Answers
How do you share a Claude Project with your team?
Claude's help center says sharing is available on the Team and Enterprise plans. A project is either public, so everyone in the organization can view and use it, or private, so only the people invited can; invited people get either view or edit access, and the chats inside a project are not shared unless someone shares each one. That solves one thing well: everyone who uses Claude on that plan opens the same instructions and the same project knowledge. It stops where the work does. A colleague who works in ChatGPT, Codex or Cursor does not read the project. A rule that changes is an edit someone has to make in the project, and nothing in it says who decided the line or when it stops being true. The way past that is to put what holds where every tool reads it and a person approves it. Arroway is that place: decisions per project, each with who approved it and when it ends, read before acting by every connected tool, Claude included. The install page is the first step.
Last updated October 7, 2026
What a shared Claude Project gives the team
According to Claude's help center, projects can be shared on Team and Enterprise plans, not on Free or Pro. A project can be public to the whole organization or private to invited members, and invited members can be given view-only or edit access; Enterprise plans can also share with groups, in beta when I read it. Project chats stay private unless shared one by one. So a team on one of those plans can keep one set of instructions and one body of project knowledge that every member opens with. For a team that lives in Claude, that is a real answer to the question.
Where it stops
A Claude Project is read by the people using Claude on that plan. The colleague working in ChatGPT, Codex or Cursor, the agent in a script and the partner without a seat never open it. A change is a manual edit by someone with edit access, and the project does not say who decided the line, whether it still stands or what it replaced; last month's rule reads like today's. And nothing in it separates a rule a person approved from a line someone pasted in. I did not read the equivalent page for ChatGPT Projects, so I do not describe it here. These limits follow from the rule living inside one product's workspace.
When to use Arroway
Use Arroway when the team uses more than one AI tool, or expects to, and a rule should change in one place and reach all of them. Each rule and decision is recorded once, with who approved it and the condition that ends it; a replacement names the rule it retires; every connected assistant — Claude, ChatGPT, Codex, Cursor or anything over MCP — reads the current version at the start of a session. Each person connects the AI they already use to the same project, and Claude keeps working as it does today. The first step is the install page.
What it looks like in practice
A six-person consultancy shares a Claude Project on the Team plan, with the tone guide, the client list and the engagement rules. Two of the six work mainly in ChatGPT, and one partner uses Cursor. In October the managing partner decides that no deliverable leaves without a second reviewer. Someone with edit access adds the line to the project. The two people in ChatGPT never see it, and a draft goes out with one reviewer. When the team opens the project to find out what is current, it also has a line from the spring that nobody remembers approving. In Arroway the rule is recorded once, with the managing partner's name, replacing the older one-reviewer rule. Claude, ChatGPT and Cursor open their next session with the two-reviewer rule, and the history shows when it changed and who changed it. The team connects each tool to the same project; nobody has to move the Claude Project.
Questions people ask about this
- Can I share a Claude Project on a free or Pro plan?
- According to Claude's help center, sharing projects is available on the Team and Enterprise plans, not on Free or Pro. Without it, what a person writes in a project stays with that person.
- Does Arroway replace Claude Projects?
- No. The project keeps working as it does today; what has to hold for the team — who approved it, what is in force, what ended — goes into Arroway, where every assistant, Claude included, reads it.
- How do I try Arroway?
- Install it in the tool you already use — the install page has one route for Claude, ChatGPT, Codex, Cursor or any MCP tool — and sign in when the tool asks. From then on, sessions open by reading the project and close by recording what was decided.
Where this is verifiable
Claude Help Center, the article on projects and sharing (support.claude.com), read on 7 October 2026 — Claude Projects are described only as that page describes them on that date, and can change in any release. I could not read OpenAI's help page on ChatGPT Projects that day, so it is not described. Product documentation on this site (How it works, Install), the answers on shared context across AI tools and on switching AI tools without losing team decisions, and the sanction, supersession and expiry-condition rules in the sanctioned product spec. Everything described here about Arroway is behaviour the tools apply today, not roadmap. The consultancy in the example is illustrative.
https://www.arroway.app/en/answers/share-a-claude-project-with-your-team