--- title: How to Build Proactive, Always-On Agents with the... description: Many proactive AI agents are built on a simple mechanism: cron-scheduled runs. More than 70% of Managed Deep Agent runs on LangSmith come from scheduled runs... canonical: https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents | daily.dev og:description: Many proactive AI agents are built on a simple mechanism: cron-scheduled runs. More than 70% of Managed Deep Agent runs on LangSmith come from scheduled runs... og:url: https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx og:image: https://api.daily.dev/og/posts/vkABYWUsX.png og:image:alt: How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents **[LangChain](https://daily.dev/sources/langchain)** · 6 min read · 1 upvotes · 0 comments ## Summary Many proactive AI agents are built on a simple mechanism: cron-scheduled runs. More than 70% of Managed Deep Agent runs on LangSmith come from scheduled runs rather than direct human messages. Crons enable memory consolidation ('dreaming'), proactive suggestions, smart triage of noisy channels like Slack or email, follow-up reminders, and multi-agent orchestration. Managed Deep Agents ships a built-in cron server plus a Schedules SDK, letting developers define static schedules in a `schedules/` file or let agents create dynamic schedules at runtime via tools like `set_schedule`, `list_schedules`, and `check_in_later`. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I create a dynamic schedule that lets an agent set its own reminders in LangChain's Managed Deep Agents? Wrap the Schedules SDK in a tool using the `@tool` decorator and call `runtime.schedules.create(owner={"type": "user"}, cron=cron, prompt=prompt)` inside an async function. This lets an agent create recurring tasks at runtime rather than only running schedules defined statically in code. Companion tools `list_schedules` and `delete_schedule` let the agent manage existing schedules the same way. _Building agents that manage their own reminders? Track SDK patterns like this one on daily.dev._ ### What percentage of Managed Deep Agent runs on LangSmith come from scheduled runs instead of user messages? More than 70% of Managed Deep Agent runs on LangSmith originate from scheduled runs rather than from a human typing a message. This reflects a shift toward proactive, always-on agents that initiate communication on their own cadence rather than waiting to be prompted interactively. _Developers weighing proactive agent design follow adoption data like this on daily.dev._ ### How do I set a fixed daily schedule for an AI agent task in Managed Deep Agents? Define a file in the `schedules/` directory using `define_schedule` from `managed_deepagents`, passing a cron expression, timezone, and prompt. For example, `cron="0 8 * * 1-5"` with `timezone="America/Los_Angeles"` runs a prompt like sending a sales KPI readout every weekday morning at 8am Pacific. _Teams scheduling recurring agent tasks can keep up with SDK changes via daily.dev._ ## Similar posts on daily.dev - [Building effective agent automations](https://daily.dev/posts/building-effective-agent-automations-zspzo7j9y) · ClaudeDevs · 1 upvotes · 0 comments - [How to Build and Schedule Local AI Assistants for Daily Tasks](https://daily.dev/posts/how-to-build-and-schedule-local-ai-assistants-for-daily-tasks-hgfbk6cu7) · freeCodeCamp · 3 upvotes · 0 comments - [The agent runs while you sleep. Design for that.](https://daily.dev/posts/the-agent-runs-while-you-sleep-design-for-that--xckrhtslo) · Medium · 1 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain) [View this post on daily.dev](https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents","url":"https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx"},"datePublished":"2026-10-28T16:21:57.373Z","dateModified":"2026-10-28T16:34:50.712Z","description":"Many proactive AI agents are built on a simple mechanism: cron-scheduled runs. More than 70% of Managed Deep Agent runs on LangSmith come from scheduled runs...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e3e9b0f7ccf809a10a9921b7cfb12d29?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e3e9b0f7ccf809a10a9921b7cfb12d29?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,ai-agents,langchain","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-to-build-proactive-always-on-agents-with-the-schedules-sdk-in-managed-deep-agents-vkabywusx#faq","mainEntity":[{"@type":"Question","name":"How do I create a dynamic schedule that lets an agent set its own reminders in LangChain's Managed Deep Agents?","acceptedAnswer":{"@type":"Answer","text":"Wrap the Schedules SDK in a tool using the `@tool` decorator and call `runtime.schedules.create(owner={\"type\": \"user\"}, cron=cron, prompt=prompt)` inside an async function. This lets an agent create recurring tasks at runtime rather than only running schedules defined statically in code. Companion tools `list_schedules` and `delete_schedule` let the agent manage existing schedules the same way. Building agents that manage their own reminders? Track SDK patterns like this one on daily.dev."}},{"@type":"Question","name":"What percentage of Managed Deep Agent runs on LangSmith come from scheduled runs instead of user messages?","acceptedAnswer":{"@type":"Answer","text":"More than 70% of Managed Deep Agent runs on LangSmith originate from scheduled runs rather than from a human typing a message. This reflects a shift toward proactive, always-on agents that initiate communication on their own cadence rather than waiting to be prompted interactively. Developers weighing proactive agent design follow adoption data like this on daily.dev."}},{"@type":"Question","name":"How do I set a fixed daily schedule for an AI agent task in Managed Deep Agents?","acceptedAnswer":{"@type":"Answer","text":"Define a file in the `schedules/` directory using `define_schedule` from `managed_deepagents`, passing a cron expression, timezone, and prompt. For example, `cron=\"0 8 * * 1-5\"` with `timezone=\"America/Los_Angeles\"` runs a prompt like sending a sales KPI readout every weekday morning at 8am Pacific. Teams scheduling recurring agent tasks can keep up with SDK changes via daily.dev."}}]} ```