# Chapter 5 on today's products (/appendices/todays-products/the-four-part-brief)

---
type: Document
title: "Chapter 5 on today's products"
description: "The products' own guidance behind lesson 5.8: the brief line by line on Claude, ChatGPT and OpenCode, which plans include Work, and how steering and a model change work on each, each with its sources and the date it was checked."
status: stable
order: 905.05
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: openai-pricing
    title: "Plans and Pricing (ChatGPT, verified 2026-11-21)"
    resource: https://chatgpt.com/pricing/
  - id: anthropic-one-claude
    title: "Claude Cowork and chat are one Claude (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude
  - id: anthropic-one-claude-plans
    title: "Claude Cowork and chat are one Claude, the plans it reaches first (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude
  - id: anthropic-one-claude-nov
    title: "Claude Cowork and chat are one Claude, on defaults and moving over (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude
  - id: anthropic-one-claude-post
    title: "Claude Cowork and chat are now one Claude (Anthropic, 16 September 2026, verified 2026-11-18)"
    resource: https://claude.com/resources/articles/cowork-is-now-claude
  - id: anthropic-artifacts
    title: "What are artifacts and how do I use them? (Claude Help Center, updated 13 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/17153992-what-are-artifacts-and-how-do-i-use-them
  - id: anthropic-claude-docs
    title: "Get started with Claude Docs (Claude Help Center, updated 12 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/16923645-get-started-with-claude-docs
  - id: anthropic-google-workspace
    title: "Use Google Workspace connectors (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors
  - id: openai-work-codex
    title: "ChatGPT Work and Codex (OpenAI Help Center, verified 2026-11-21)"
    resource: https://help.openai.com/en/articles/20001275-chatgpt-work-and-codex
  - id: openai-prompting
    title: "Prompting (OpenAI, ChatGPT Learn, verified 2026-11-21)"
    resource: https://learn.chatgpt.com/docs/prompting
  - id: openai-work-files
    title: "Creating and editing documents, spreadsheets, and presentations with ChatGPT Work (OpenAI Help Center, verified 2026-11-21)"
    resource: https://help.openai.com/en/articles/20001278-creating-and-editing-documents-spreadsheets-and-presentations-with-chatgpt-work
  - id: openai-space
    title: "Getting started with Space in ChatGPT (OpenAI Help Center, verified 2026-11-21)"
    resource: https://help.openai.com/en/articles/20001549-getting-started-with-space-in-chatgpt
  - id: openai-permissions
    title: "Permissions (OpenAI, ChatGPT Learn, verified 2026-11-21)"
    resource: https://learn.chatgpt.com/docs/permission-modes
  - id: claude-code-queue
    title: "Interactive mode: queue messages while Claude works (Claude Code Docs, verified 2026-11-18)"
    resource: https://code.claude.com/docs/en/interactive-mode
  - id: claude-tag-steer
    title: "How Claude Tag works: reply in the thread to steer (Claude Docs, verified 2026-11-18)"
    resource: https://claude.com/docs/claude-tag/concepts/how-it-works
  - id: anthropic-opus5
    title: "Prompting Claude Opus 5 (Claude Docs, Anthropic, verified 2026-11-18)"
    resource: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5
  - id: anthropic-opus-5-5
    title: "Prompting Claude Opus 5.5 (Claude Docs, Anthropic, verified 2026-11-18)"
    resource: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5
  - id: opencode-v2
    title: "OpenCode v2 documentation (OpenCode, verified 2026-10-23)"
    resource: https://opencode.ai/v2/docs/
  - id: opencode-cli
    title: "CLI (OpenCode v2 documentation, verified 2026-10-23)"
    resource: https://opencode.ai/v2/docs/cli/
  - id: opencode-instructions
    title: "Instructions (OpenCode v2 documentation, verified 2026-10-23)"
    resource: https://opencode.ai/v2/docs/instructions/
  - id: opencode-agents
    title: "Agents (OpenCode v2 documentation, verified 2026-10-23)"
    resource: https://opencode.ai/v2/docs/agents/
  - id: opencode-mcp
    title: "MCP servers (OpenCode v2 documentation, verified 2026-10-23)"
    resource: https://opencode.ai/v2/docs/mcp-servers/
  - id: opencode-permissions
    title: "Permissions (OpenCode v2 documentation, verified 2026-10-23)"
    resource: https://opencode.ai/v2/docs/permissions/
  - id: anthropic-cowork-start
    title: "Get started with Claude Cowork (Claude Help Center, updated 18 November 2026, verified 2026-11-18)"
    resource: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork
  - id: claude-code-subagents
    title: "Create custom subagents (Claude Code Docs, verified 2026-11-18)"
    resource: https://code.claude.com/docs/en/sub-agents
  - id: anthropic-subagents-article
    title: "How and when to use subagents in Claude Code (Anthropic, 7 April 2026, verified 2026-11-18)"
    resource: https://claude.com/resources/articles/subagents-in-claude-code
  - id: openai-subagents
    title: "Subagents (OpenAI, ChatGPT Learn, verified 2026-11-21)"
    resource: https://learn.chatgpt.com/docs/agent-configuration/subagents?surface=app
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 [5.8](../../managing-ai-workers/the-four-part-brief/both-ai-vendors.md). The lesson teaches how the AI vendors' own guides name the four parts, and the differences that change a brief. This page holds each product's own guidance, line by line, with its sources and the date each was checked.

Products change every few weeks. Check the date on each box before you rely on a line, and open its source if the date is old.

## The brief, line by line

The three boxes below follow the same eight lines in the same order, and the open-source box adds a ninth, on running it safely. Read the box for the app you use. The others are there to compare. A number such as (5.3) points to the concept that line matches.

> **Anthropic, as verified 18 November 2026.**
> - *Where you brief it.* Any conversation in the new Claude experience, with no mode to pick. It is rolling out gradually on the Pro, Max and Ultra plans. On Team and Enterprise, it is available where the Chat and Cowork unified setting is on. Pro, Max and Ultra accounts that do not have it yet still see Chat and Cowork.[^anthropic-one-claude-plans]
> - *What to include (5.1).* Claude's help center lists the desired outcome, the format, and the inputs Claude will need.[^anthropic-one-claude] Its guide to Docs adds what the result is for, who will read it and what it should cover. It also says to name the file or app where the content is kept.[^anthropic-claude-docs]
> - *Outcome or steps (5.2).* Describe the outcome, and Claude works through the steps. You do not need to break the work into steps.[^anthropic-one-claude]
> - *Context (5.3).* Attach files and links, or name connected apps such as Google Drive. Google Docs added to a chat or project sync from Drive, so Claude reads the latest version.[^anthropic-google-workspace]
> - *Plan first (5.4).* When you ask for a doc, Claude asks clarifying questions before it writes a draft.[^anthropic-claude-docs] With the Manual setting, Claude also asks before it takes actions.[^anthropic-one-claude]
> - *Helpers (5.4).* For a complex task, Claude may on its own coordinate several sub-agents working at the same time.[^anthropic-cowork-start] You can ask for helpers in plain words.[^anthropic-subagents-article] Anthropic's prompting guide for Opus 5 shows how to say when Claude should not use one.[^anthropic-opus5] In Claude Code, a helper starts fresh and does not see your conversation, unless it is a fork, which starts with a copy of it.[^claude-code-subagents]
> - *Deliverables and destination (5.7).* Documents, spreadsheets with working formulas and presentations.[^anthropic-one-claude] Claude Docs is on every plan, Free included, and you can export a doc to Word, PDF, Markdown or Google Docs.[^anthropic-claude-docs] Anthropic's artifacts page says Slides and Design are on every plan too.[^anthropic-artifacts] Anthropic's launch post of 16 September 2026 called all three beta, on paid plans.[^anthropic-one-claude-post] With the Google Docs, Sheets and Slides connectors, Claude creates and edits Google files. Name the destination you want: a Google file or a file to download,[^anthropic-google-workspace] or a Claude Doc.[^anthropic-claude-docs]
> - *Autonomy.* A permission setting in the message box. Manual asks before Claude takes actions. Auto keeps working, with automated safety checks before actions. It covers the whole conversation, and you can stop or redirect Claude.[^anthropic-one-claude] Auto is rolling out as the default on Pro, Max, Ultra and Team. Manual is the default on Enterprise, except in the Cowork side panel in Chrome.[^anthropic-one-claude-nov] Anthropic's launch post says Claude asks by default, so read what your own message box shows.[^anthropic-one-claude-post]

> **OpenAI, as verified 21 November 2026.**
> - *Where you brief it.* A ChatGPT conversation in Work. Choose Work from the Chat and Work toggle.[^openai-work-codex]
> - *What to include (5.1).* OpenAI's prompting guide lists goal, context, output and boundaries, using only the parts that help. For a longer task it adds: the result, the source material, the audience, and how you will review the work.[^openai-prompting]
> - *Outcome or steps (5.2).* Start with the result, not a detailed list of steps. Describe a process only when the process matters.[^openai-prompting]
> - *Context (5.3).* Attach files, use a project, or name connected sources and what to take from each. Add only the sources that matter.[^openai-prompting]
> - *Plan first (5.4).* Ask for a plan when the approach matters.[^openai-prompting]
> - *Helpers (5.4).* ChatGPT and Codex can run subagents. Usually, you ask for them directly, such as "check these in parallel". In Codex, a project's or skill's instructions can also ask for them. The desktop app shows each helper's thread, with its work and the summary it sent back. Helpers keep the permission setting you chose, and they use more of your plan than one worker doing the same job.[^openai-subagents]
> - *Deliverables and destination (5.7).* Documents, spreadsheets and presentations, including native Google Docs, Sheets and Slides when the Google Workspace app is turned on. OpenAI says to name the output format and where the file should be created.[^openai-work-files] On Pro, Business and Enterprise, and on Plus as it rolls out, ChatGPT also makes pages in Space: editable documents you can share and edit together. Name the space when you ask for a page.[^openai-space]
> - *Autonomy.* Boundaries you write in the prompt, such as requiring your approval before ChatGPT sends, publishes or changes information others rely on.[^openai-prompting] In the desktop app, a permissions control sets local actions. Ask for approval is the recommended start. Approve for me sends requests to automatic review. Which choices you see depends on your app version and your organization.[^openai-permissions]

> **Open source, as verified 23 October 2026.**
> - *Where you brief it.* OpenCode, an open-source coding agent, in its terminal, desktop or web app.[^opencode-v2] All three connect to one OpenCode service on your own computer.[^opencode-cli]
> - *What to include (5.1).* The same four parts. Rules for every task, such as "always cite the policy," can go in an AGENTS.md file in the project's folder. OpenCode loads it for you.[^opencode-instructions]
> - *Outcome or steps (5.2).* Describe the outcome. Build, the default agent, does the work.[^opencode-agents]
> - *Context (5.3).* The files in its folder, called its workspace, and other apps, through MCP servers, which work like connectors.[^opencode-mcp] Name the governed source by its file name.
> - *Plan first (5.4).* Choose the plan agent. It plans without editing your project files, but its shell commands still follow your rules.[^opencode-agents] Approve the plan, then switch to build.
> - *Helpers (5.4).* Built-in general and explore helpers. Each runs in a child session with a fresh context, not the parent's conversation, and with its own permission rules.[^opencode-agents]
> - *Deliverables and destination (5.7).* Files it writes on your own computer, such as the proposal CSV.[^opencode-cli] Name the folder and the file name.
> - *Autonomy.* Every agent starts out allowed to use every tool. Only reading a file of sensitive settings asks first. A rule can set each action, such as editing files or running commands, to allow, ask or deny.[^opencode-permissions] A custom agent, one text file, carries its own instructions, model and rules.[^opencode-agents]
> - *Running it safely.* Before the first brief, set every action that can change or send something to ask, so nothing happens until you approve. Helpers have their own rules, so set theirs too.

## Access, steering and model changes

Other differences between the products are about access: which plans include each feature, and what is still in beta. OpenAI's page says Work, its name for longer tasks, needs an eligible paid plan,[^openai-work-codex] and its pricing page lists some on the free desktop app.[^openai-pricing]

**Steering a run ([5.5](../../managing-ai-workers/the-four-part-brief/iterate.md)).** Claude Code holds a message you type while it works, and passes it on as soon as its current tool calls finish, in the same turn.[^claude-code-queue] In Claude Tag, anyone in the channel can steer a running session by replying in its thread.[^claude-tag-steer] In both, name the part that changed.

**When the model changes ([5.5](../../managing-ai-workers/the-four-part-brief/iterate.md)).** Run each saved brief again, on either AI vendor or an open-source tool. Anthropic's guide for Claude Opus 5 says the model checks its own work without being told to. Old lines that ask it to verify make it check twice, so the guide says to remove them.[^anthropic-opus5] Anthropic's guide for Claude Opus 5.5 adds that lines telling the model to think carefully can go too, because how hard it thinks is a setting ([5.1](../../managing-ai-workers/the-four-part-brief/four-parts.md)).[^anthropic-opus-5-5]

[^openai-pricing]: Plans and Pricing, ChatGPT.
[^anthropic-one-claude]: Claude Cowork and chat are one Claude, Claude Help Center.
[^anthropic-one-claude-plans]: Claude Cowork and chat are one Claude, Claude Help Center, accessed 18 November 2026.
[^anthropic-one-claude-nov]: Claude Cowork and chat are one Claude, Claude Help Center, accessed 18 November 2026.
[^anthropic-one-claude-post]: Claude Cowork and chat are now one Claude, Anthropic, 16 September 2026.
[^anthropic-artifacts]: What are artifacts and how do I use them?, Claude Help Center.
[^anthropic-claude-docs]: Get started with Claude Docs, Claude Help Center.
[^anthropic-google-workspace]: Use Google Workspace connectors, Claude Help Center.
[^openai-work-codex]: ChatGPT Work and Codex, OpenAI Help Center.
[^openai-prompting]: Prompting, ChatGPT Learn, OpenAI.
[^openai-work-files]: Creating and editing documents, spreadsheets, and presentations with ChatGPT Work, OpenAI Help Center.
[^openai-space]: Getting started with Space in ChatGPT, OpenAI Help Center.
[^openai-permissions]: Permissions, ChatGPT Learn, OpenAI.
[^claude-code-queue]: Interactive mode, Claude Code Docs.
[^claude-tag-steer]: How Claude Tag works, Claude Docs.
[^anthropic-opus5]: Prompting Claude Opus 5, Claude Docs, Anthropic.
[^anthropic-opus-5-5]: Prompting Claude Opus 5.5, Claude Docs, Anthropic.
[^opencode-v2]: OpenCode v2 documentation, OpenCode.
[^opencode-cli]: CLI, OpenCode v2 documentation.
[^opencode-instructions]: Instructions, OpenCode v2 documentation.
[^opencode-agents]: Agents, OpenCode v2 documentation.
[^opencode-mcp]: MCP servers, OpenCode v2 documentation.
[^opencode-permissions]: Permissions, OpenCode v2 documentation.
[^anthropic-cowork-start]: Get started with Claude Cowork, Claude Help Center.
[^claude-code-subagents]: Create custom subagents, Claude Code Docs.
[^anthropic-subagents-article]: How and when to use subagents in Claude Code, Anthropic.
[^openai-subagents]: Subagents, ChatGPT Learn, OpenAI.
