# Put your agent on a schedule Source: https://www.hyperagent.com/docs/guides/put-your-agent-on-a-schedule > For AI agents: the documentation index is at https://www.hyperagent.com/llms.txt and the complete documentation in one file at https://www.hyperagent.com/llms-full.txt. Any docs page is also served as Markdown by appending `.md` to its URL. Have your agent repeat a job at the right time and deliver the result where you need it. Schedule a job your agent already knows how to do. Your agent can prepare a brief, check for updates, or refresh a report regularly, then deliver the result where you need it. Start with **a saved agent and a job you’ve reviewed together**. A schedule repeats one of your agent’s jobs; your agent can keep helping with other responsibilities too. ## What you’ll learn [#what-youll-learn] * **Describe the routine** Tell Hyperagent what to run and when. * **Give each run the right starting point** Include the request, sources, and skill to use. * **Choose access and delivery** Decide what your agent can change and where the result arrives. * **Test before relying on it** Check the work, delivery, and next scheduled time. Deliver briefs for the day’s calls every morning Example A customer-relationship agent helps with meetings, follow-ups, and renewals. One useful routine is preparing a webpage with a brief for each customer call that day. When to start Every weekday at 7 a.m., in the timezone you choose. What to do Read the Daily Briefing skill, check today’s calendar and customer records, and prepare the briefs. What to deliver A webpage with the background, risks, and questions for each call, with source links and gaps clearly marked. ## Set up and test the schedule [#set-up-and-test-the-schedule] ### Pick a job you want to repeat [#pick-a-job-you-want-to-repeat] Choose a job your agent already knows how to do and that you want repeated. Prepare for customer calls Examples Check your calendar and customer records, then deliver a brief for the day’s calls. Runs Every weekday morning Delivers to Email Review new inquiries Examples Summarize new customer inquiries and flag any that need a reply. Runs Every hour during the workday Delivers to Thread Track upcoming renewals Examples Review contracts renewing in the next 30 days and list accounts that need a follow-up. Runs Every Monday Delivers to Email Summarize campaign results Examples Collect the week’s campaign metrics and report what changed and what to investigate. Runs Every Friday Delivers to Slack Check project progress Examples Review your project tracker and flag overdue tasks or blocked work. Runs Every afternoon Delivers to Room For each scheduled job, decide: Time When and how often it should run. Job What your agent should do. Output What you want back, such as a brief, report, or list of findings. Delivery Where the result should arrive and whether you also want a completion notification. Work through a real task with Hyperagent first. If you need a saved agent, [turn that thread into an agent](https://www.hyperagent.com/docs/guides/turn-a-thread-into-an-agent). If you’re still repeating the same corrections, [teach your agent how you work](https://www.hyperagent.com/docs/guides/teach-your-agent-how-you-work) before scheduling the job. ### Set up a schedule [#set-up-a-schedule] * **Find your agent** Open **Agents** in the sidebar and select the agent you want to schedule. * **Open its schedules** Select **Configure**, then **Intake**. Find the **Scheduled** section. * **Start a schedule** Choose **Create schedule**. If the agent already has schedules, choose **Add** beneath the list. Yes. Open a conversation with your saved agent and describe the job, timing, timezone, thread choice, and write permissions. Ask explicitly for a proposal without saving or enabling it if you want to review first. Propose a weekday 7 a.m. schedule in America/New\_York for your customer-call briefs. Use the Daily Briefing skill, today’s calendar, and the customer records you can access. Create a webpage and flag missing information. Use a new thread each run, keep integration writes read-only, and leave the schedule paused. Show me the proposal without saving or enabling it. Review and edit the proposal, then select **Update agent** to save it. New schedules are active by default unless the proposal explicitly keeps them paused. Some recurring schedules require an additional cost confirmation before saving. Chat can also save eligible updates immediately when your consent settings allow it, so check whether the response is a proposal or a saved confirmation. After saving, open the schedule’s details to check its status and timing, test with **Run now**, and resume when ready. ### Describe the job and when to run it [#describe-the-job-and-when-to-run-it] * **Describe the routine** In **Describe your schedule**, say what your agent should do and when it should run. * **Generate a draft** Select **Generate**. Hyperagent drafts the timing and rewrites **Message**; it does not save the schedule. Review its wording before saving. Every weekday at 7 a.m., prepare a brief for today’s customer calls using the Daily Briefing skill. Use today’s calendar and the relevant customer records. Create a webpage with risks and questions first, and link to the sources. If there are no customer calls, say so. Flag missing information instead of guessing. **Check the timing before continuing:** * **Repeat** Does the schedule run on the days and at the frequency you want? * **Timezone** Select the timezone explicitly. It initially follows your browser’s timezone; mentioning another timezone only in the request is not enough. The scheduled time is when your agent starts, not when the result will be ready. **Review the schedule’s Message.** This is the request your agent receives each time the schedule starts a run. It should make sense without the conversation where you first worked out the job. The job Is it clear what your agent should produce or check? The method Does it name the saved skill to read, without copying the whole procedure? The sources Can your agent find the current information needed for each run? Missing information Does the request explain what to flag or stop for instead of guessing? ```markdown title="Schedule message" Prepare a brief for today’s customer calls. Read the Daily Briefing skill and follow its method. Use today’s calendar and the customer records you can access. Create a webpage with a section for each customer call. Flag missing information instead of guessing. If there are no customer calls today, say so. Do not contact customers or change their records. ``` Use your own skill and sources. Make sure the skill is saved and available to this agent, and that the required connections and source access are enabled. For the call-brief example, webpage generation must also be available. Naming them in **Message** does not grant access. If the request needs more work, ask your agent to help draft it in the thread, then copy the reviewed version into **Message**. ### Choose whether each run starts fresh [#choose-whether-each-run-starts-fresh] Expand **Advanced** and use **Thread** to choose how scheduled runs use a conversation. Use this when each occurrence should stand on its own, such as a daily brief or weekly report. Your agent uses its saved setup with the new request, without the previous thread’s conversation. Use this when the next run should build on work in the same thread. Select the thread to continue. For the daily-brief example, choose **New thread each run** so yesterday’s customer details do not become the conversation history for today’s brief. See [Thread context](https://www.hyperagent.com/docs/concepts/threads/loading-context) for what your agent brings into a fresh thread. ### Decide what your agent can change [#decide-what-your-agent-can-change] Under **Integration writes**, choose **Read-only**, **Ask**, or **Allow**. Gathering information and preparing a result usually does not require changing records in a connected service. This setting does not give the agent access it otherwise lacks. Your agent can read connected services without changing their records. Use this for reporting and research that does not need external updates. A change in a connected app pauses the run for your approval. Review the request in the run’s thread or Inbox. Approving resumes that action; denying it or letting the request expire leaves it undone. Your agent can use its permitted write access without waiting for you. Review the actions the job needs before choosing this setting. For the call-brief example, **Read-only** is enough. See [scheduled writes and approvals](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#integration-writes-and-approvals) for the detailed behavior. ### Choose where the result arrives [#choose-where-the-result-arrives] Choose a delivery destination, or keep the result in the run’s thread. Email and Slack DM deliver to you, the schedule owner. Slack channel delivery needs a configured channel. Telegram delivery requires **Continue existing** with a Telegram-linked thread. Check that the destination is available. * **Delivery** Where a copy of the final report goes. Choosing a destination does not grant general write access to that service. * **Notify me when a run completes** Under **Advanced**, turn this on if you also want a completion notification. Browser and mobile notifications depend on your notification settings. Report delivery is separate from permission to change connected records. You can keep the job read-only and still have its finished result delivered to an available destination. Select **Save**, then open the saved schedule and check its status and **Next** time. New schedules are active by default. Pause yours if you want to finish testing before recurring runs begin. ### Run it now and check the result [#run-it-now-and-check-the-result] Save any changes, open the saved schedule, select **Run now**, then confirm **Run Now**. This starts a real run with the schedule’s permissions and delivery settings, so you can check the whole process before relying on it regularly. * **Sources** Did your agent use current information and the right records? * **Work** Did your agent follow the skill and identify anything missing? * **Delivery** Can you open the result where you expected it? * **Timing** Does the next scheduled run match what you intended? **Run Now** starts an immediate run without moving the next scheduled time. The schedule’s write permissions, delivery settings, and completion notifications still apply. If something needs changing, ask your agent to help improve the request or skill, review and save those changes, then test again. A completed run is only useful if the result meets your needs. If you paused the schedule for testing, resume it when the work and delivery are correct. ## Keep track of scheduled work [#keep-track-of-scheduled-work] Select the saved schedule to open its details. **Run history** appears below **Message**; open a run’s thread to inspect the work, read the result, or investigate a problem. Update or pause the schedule when the job changes. ## FAQ [#faq] Not when you choose **New thread each run**. Save reusable procedures in skills and make sure your agent can access them. Put the job and current-source instructions in the schedule’s Message. Choose **Continue existing** only when the run should continue work in that particular thread. Tell your agent what an empty result means and what to do. For example, no customer calls today should be reported differently from failing to read the calendar. For monitoring jobs, turn on **Only when something needs attention**. Each occurrence still runs and uses model capacity, but an all-clear result stays quiet, including its completion notification. This mode uses a lighter check model unless you select another. See [quiet delivery](https://www.hyperagent.com/docs/concepts/agents/invocations/schedules#choose-how-scheduled-runs-work) for more detail. Open the run’s thread and check the schedule for a delivery warning. Review the destination and connection access. Finishing the job and delivering its result are separate outcomes; test delivery again after fixing access. Yes. Expand **Advanced** and choose the schedule’s **Model** from the compatible models available to you. New threads keep the selected model; a continued thread uses the override for the scheduled run only. In attention-only mode, the selection controls the check model. Test the result with the selected model before relying on it for the job. See [Spend less on recurring work](https://www.hyperagent.com/docs/guides/save-on-recurring-work) for more ways to reduce recurring costs. ## What’s next [#whats-next] Improve the steps and checks your agent follows on each run. Choose models and reusable scripts that fit the job.