Skip to content

Chapter 18

Your supervised agent task


The chapter in a minute

  • Start with a job an agent can only research and draft, with nothing connected and no step you can't take back.
  • Write a task brief that asks for the step plan first and tells the agent where to stop and ask you.
  • Give it a town or an area, read every step of its plan before your yes, and say no once on purpose to see what it does.
  • Read the step log with your plan beside you, note your own yes and no if the log doesn't, and check every result on its own page.
  • Save the brief and your lesson in your prompt notebook. Without an agent feature, run the same steps with the walk-through.

Try it now

One supervised task

0 of 11 steps done

Step 1 of 11

Know it. Ask checklist question 1: 'Do I know what kind of tool this is, and what it does well and badly?' Then ask chapter 15's agent test: 'Does it plan its own steps and use tools towards a goal?' If you have no agent feature, you'll do the rest of the steps with the walk-through.

Progress is saved in this browser only.

Tools and settings, as of a date

The book points to the ‘Agent options’ section of the companion page. Here it is in full, with the date each detail was checked. Open it on the companion page

Chapters 15 and 18 both close with this pointer. Chapter 18 adds that the section lists the current options "with the date each was checked". Ireland and the UK readers: not every feature is offered where you live.

Checked: 2 November 2026. This is the fastest-moving section on the page. Since the book's notes were taken, OpenAI has withdrawn its 2025 agent mode and replaced it with ChatGPT Work, and Anthropic's browser agent now runs inside Claude Cowork.

Current agent features, by provider

Provider and featurePlan, country and age limitsPage and date
OpenAI, ChatGPT Work (with its cloud browser)Eligible paid plans, not Free or Go. OpenAI's launch note says Work "is available in all supported regions", and Ireland and the UK are both on its list of supported countries. Availability may vary while it rolls out.ChatGPT Work and Codex (opens in a new tab), Using cloud browser in ChatGPT (opens in a new tab), ChatGPT release notes (opens in a new tab) (9 July 2026 entry), ChatGPT Supported Countries (opens in a new tab); all checked 2 November 2026
OpenAI, dots (always-on agents that keep working between conversations)Rolling out to eligible Pro and Business Premium users aged 18 or over. Pro access excludes the European Economic Area, Switzerland and the UK at launch, so not yet for personal accounts in Ireland or the UK. Created in the desktop app or on desktop web.ChatGPT release notes (opens in a new tab) (29 September 2026 entry), checked 2 November 2026
OpenAI, ChatGPT agent (the 2025 agent mode)No longer available. The page now says to use ChatGPT Work instead.ChatGPT agent (opens in a new tab), checked 2 November 2026
Anthropic, Claude Cowork and Claude in ChromePaid plans (Pro, Max, Ultra, Team and Enterprise). The help pages give no country limits, and Ireland and the UK are on Anthropic's list of supported countries.Get started with Claude Cowork (opens in a new tab), Get started with Claude in Chrome (opens in a new tab), Claude in Chrome permissions guide (opens in a new tab), supported countries (opens in a new tab); all checked 2 November 2026
Google, tasks in GeminiAge 18 or over; a personal Google Account; a Google AI Pro or Ultra subscription; Keep Activity on. Offered wherever the Gemini app is, except the European Economic Area, Nigeria, Switzerland and the UK. That rules out both Ireland (part of the European Economic Area) and the UK as of 2 November 2026.Manage your tasks and workflows in Gemini Apps (opens in a new tab), checked 2 November 2026

How the options arrived, with dates

Which show a plan first, and what happens after a no

Stop and take-over controls

Approval setting names and where they sit

See "Connections and permissions".

Sign-in handover and banking refusals

Every provider checked says the agent should stop and ask before it pays, sends in your name or signs in.

  • Signing in: ChatGPT Work pauses and asks you to sign in through a secure form; OpenAI says the model can't see the username and password typed there, and you should never paste passwords, security codes or card details into the chat (cloud browser page (opens in a new tab)). Google's tasks page and OpenAI's earlier agent pages also hand sign-in over to you.
  • Publishing or sharing personal data: Anthropic's pilot page says Claude asks users before high-risk actions like publishing, purchasing or sharing personal data.
  • Refused or blocked outright by at least one provider: bank transfers and banking (OpenAI's 2025 agent pages); financial services sites (Anthropic's pilot); purchases and financial transactions, account creation, trades and permanent deletions in Claude in Chrome, whatever approval mode you choose (permissions guide (opens in a new tab), checked 2 November 2026).

Scheduling and recurring tasks

As of 2 November 2026, all three providers let tasks repeat:

Makers' best-practice advice

How to clear an agent task from an assistant's history

Chapter 18 suggests clearing a finished task if you'd like to. Here is how, as of 2 November 2026.

ChatGPT Work. A Work task is a chat, so you delete it the same way (Deleting and archiving chats in ChatGPT (opens in a new tab)):

  1. Open your chat history.
  2. Select the more options menu (•••) next to the task's chat.
  3. Select Delete, then confirm.

It leaves your account view at once and is deleted from OpenAI's systems within 30 days, with security and legal exceptions. Files saved separately in your Library are not deleted with it. If the task repeats, also remove it from Scheduled, where scheduled tasks are managed (ChatGPT Work and Codex (opens in a new tab)). To clear the sign-ins and cookies its cloud browser kept (Using cloud browser in ChatGPT (opens in a new tab)):

  1. Open Settings.
  2. Select Cloud browser.
  3. Under Browser data, select Cookies.
  4. Clear the data for all sites, or for one site.

Claude Cowork and Claude in Chrome. Side panel sessions in Chrome appear in your Cowork history like any other task (Get started with Claude in Chrome (opens in a new tab)). To delete one (Get started with Claude Cowork (opens in a new tab)):

  1. Find the task in your Tasks list.
  2. Click ⋮ next to it and choose Delete. Or tick one or more tasks in the list and click the bin icon.

The task leaves your history straight away and is deleted from Anthropic's storage within 30 days. To withdraw a website permission you gave Claude in Chrome, open the extension's settings and go to Permissions (permissions guide (opens in a new tab)).

Gemini tasks. To delete a task thread on a computer (Find and manage your tasks in Gemini Apps (opens in a new tab)):

  1. Go to gemini.google.com.
  2. In the sidebar, hover over the task.
  3. Click More, then Delete.

Deleting the thread removes the task, its Gemini Apps activity and any schedules attached to it. It doesn't remove files the task created or changed, or the data from Gemini's remote browser and remote code. Delete those separately (Gemini tasks page (opens in a new tab)): go to Settings, then Browser, and click Delete next to "Delete remote browser data"; then go to Settings, then Task settings, and click Delete under "Delete remote code execution".

Chapter 8 explains what deleting history does and doesn't reach.

Benchmark figures

Never in print. If you carry them here: see "Tool list" for the AI Index figures. Also Xue and colleagues, "An Illusion of Progress? Assessing the Current State of Web Agents" (COLM 2025): 300 tasks on 136 real websites, with average success down 31.6% from easy to medium tasks and lower again for hard tasks. arXiv 2504.01382 (opens in a new tab) Also, as the book notes, short tasks with few steps did best in that study.

Printable copies of Table 18.1 and Figure 18.3

For readers doing the chapter 18 walk-through on paper. These are the book's own material and are in the companion PDF. See "The companion PDF".

From the book

For your first agent task, let it research and draft. Never let it pay, sign in, book or send.
Your First Rung, chapter 18

Sources

  1. Incident 1028: OpenAI's Operator Agent Reportedly Executed Unauthorized $31.43 Transaction Despite Safety Protocol (opens in a new tab) · AI Incident Database, 2025
  2. Building effective agents (opens in a new tab) · Anthropic, 2024
  3. Piloting Claude in Chrome (opens in a new tab) · Anthropic, 2025
  4. Claude in Chrome permissions guide (opens in a new tab) · Anthropic, 2026
  5. Use connectors to extend Claude's capabilities (opens in a new tab) · Anthropic, 2026
  6. Careful adoption of agentic AI services (opens in a new tab) · Australian Signals Directorate's Australian Cyber Security Centre and Cybersecurity and Infrastructure Security Agency and National Security Agency and Canadian Centre for Cyber Security and National Cyber Security Centre (New Zealand) and National Cyber Security Centre (UK), 2026
  7. Gemini 3 brings upgraded smarts and new capabilities to the Gemini app (opens in a new tab) · Google, 2025
  8. Ask Gemini to handle your multi-step tasks in select Android apps (opens in a new tab) · Google, 2026
  9. Manage your tasks & workflows in Gemini Apps (opens in a new tab) · Google, 2026
  10. The 2026 AI Index Report (opens in a new tab) · Stanford Institute for Human-Centered Artificial Intelligence, 2026
  11. ICO tech futures: Agentic AI (opens in a new tab) · Information Commissioner's Office, 2026
  12. Prompt injection is not SQL injection (it may be worse) (opens in a new tab) · Chismon, Dave, 2025
  13. Thinking carefully before adopting agentic AI (opens in a new tab) · Martin R and Kate S, 2026
  14. Introducing ChatGPT agent: bridging research and action (opens in a new tab) · OpenAI, 2025
  15. Introducing Operator (opens in a new tab) · OpenAI, 2025
  16. ChatGPT agent (opens in a new tab) · OpenAI, 2026
  17. Connecting and managing app accounts in ChatGPT (opens in a new tab) · OpenAI, 2026
  18. Managing app permissions in ChatGPT (opens in a new tab) · OpenAI, 2026
  19. LLM06:2025 Excessive Agency (opens in a new tab) · OWASP Gen AI Security Project, 2025
  20. LLM01:2025 Prompt Injection (opens in a new tab) · OWASP Gen AI Security Project, 2025
  21. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (opens in a new tab) · Xie, Tianbao and Zhang, Danyang and Chen, Jixuan and Li, Xiaochuan and Zhao, Siheng and Cao, Ruisheng and Hua, Toh Jing and Cheng, Zhoujun and Shin, Dongchan and Lei, Fangyu and Liu, Yitao and Xu, Yiheng and Zhou, Shuyan and Savarese, Silvio and Xiong, Caiming and Zhong, Victor and Yu, Tao, 2024
  22. An Illusion of Progress? Assessing the Current State of Web Agents (opens in a new tab) · Xue, Tianci and Qi, Weijian and Shi, Tianneng and Song, Chan Hee and Gou, Boyu and Song, Dawn and Sun, Huan and Su, Yu, 2025
  23. WebArena: A Realistic Web Environment for Building Autonomous Agents (opens in a new tab) · Zhou, Shuyan and Xu, Frank F. and Zhu, Hao and Zhou, Xuhui and Lo, Robert and Sridhar, Abishek and Cheng, Xianyi and Ou, Tianyue and Bisk, Yonatan and Fried, Daniel and Alon, Uri and Neubig, Graham, 2023