# Side by side (/claude-and-chatgpt-2-tour/side-by-side) --- type: Document title: "Side by side" description: "A feature map of Claude, ChatGPT and OpenCode, what the apps share, where they differ, and what a comparison cannot tell you." status: stable order: 0.24 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-11-05T15:14:05Z chapter: "F00T" part: Front expert_status: required concepts: [ "Side by side" ] last_verified: 2026-11-05 sources: - id: openai-merge title: "OpenAI is finally merging ChatGPT's Chat and Work tabs (TechCrunch, verified 2026-11-05)" resource: https://techcrunch.com/2026/11/02/openai-is-finally-merging-chatgpts-chat-and-work-tabs/ - id: lds-chat-work-merge title: "OpenAI to merge ChatGPT Chat and Work tabs, pool Codex usage (Let's Data Science, verified 2026-11-05)" resource: https://letsdatascience.com/news/openai-to-merge-chatgpt-chat-and-work-tabs-pool-codex-usage-a4ede6bc generated: at: 2026-11-05T15:14:05Z by: process:panaversity trust_tier: unverified build_id: sha256:2a056b33672a35ac4eceb7ea3c08a7eb0dc65554836f5b781c35b7b7ba102fec dirty: true ksor_version: 0.0.60 --- *As verified on November 5, 2026.* ### Feature map The open-source column describes OpenCode, which Part III covers beside Claude Code and Codex. "Not documented" means the feature was not found in the product's documentation, not that it is impossible. | What you need | Claude | ChatGPT | Open source (OpenCode) | | --- | --- | --- | --- | | **Start a delegated job** | Ask in any conversation, and Claude decides when a request becomes a task | Choose Work with the toggle above the message box | Ask the coding agent | | **Technical work and software** | The Code tab (Claude Code), useful beyond programming | Codex, for software or any job where you want the technical detail | OpenCode, in a terminal, desktop app or editor | | **Choose the model** | Claude models | OpenAI models | Over 75 providers, including models run on your own computer | | **Finished work** | Docs, Slides, Design, Dashboards and Motion artifacts, plus files | Documents, spreadsheets, presentations, web apps, Slides and Sites | Files and code | | **Work on it with your team** | Share Docs and Slides artifacts, which the team edits with Claude | Share pages and Slides in Space, and ask ChatGPT for edits from a comment | Through your own tools, such as GitHub | | **Shareable live tools** | Artifacts that read your connected apps and can call Claude | Sites that update as their data changes | Not documented | | **Browser and your computer** | Built-in browser, Claude in Chrome, computer use | Built-in browser, cloud browser, ChatGPT in Chrome, computer use, Record & Replay | Not documented | | **Your apps and methods** | Connectors, skills and plugins | Plugins, skills (called with "@") and site tools | MCP servers and skills | | **Work while you are away** | Cloud tasks and sessions, Remote Control, keep-awake | Cloud Work, Codex Cloud, Codex Remote | Not documented | | **Where cloud work runs** | A fresh virtual machine for each session, deleted when the session ends | Virtual-machine-backed sandboxes that can be reused across tasks, with saved state | On your own computer, unless you host it elsewhere yourself | | **Work toward a finish line** | `/goal`, judged each turn by a separate model | Codex goal mode, bounded by a token budget | Not documented | | **Parallel work** | Nested sessions, a coordinating session, Projects with cloud threads | Parallel chats and projects, worktrees, Codex Cloud | Several agents in parallel in one project | | **Scheduled and triggered work** | Scheduled tasks, and cloud tasks that start on GitHub events or API calls | Scheduled tasks, with triggers on Gmail, Slack, GitHub and plugin events | Not documented | | **Change the app itself** | Mods | Not documented | Open source code you can change | | **How freely it acts** | Auto or Manual for the whole conversation, with more modes in the Code tab | Ask for approval, Approve for me (auto-review), Full access or Custom | Configurable permissions | ### What they now share The two apps have converged. Both are now AI Worker platforms. Both have moved from answering questions to doing whole jobs: research, files, a browser, your computer, your connected apps, and finished documents, spreadsheets and presentations at the end. Both build presentations you can edit yourself and export to PowerPoint or Google Slides (ChatGPT's Slides is reported and still rolling out). Both draw charts and interactive visuals inside the conversation. Both let you save a way of working as a skill. Both keep a separate, specialist place for software. Both run work in the cloud so it continues with your laptop closed, and let you follow it from your phone. Both run work on a schedule. Both connect to outside tools through MCP, which is why a connector you build in Part III can serve both, and OpenCode too. And both vendors now give the same advice for briefing them: the outcome and how to check it, not the steps. ### Where they differ ![How work begins in each app: two ways to start, and permissions govern the actions. In Claude, your request goes to one conversation, where Claude decides between a quick answer and a task that uses files, a browser, apps and the screen. The task leads to the permission setting, Auto or Manual, which applies to the conversation. In ChatGPT, you choose Chat for an answer or Work for files, a browser, apps and the screen, and Codex provides another workspace for hands-on tasks. Work leads to the permission mode: Ask for approval, Approve for me, Full access or Custom. A band says choosing a task does not grant unlimited authority, and permission settings control what the worker may do. A note says this is an illustrative overview and tools vary by app, plan and version.](img/how-work-begins.png) The two rows differ in the middle box, who decides that work begins. They end in the same place: a permission setting that decides what the worker may do once it starts. That is why this section begins with permissions. **How permission is set.** This is the difference that matters most for an AI Worker. Claude sets one level, Auto or Manual, for a whole conversation, and the Code tab adds finer modes. ChatGPT sets a permission mode with a sandbox around the workspace, can route approvals to a reviewing model, and in the cloud browser separates permission to visit a site from permission to act on it. Before you delegate, read what each mode actually allows, not its name. **Who decides that work begins.** In Claude, the conversation decides. In ChatGPT, you do, by choosing Work. This difference is narrowing *(reported)*, so do not choose an app on it.[^openai-merge],[^lds-chat-work-merge] Whichever app you use, the permission setting is where you control what happens once work begins. **What surrounds the coding agent.** Claude's Code tab has grown into a workspace for running many sessions at once: nested sessions, a coordinating session and projects with cloud threads. Codex leans toward the software lifecycle: inline diffs, pull-request review, several repositories, worktrees and cloud runs. **What starts work without you.** ChatGPT can start a task when an email, a Slack message or a pull request arrives. Claude's cloud tasks start on a schedule, a GitHub event or an API call. **What you can build on top.** Claude's artifacts can call Claude for whoever uses them, at the user's cost. ChatGPT's Sites publish web apps that update from their data. Claude also lets you reshape the app itself with mods. **Where open source fits.** OpenCode is a coding agent, not a desktop app for everyday delegated work. Its strength is choice: it runs models from many providers, including models on your own computer, which matters where cost, data location or vendor independence comes first. For a non-developer starting out, the two vendor apps remain the easier place to begin. ### What the comparison cannot tell you Neither vendor's documentation shows which app reasons better, makes fewer spreadsheet errors, finishes more web tasks, or keeps your data safer. An easier interface can reduce friction, but it cannot stand in for a correct result or a sound permission boundary. The only fair comparison is the one this book teaches you to run: the same job, the same inputs, the same done-when and the same limits on each, repeated, with the results checked against the files each run left behind, never against the worker's account of its own work. [^openai-merge]: On November 2, 2026, OpenAI told users it will merge the Chat and Work tabs into one experience, first for a small group of users, while Codex stays separate. When that reaches your account, ChatGPT starts work from a single conversation, as Claude does. OpenAI is finally merging ChatGPT's Chat and Work tabs, TechCrunch. [^lds-chat-work-merge]: OpenAI to merge ChatGPT Chat and Work tabs, pool Codex usage, Let's Data Science.