# 11.7 The details on today's tools (/managing-ai-workers/when-the-worker-goes-wrong/both-ai-vendors) --- type: Document title: "11.7 The details on today's tools" description: "What Anthropic's and OpenAI's own pages say about task records, scheduled runs, usage and limits, and what two open-source tools add." status: stable order: 211.7 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-11-04T06:52:58Z chapter: "11" part: II expert_status: required concepts: [ "11.7" ] last_verified: 2026-10-17 review_by: 2026-11-17 sources: - id: anthropic-scheduled-tasks title: "Schedule recurring tasks in Claude Cowork (Claude Help Center, verified 2026-11-03)" 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, verified 2026-11-03)" resource: https://support.claude.com/en/articles/15520349-use-claude-cowork-on-web-desktop-and-mobile - id: anthropic-cowork title: "Get started with Claude Cowork (Claude Help Center, verified 2026-11-03)" resource: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork - id: anthropic-usage-best-practices title: "Usage limit best practices (Claude Help Center, updated 30 October 2026, verified 2026-10-31)" resource: https://support.claude.com/en/articles/9797557-usage-limit-best-practices - id: anthropic-usage-limits title: "How do usage and length limits work? (Claude Help Center, updated 16 September 2026, verified 2026-10-08)" resource: https://support.claude.com/en/articles/11647753-how-do-usage-and-length-limits-work - id: anthropic-usage-credits title: "Manage usage credits for paid Claude plans (Claude Help Center, updated 30 October 2026, verified 2026-10-31)" resource: https://support.claude.com/en/articles/12429409-manage-usage-credits-for-paid-claude-plans - id: openai-scheduled-tasks title: "Scheduled tasks in ChatGPT (OpenAI Help Center, verified 2026-10-08)" resource: https://help.openai.com/en/articles/10291617-scheduled-tasks-in-chatgpt - id: openai-work-codex title: "ChatGPT Work and Codex (OpenAI Help Center, verified 2026-10-08)" resource: https://help.openai.com/en/articles/20001275-chatgpt-work-and-codex - id: openai-codex-usage title: "Using Codex with your ChatGPT plan (OpenAI Help Center, verified 2026-10-08)" resource: https://help.openai.com/en/articles/11369540-using-codex-with-your-chatgpt-plan - id: openai-usage-limits title: "Understanding ChatGPT and Codex usage limits (OpenAI Help Center, verified 2026-11-03)" resource: https://help.openai.com/en/articles/20001625-understanding-chatgpt-and-codex-usage-limits - id: openai-moving-desktop title: "Moving to the new ChatGPT desktop app (OpenAI Help Center, verified 2026-11-03)" resource: https://help.openai.com/en/articles/20001276-moving-to-the-new-chatgpt-desktop-app - id: openai-work-start title: "Get started with ChatGPT Work (ChatGPT Learn, verified 2026-11-03)" resource: https://learn.chatgpt.com/docs/get-started-with-work - id: anthropic-desktop-changelog title: "Changelog: release notes for Claude Desktop (Claude.ai Documentation, updated 7 October 2026, verified 2026-10-08)" resource: https://claude.com/docs/cowork/changelog - id: anthropic-routines title: "Automate work with routines (Claude Code Docs, verified 2026-10-08)" resource: https://code.claude.com/docs/en/routines - id: anthropic-claude-tag title: "What is Claude Tag? (Claude Help Center, updated 24 September 2026, verified 2026-10-08)" resource: https://support.claude.com/en/articles/15594475-what-is-claude-tag - id: openai-dots-faq title: "Dots privacy, security and safety FAQs (OpenAI Help Center, verified 2026-10-08)" resource: https://help.openai.com/en/articles/20001529-dots-privacy-security-and-safety-faqs - id: anthropic-duet-help title: "Get started with Claude Duet (Claude Help Center, verified 2026-10-23)" resource: https://support.claude.com/en/articles/17631495-get-started-with-claude-duet - id: anthropic-duet-product title: "Claude Duet (Anthropic product page, verified 2026-10-23)" resource: https://claude.com/product/claude-duet - id: openai-dots title: "Introducing dots (OpenAI, 29 September 2026, verified 2026-10-23)" resource: https://openai.com/index/introducing-dots/ - id: omnara title: "Omnara README (Omnara, GitHub, Apache 2.0, verified 2026-10-22)" resource: https://github.com/omnara-ai/omnara/blob/main/README.md - id: opencode-changelog title: "Changelog (OpenCode, verified 2026-10-23)" resource: https://opencode.ai/changelog - id: opencode-permissions title: "Permissions (OpenCode v2 documentation, verified 2026-10-23)" resource: https://opencode.ai/v2/docs/permissions/ generated: at: 2026-11-04T06:52:58Z by: process:panaversity trust_tier: unverified build_id: sha256:46fd53c5d7ab1c14f6347908d45c9fdaecda4d914439923ee878bdcecd57803e dirty: true ksor_version: 0.0.60 --- This page gives the details behind the AI vendor boxes in [11.1 Stop first, then read the record](stop-first.md) and [11.4 Usage and limits](usage-and-limits.md). Anthropic makes Claude. A Claude conversation becomes a task when the work needs it, and Anthropic's pages call these tasks Cowork. Claude Code is its coding harness. OpenAI makes ChatGPT. In a ChatGPT task, an agent acts across your apps and files, and OpenAI's pages call this Work. Codex is OpenAI's coding agent. The details are what each AI vendor's own pages said on 8 October 2026, unless a line gives a later date. Products change, so check each AI vendor's current pages before you rely on a line. A box after the tables covers open-source tools. ### Where to look when a job goes quiet or stops **On Claude:** - Did it run? Open *Scheduled* in the sidebar. It shows upcoming and past runs, and each run is its own session.[^anthropic-scheduled-tasks] - Is it waiting for you? In Manual mode a task pauses for approval. In Auto mode it pauses to ask when it blocks an action.[^anthropic-cowork] - Is it a Claude Code routine? Ask `/schedule` why it did nothing.[^anthropic-routines] - Did it reach a limit? Open *Settings > Usage*. Progress bars show the session and weekly limits, with reset times.[^anthropic-usage-best-practices] - Does it need files on your computer? The scheduling page[^anthropic-scheduled-tasks] and the page on web, desktop and mobile[^anthropic-cowork-surfaces] differ on where it runs. So check where the task says it runs. **On ChatGPT:** - Did it run? Open the *Scheduled* page. It shows results, and you can pause or resume a task there.[^openai-scheduled-tasks] - Did it pause? A task pauses when it needs approval or further action, when it is inactive, or when its chat was deleted.[^openai-scheduled-tasks] - Does it depend on an app? Confirm the app is still connected.[^openai-scheduled-tasks] - Did it reach a limit? Open the usage dashboard.[^openai-codex-usage] - Does it need project files? A scheduled task created in a project cannot reach uploaded files or project files.[^openai-scheduled-tasks] **For reference.** ### Reading the task record | | Anthropic | OpenAI | | --- | --- | --- | | Step list for a task | Progress indicators show each step, and finished outputs arrive in the session.[^anthropic-cowork] | ChatGPT tasks: review progress, answer questions, change direction and approve important actions. No separate step log is documented.[^openai-work-codex] | | Scheduled runs | *Scheduled* in the sidebar: upcoming and past runs, each run its own session. Pause, resume, run on demand, edit or delete.[^anthropic-scheduled-tasks] | *Scheduled* page: review results, pause or resume. Also reached from Settings > Notifications ("Manage tasks").[^openai-scheduled-tasks] | | Why a task pauses | In Manual mode a task pauses for approval. In Auto mode it pauses to ask when it blocks an action. There is no list of reasons for scheduled tasks.[^anthropic-cowork] | Needs approval, needs further action, inactive, or its chat was deleted[^openai-scheduled-tasks] | | A task that stopped | As of 3 November 2026: cloud sessions keep running in the background, so open the session from any device to check its progress. A session on your own computer may have ended if the app closed or the computer went to sleep. On Pro, Max and Ultra, that means only tasks you started before October 6, 2026.[^anthropic-cowork] | As of 3 November 2026: keep your computer online for any step that needs its files or tools.[^openai-work-start] Tasks in the cloud sync across web, mobile and desktop, so you can continue one on another device.[^openai-moving-desktop] | | A quiet event-triggered task | For Claude Code routines, you can ask `/schedule` why a routine did nothing, and GitHub events above the hourly limits are dropped.[^anthropic-routines] | Check for a pause or a pending approval, and confirm the app is still connected[^openai-scheduled-tasks] | | Standing worker | As verified 23 October 2026: Claude Duet's *Tasks* tab shows what it is working on and highlights tasks that need your input.[^anthropic-duet-help] Its product page says you can see what it has done and is doing, and steer it.[^anthropic-duet-product] | A dot is an always-on agent. Its *Activity View*, in the desktop app, shows its ongoing and delegated tasks, status and steps. You can redirect it or tell it to stop. Whether an action can be undone depends on the action.[^openai-dots-faq] | | Shared worker in Slack | Claude Tag, in beta on Team and Enterprise, is one shared Claude in a Slack channel. Its Activity page lists every task for Owners.[^anthropic-claude-tag] | Not compared here | | Changing direction during a task | A message typed during a reply waits. *Send now* stops the reply and sends yours (added 10 September 2026). In Claude Code cloud sessions, you can go back to an earlier message (added 13 August 2026).[^anthropic-desktop-changelog] | Change direction during the task[^openai-work-codex] | | Files for scheduled work | Tasks use the connectors and plugins you have set up. As of 3 November 2026, two Anthropic pages differ on a task that needs files or apps on your own computer. The scheduling page says it runs only there.[^anthropic-scheduled-tasks] The page on web, desktop and mobile says new scheduled tasks run in the cloud, and reach your files only while the Claude Desktop app is open.[^anthropic-cowork-surfaces] So check where the task says it runs. | A scheduled task created in a project cannot reach uploaded files or project files.[^openai-scheduled-tasks] | ### Usage and limits | | Anthropic | OpenAI | | --- | --- | --- | | Time windows | Fixed-allowance plans (Pro, Max, Ultra, Team, seat-based Enterprise): a five-hour session limit and weekly limits. Ultra accounts that Anthropic has verified have no five-hour limit. Some plans add a separate weekly limit for one model.[^anthropic-usage-best-practices] | In Codex, and so in Work: five-hour and weekly windows[^openai-codex-usage] | | Where to look | *Settings > Usage*: progress bars for the session and weekly limits, with reset times[^anthropic-usage-best-practices] | Usage dashboard. `/status` in a Codex CLI session.[^openai-codex-usage] | | What shares the pool | claude.ai, Claude Code and Claude Desktop[^anthropic-usage-limits] | On plans with shared allowances: Work, Codex, ChatGPT for Excel and workspace agents. Ordinary chat is not on the list.[^openai-codex-usage] As of 3 November 2026, OpenAI says that from December, Plus, Pro and Business plans will share one allowance across ChatGPT and Codex, and that Instant chat will not draw from it.[^openai-usage-limits] | | A standing worker | As verified 23 October 2026: Duet's background work, such as the morning brief and check-ins, counts toward your plan's limits.[^anthropic-duet-help] Its product page says it shares them "with the rest of Claude."[^anthropic-duet-product] | As verified 23 October 2026: conversations with a dot do not count toward ChatGPT's usage limits. Tasks it starts in Codex or ChatGPT Work do.[^openai-dots] | | At a limit | Wait for the reset, upgrade, or buy usage credits. Credits (Pro, Max and Ultra) are billed at standard API rates, with an optional monthly spending limit and auto-reload.[^anthropic-usage-credits] | The active Codex turn can continue, subject to fair use. Then add credits, apply an available reset, upgrade or wait. Support cannot reset limits.[^openai-codex-usage] | | No fixed limits | Usage-based Enterprise plans, billed by how much is used[^anthropic-usage-best-practices] | Enterprise token-based billing: continuing depends on the workspace budget and user limits[^openai-codex-usage] | | Ways to use less | Content in projects is cached, or stored for reuse, and counts less when reused, until the cache expires.[^anthropic-usage-best-practices] Long chats cost more. With code execution on, earlier messages are summarized near the context limit, and those chats use more of the limit.[^anthropic-usage-limits] | Usage depends on model, task size, reasoning level, speed and tools[^openai-codex-usage] | | Scheduled task limits | Not documented for scheduled tasks in the Claude app. Claude Code routines allow 100 scheduled runs an hour per account.[^anthropic-routines] | Free: a one-time task, or a recurring task at most once a day. Paid plans: recurring tasks up to once an hour. Event-triggered tasks: 30 runs an hour, 720 a day.[^openai-scheduled-tasks] | > **Open source, as verified 23 October 2026.** > - *Reading the record.* Omnara, a runtime you can host yourself, saves every step of every agent. That record is the agent's state, so Omnara can pick an agent back up after a crash or a restart.[^omnara] It shows what the agent attempted. It is run evidence, not outcome evidence, so it does not prove what happened in the business system (11.2). > - *Which version ran.* OpenCode, an open-source coding agent, lists nine version 2 releases in its changelog, from 8 to 22 October 2026.[^opencode-changelog] So write down which version of each tool ran, as part of the task record. > - *Running it safely.* OpenCode's agents start by allowing almost every action. Before a run, set any action you could not undo to ask or deny.[^opencode-permissions] [^anthropic-cowork]: Get started with Claude Cowork, Claude Help Center. [^openai-work-codex]: ChatGPT Work and Codex, OpenAI Help Center. [^anthropic-scheduled-tasks]: Schedule recurring tasks in Claude Cowork, Claude Help Center. [^anthropic-cowork-surfaces]: Use Claude Cowork on web, desktop, and mobile, Claude Help Center. [^openai-scheduled-tasks]: Scheduled tasks in ChatGPT, OpenAI Help Center. [^anthropic-routines]: Automate work with routines, Claude Code Docs. [^anthropic-claude-tag]: What is Claude Tag?, Claude Help Center. [^openai-dots-faq]: Dots privacy, security and safety FAQs, OpenAI Help Center. [^anthropic-desktop-changelog]: Changelog: release notes for Claude Desktop, Claude.ai Documentation. [^anthropic-usage-best-practices]: Usage limit best practices, Claude Help Center. [^openai-codex-usage]: Using Codex with your ChatGPT plan, OpenAI Help Center. [^openai-usage-limits]: Understanding ChatGPT and Codex usage limits, OpenAI Help Center. [^openai-moving-desktop]: Moving to the new ChatGPT desktop app, OpenAI Help Center. [^openai-work-start]: Get started with ChatGPT Work, ChatGPT Learn. [^anthropic-usage-limits]: How do usage and length limits work?, Claude Help Center. [^anthropic-usage-credits]: Manage usage credits for paid Claude plans, Claude Help Center. [^anthropic-duet-help]: Get started with Claude Duet, Claude Help Center. [^anthropic-duet-product]: Claude Duet, Anthropic. [^openai-dots]: Introducing dots, OpenAI, 29 September 2026. [^omnara]: Omnara, README on GitHub. [^opencode-changelog]: Changelog, OpenCode. [^opencode-permissions]: Permissions, OpenCode v2 documentation.