# Chapter 3 on today's products (/appendices/todays-products/the-10-80-10-operating-rhythm)

---
type: Document
title: "Chapter 3 on today's products"
description: "The scheduled-task settings of Claude, ChatGPT and two open-source tools, plan by plan, behind lesson 3.7, each with its sources and the date it was checked."
status: stable
order: 905.03
ksor:
  owner: team:panaversity
  audience: [ public ]
  approval:
    by: process:panaversity
    at: 2026-11-20T22:26:36Z
chapter: "Today's products"
part: Back
expert_status: required
concepts: []
last_verified: 2026-10-23
sources:
  - id: anthropic-scheduled-tasks
    title: "Schedule recurring tasks in Claude Cowork (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork
  - id: anthropic-scheduled-tasks-local
    title: "Schedule recurring tasks in Claude Cowork, where a task runs (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork
  - id: anthropic-scheduled-tasks-plans
    title: "Schedule recurring tasks in Claude Cowork, the plans that have them (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork
  - id: anthropic-cowork-surfaces
    title: "Use Claude Cowork on web, desktop, and mobile (Claude Help Center, updated 17 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/15520349-use-claude-cowork-on-web-desktop-and-mobile
  - id: anthropic-cowork-safely
    title: "Use Claude Cowork safely (Claude Help Center, updated 16 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/13364135-use-claude-cowork-safely
  - id: openai-scheduled-tasks
    title: "Scheduled tasks in ChatGPT (OpenAI Help Center, verified 2026-11-21)"
    resource: https://help.openai.com/en/articles/10291617-scheduled-tasks-in-chatgpt
  - id: openclaw-automations
    title: "Automations (OpenClaw documentation, verified 2026-10-23)"
    resource: https://docs.openclaw.ai/automation/cron-jobs
  - id: omnara-cron-trigger
    title: "Create a cron trigger (Omnara API reference, verified 2026-10-23)"
    resource: https://docs.omnara.com/api-reference/endpoints/configs-and-profiles/create-cron-trigger
  - id: omnara-permissions
    title: "Tool permissions (Omnara documentation, verified 2026-10-23)"
    resource: https://docs.omnara.com/tools/permissions
  - id: omnara-integrations
    title: "Integrations (Omnara documentation, verified 2026-10-23)"
    resource: https://docs.omnara.com/integrations/overview
  - id: openclaw-sandbox
    title: "Sandboxing: modes, scope and backend (OpenClaw documentation, verified 2026-10-23)"
    resource: https://docs.openclaw.ai/gateway/sandboxing/modes-scope-and-backend
  - id: omnara
    title: "Omnara README (Omnara, GitHub, Apache 2.0, verified 2026-10-23)"
    resource: https://github.com/omnara-ai/omnara/blob/main/README.md
  - id: openclaw-dedicated-machine
    title: "Secrets and storage (OpenClaw documentation, verified 2026-10-23)"
    resource: https://docs.openclaw.ai/gateway/security/secrets-and-storage
  - id: openclaw-exposure
    title: "Exposure runbook (OpenClaw documentation, verified 2026-10-23)"
    resource: https://docs.openclaw.ai/gateway/security/exposure-runbook
generated:
  at: 2026-11-20T22:26:36Z
  by: process:panaversity
trust_tier: unverified
build_id: sha256:479cf62a84fc89d3e00a175f36b0afa3eac965ca184492297d418b562d4e51c3
dirty: true
ksor_version: 0.0.60
---

This page backs [3.7](../../ai-worker-paradigm/the-10-80-10-operating-rhythm/both-ai-vendors.md), on how today's tools support the rhythm in a scheduled task. The lesson teaches the differences that change how you set a task up. This page holds each product's own settings, with their sources and the dates they were checked.

Products change often. Check the date on each box before you rely on it.

> **Anthropic, as verified 18 November 2026.** **Scheduled tasks** are on all paid plans: Pro, Max, Ultra, Team and Enterprise.[^anthropic-scheduled-tasks-plans] You set one up on the Scheduled page. In the new Claude experience, you can also describe it in any conversation and confirm. Claude saves your instructions, and runs the task hourly, daily, on weekdays, weekly or on demand, with your connected tools, skills and plugins. Tasks run remotely, so they run even when your computer is asleep.[^anthropic-scheduled-tasks] A task with a folder on your computer runs only while that computer is awake and Claude Desktop is open ([1.5](../../ai-worker-paradigm/from-chatbots-to-ai-workers/both-ai-vendors.md)).[^anthropic-scheduled-tasks-local]
>
> - *First 10:* when you set a task up by hand, you choose its **approval mode**:[^anthropic-scheduled-tasks] Manually approve, Automatically approve or Skip all approvals.[^anthropic-cowork-safely] Anthropic's steps for scheduling from a conversation do not mention the setting, so check it on the Scheduled page after you create the task. A tool you set to Always ask is apart from the mode. A scheduled task that uses it may wait for your answer, or finish without the tool.[^anthropic-scheduled-tasks]
> - *Middle 80:* in Automatically approve, Claude checks each action for safety before it runs it. In Skip all approvals, nothing checks the task's actions. In every mode, Claude asks before it permanently deletes files. Anthropic advises starting with low-risk tasks, such as summaries, and advises against scheduling tasks that send messages, make purchases or take other actions that are hard to undo.[^anthropic-cowork-safely]
> - *Final 10:* each scheduled task runs as its own session. You review upcoming and past runs on the Scheduled page, where you can also pause, edit or run a task,[^anthropic-scheduled-tasks] and Anthropic advises reviewing the output after each run.[^anthropic-cowork-safely]

> **OpenAI, as verified 21 November 2026.** **Scheduled tasks** in ChatGPT run once, on a schedule, or as monitoring tasks that watch for a change and notify you. They are on every plan, with limits: Free users can run a task at most once a day, and each plan limits how many tasks can be active at once. **Event-triggered tasks**, which respond to activity in Gmail, Slack or GitHub, are not available on Free or Go. On Enterprise and Edu, an admin must switch them on first.[^openai-scheduled-tasks]
>
> - *First 10:* you write the instructions. For an event-triggered task, you review its **Trigger**, **Condition** and **Prompt** before you rely on it. In managed workspaces, admins may control which apps and actions are allowed.
> - *Middle 80:* connected apps read or act within the permissions you granted. An action that sends a message or changes data in another app may need approval. If it does, the task **pauses** until you review it.
> - *Final 10:* you review results on the Scheduled page. If a task stops responding, OpenAI says to check there for a paused task or a pending approval, and to confirm the app connection is still authorized.[^openai-scheduled-tasks]

> **Open source, as verified 23 October 2026.** Two of the book's open-source projects run work on a schedule. **Automations** are OpenClaw's scheduler: one-time jobs, cron schedules, webhooks and Gmail triggers. Each wakes the agent at the set time and can send the result to a chat app.[^openclaw-automations] In Omnara, a **cron trigger** starts a new agent on a schedule, or sends input to one that is running, in the time zone you choose.[^omnara-cron-trigger]
>
> - *First 10:* you write the job's instructions, and you set each tool yourself. In Omnara, each tool is set to always allow, always ask or always deny. Tools from connected MCP servers start at ask, and Omnara's own tools start at allow.[^omnara-permissions]
> - *Middle 80:* a tool set to ask stops the agent until a person approves, in Omnara's dashboard or in Slack or Discord.[^omnara-integrations] OpenClaw's tools run on the computer itself unless you turn its sandbox on, and the sandbox is off by default.[^openclaw-sandbox]
> - *Final 10:* Omnara saves every step of every agent, so you can read what each run did.[^omnara]
>
> *Running it safely:* run a scheduled assistant on a dedicated machine, VM or container, with its own credentials,[^openclaw-dedicated-machine] and never open it to the public internet.[^openclaw-exposure]

[^anthropic-scheduled-tasks]: Schedule recurring tasks in Claude Cowork, Claude Help Center, accessed 18 November 2026.
[^anthropic-scheduled-tasks-local]: Schedule recurring tasks in Claude Cowork, Claude Help Center, accessed 18 November 2026.
[^anthropic-scheduled-tasks-plans]: Schedule recurring tasks in Claude Cowork, Claude Help Center, accessed 18 November 2026.
[^anthropic-cowork-safely]: Use Claude Cowork safely, Claude Help Center, accessed 18 November 2026.
[^openai-scheduled-tasks]: Scheduled tasks in ChatGPT, OpenAI Help Center, accessed 21 November 2026.
[^openclaw-automations]: Automations, OpenClaw documentation, accessed 23 October 2026.
[^omnara-cron-trigger]: Create a cron trigger, Omnara API reference, accessed 23 October 2026.
[^omnara-permissions]: Tool permissions, Omnara documentation, accessed 23 October 2026.
[^omnara-integrations]: Integrations, Omnara documentation, accessed 23 October 2026.
[^openclaw-sandbox]: Sandboxing, modes, scope and backend, OpenClaw documentation, accessed 23 October 2026.
[^omnara]: Omnara, README on GitHub, accessed 23 October 2026.
[^openclaw-dedicated-machine]: Secrets and storage, OpenClaw documentation, accessed 23 October 2026.
[^openclaw-exposure]: Exposure runbook, OpenClaw documentation, accessed 23 October 2026.