ML Workflow Orchestration

4/30/2026

This post announces a significant strategic investment in AI at Temporal, including the acquisition of two teams (Chkk and Adviser Labs) with deep expertise in distributed systems, AI research, and building production systems on Temporal. It outlines five key initiatives for this investment: winning agentic AI use cases, enhancing AI-powered developer experiences, leveraging Temporal Nexus for agent communication, forming strategic partnerships with AI platforms (OpenAI, Google ADK, Vercel, Braintrust), and developing internal AI agents. The post emphasizes that Durable Execution is foundational for modern AI and highlights the reliability challenges associated with long-running AI agents. It also mentions an upcoming event, Replay, with multiple talks focusing on AI.

4/20/2026

This post details the integration of Temporal with Google's Agent Development Kit (ADK). The integration allows ADK agents to leverage Temporal's durable execution by running each LLM call and tool call as a separate Temporal Activity. This provides granular retries, improved visibility in the Temporal UI, and more robust failure handling compared to running the entire agent within a single Activity. Key technical contributions include the `TemporalModel` wrapper for rerouting LLM calls to Activities, the `activity_tool` helper for defining tools as Activities, and modifications to ADK's time and UUID functions to ensure determinism within Temporal Workflows. The post also discusses the handling of MCP tools and the serialization of context objects.

9/29/2025

This post details Grid Dynamics' migration of a deep research agent from a LangGraph/Redis/Kafka architecture to Temporal. Key technical contributions include: demonstrating how Temporal's durable execution simplifies state management by making state an integral part of the workflow rather than a separate, fragile object; showcasing the elimination of thousands of lines of custom retry and error handling code by leveraging Temporal's declarative RetryPolicy configurations for Activities; and highlighting how Temporal's event history automatically and durably persists state updates, reducing the need for manual state management and debugging complex issues related to caching and stale state.

9/3/2025

This post announces the acquisition of Crystal DBA, which brings deep systems and AI expertise to Temporal. It also details several partnerships and integrations that enhance Temporal's capabilities for AI workflows, including OpenAI Agents SDK, MongoDB, Pydantic, and Grid Dynamics. The post emphasizes Temporal's role in building resilient and scalable AI agents and agentic workflows.

8/27/2025

This post details how Temporal can be used to build durable multi-agentic AI systems. It introduces two key patterns: Agent Routing and Task Delegation. A concrete example is provided for a detection and repair system for order management, demonstrating how to use Temporal Workflows and Activities to orchestrate AI agents for analysis, plan creation, and plan execution. The post also covers integrating conversational agents via the Model Context Protocol (MCP) and outlines the common steps for building agentic applications.

6/26/2025

This post provides a practical guide to building production-ready agentic AI systems, building upon the concept that agentic systems are distributed systems in disguise. It defines key terms like AI, Goal, Tool, User, Agent, and Agentic System, and introduces advanced concepts like Multi-Agent systems and Agents as Tools. The post illustrates the agentic flow (Interaction, Decision, Action) orchestrated by Temporal Workflows, and details the challenges in building these systems for production, such as unreliability of components, non-determinism of AI, complexity, and security. It strongly advocates for Temporal's Durable Execution as the solution for building stateful, fault-tolerant, and observable agentic systems, and provides a simplified code example of an agentic workflow framework using Temporal Signals, Activities, and workflow logic for planning and executing tools, including user interaction for confirmation and input gathering.

6/4/2025

This post introduces a mental model for building agentic AI applications, focusing on the event loop, LLM-tool interaction, and durable execution of these agents. It details the components of an agent (prompt, tools, execution mechanism, LLM input update) and emphasizes the need for a durable event loop and durable invocation of LLMs and tools. The post also discusses the language interfaces for LLMs and tools, and how to prepare for tool invocation by gathering and structuring inputs, potentially involving user interaction and LLM-driven validation. Finally, it outlines the components of LLM input for subsequent turns, including the goal, tools, example conversation, context instructions, and conversation history, highlighting the role of prompt engineering in managing these elements for effective agentic application development.

2/25/2025

This post details how Temporal can be used to build agentic AI workflows, addressing limitations of current frameworks in durability, scalability, and integration. It highlights Temporal's strengths in developer velocity, observability, scheduled execution, durable and resilient execution (handling LLM probabilistic nature and real-world failures), long-running and stateful capabilities, human-in-the-loop support, flexible integration with any LLM/database/service, and centralized orchestration. It provides a typical workflow example and emphasizes Temporal's role as a robust foundation for evolving AI agents.

12/19/2024

This post details how a technology company is using Temporal to build an extensible platform for managing long-running GPU resource management workflows. The platform was built in three months and leverages child workflows. The team is migrating parts of the platform to use Temporal Nexus for improved extensibility and integration. They also developed an automation pool for smaller, ad-hoc tasks. The post highlights the benefits of Temporal Cloud over self-hosting for managing infrastructure overhead and enabling developers to focus on application logic.

11/22/2024

This post details how Julep AI uses Temporal to build multi-step AI workflows, enabling AI agents to remember past interactions and execute complex tasks. It highlights use cases like automating video editing, personalizing content, and securing identity verification. The post emphasizes Temporal's role in managing tens of thousands of tasks across complex, long-running AI workflows, ensuring reliability through automatic retries and providing observability via its UI.

11/19/2024

This post details 9 real-world generative AI use cases powered by Temporal, including video content processing and translation, conversational AI and call center transcription, synthetic data generation and processing, AI platforms for predictive analytics and customer insights, market intelligence and cryptocurrency data enrichment, AI-powered HR workflows, AI infrastructure and resource optimization, state tracking in generative AI workflows, and research and applied AI workflow orchestration. It emphasizes Temporal's role in managing complexity, statefulness, and reliability for these long-running AI workflows. The post also outlines the benefits of Temporal for generative AI, such as reliable performance, cost savings, and faster development, and its suitability for handling sync/async processes, state tracking, and scalability.

11/4/2024

This post details how The Washington Post's Arc XP division used Temporal to revamp their media workflows, specifically for an automated thumbnail selection system. By leveraging Temporal's durable execution and multi-language support, they achieved a 600% runtime improvement, reducing processing time from 80 seconds per minute of video to about 10 seconds for a 4-5 minute video. This was accomplished by distributing workloads across AWS instances. The Replay feature was highlighted as a key benefit for support staff in debugging and incident management.

6/18/2024

This post details the integration of Temporal with Amazon Bedrock to build a resilient AI chatbot. It demonstrates how Temporal Workflows can manage the stateless nature of LLMs by storing conversation history, handle long-running sessions without consuming excessive resources, and provide a unified view of execution history for debugging. The post provides code examples using the Temporal Python SDK for a basic workflow that invokes Bedrock activities, highlighting Temporal's guarantees for reliable execution even in the face of simulated failures.

4/22/2024

This post details how Temporal is applied to AI/ML workflows, focusing on two main patterns: orchestration of end-to-end AI/ML processes (e.g., Descript's video enhancement and voice generation) and management of AI/ML data flows (e.g., Neosync's data automation and anonymization). It highlights the use of Workflows and Activities for defining sequences of operations and handling unreliable tasks, with examples of Python code for training, testing, and deploying models. The post also discusses cost savings through selective use of GPU resources via Task Queues and the ability to orchestrate multiple AI pipelines.

3/26/2024

This post details nine ways Temporal can be used in AI workflows, expanding on the existing ML Workflow Orchestration feature. It elaborates on specific applications like orchestrating AI pipelines, scalable model training with retries and checkpoints, distributed data processing with state management, automating continuous learning and model deployment, managing experimentation and versioning, efficient GPU utilization via worker slot limiting, scaling AI operations, enabling event-driven and asynchronous execution, and providing observability and debugging capabilities for complex AI processes. It also provides links to Temporal's getting started guides and sample repositories for various SDKs.