m |
Apollo standardizes on Temporal to run durable, auditable workflows inside Azure with workers on Kubernetes, Terraform modules for IAC, RBAC and audit logging… | ||
| When Money Moves: Durable Execution for Wealth Management Transfers | Suresh Nageswaran | 42m |
Reimagines ACATS transfers by wiring Temporal workflows for durable execution, a control plane that runs LLM-based triage, and an XTDB-backed bitemporality… | ||
| Taming AI Agents With Output.Ai | Daniel Lopes | 45m |
Argues that agent reliability is a distributed systems problem and shows an open source TypeScript framework built on Temporal called Output.ai that teams… | ||
| How Temporal Powers Salesforce's AI-Driven DDoS Protection | Simone Mainardi, Prabhat Singh, Gagan Shivananda Bharathi Gangothri | 37m |
Salesforce builds an AI-driven DDoS system on Temporal that delivers 10× faster first mitigation, 15× faster analysis and 3× faster end-to-end resolution… | ||
| Confidently Shipping with Temporal | Anastasiya Melentyeva, Hudson Southey-Gordon | 18m |
Xero describes a concrete pipeline for safe Temporal adoption: automated namespace provisioning via Terraform Temporal Cloud provider that enforces retention… | ||
| Being Creative: Tales from the Trenches | James Watkins | 31m |
Covers real-world Temporal misuses and fixes with concrete numbers and knobs: explains why replay is the baseline (not a slow path), shows how huge namespaces… | ||
| Resource Fairness: Implementing (and Deprecating) a Lease Broker | Andrew Wells | 41m |
Built a Temporal-based semaphore called lease broker workflow to enforce per-client concurrency for OCR activities, using signals and continue-as-new; it works… | ||
| 100 Temporal Mistakes and How to Avoid Them | Jacob LeGrone | 26m |
Practical checklist of production mistakes and fixes for Temporal: use schedule to close timeout as the real bound and prefer unlimited retries with… | ||
| Announcing Major Worker Improvements @ Replay 2026 | W/ Temporal Software Engineers | Carly de Frondeville, Stefan Richter, Sagar Randive | 41m |
Announces that Temporal now routes running workflows to immutable worker deployment versions, letting new workflows start on a marked current version while… | ||
| nothing matches | ||