Roleplane — need-to-know context for your team's AI

Why teams ask for this

All or nothing

Connect an assistant to your docs or Slack and it can read everything that person can open: salaries, board notes, client files. As one engineer put it on Hacker News: "It's all or nothing."

Source ↗

Everyone sets it up alone

OAuth, API keys, kubeconfigs and SSH keys on every laptop, redone for every new hire. Another wrote: "MCP auth has been a huge pain point for us."

Source ↗

Context stuck in one assistant

Engineers in Claude Code, PMs in ChatGPT, and each tool gets its own hand-pasted picture of the company.

Same team, different context per role

Engineering's AIThe repos it works on in GitHub, Linear issues, #incidents and production logs, read-only.

Sales' AIThe sales playbook in Notion, #deals and the Proposals folder in Drive. Not the codebase.

Support's AIHelp-center docs, #support and the escalations board in Trello. Not salaries or board notes.

How it works

Connect your sources, read-only: Notion, Slack, Google Drive, Trello, GitHub, Linear, servers, Kubernetes.

For each role, pick what its AI may read — pages, channels, folders, repos, hosts — and add a few rules for how that role's AI should work.

Each person adds one link to their assistant. New hires get their role's context on day one.

Piloting now

I set up Roleplane for your team by hand, within a week.

Live, read-only access to what you pick in Notion, Slack, Google Drive, Trello, GitHub and Linear.
Servers and Kubernetes, read-only: a separate user or service account per role, a whitelist of commands, no access to secrets, every command logged, keys kept off laptops.
On request, with your admin: Jira and Confluence (paid Atlassian plans), SharePoint, HubSpot, Zendesk and read-only database views.
Anything else — legal docs, runbooks, wiki exports — as a role's knowledge pack, updated by hand.
Access is created on your side and deleted when the pilot ends; we agree on this in writing.
Works with Claude (custom connectors, including Team and Enterprise), Claude Code, Cursor and any MCP client. ChatGPT connects through custom connectors: developer mode on Plus and Pro, enabled by an admin on Business and Enterprise. Read-only is all it needs to load context.

Founding price: $150/month per team of up to 25 people, locked for 12 months.

You pay only after it works. Larger team? Tell us your size.

Request a pilot

Who's building this

I'm Danil, a developer. Right now Roleplane is me, setting up the first pilots by hand and turning them into a product. If you'd rather talk first: book a 20-min call.

Questions

Don't Claude and ChatGPT already have roles?

They control which connectors and tools a role can use, inside one vendor. In Claude, custom roles are Enterprise-only. Roleplane decides what each role's AI can read inside those sources — which pages, channels, folders and hosts — across assistants.

Isn't this what Credal does?

Yes, Credal scopes data per role too — for large companies, through a sales process. Roleplane is for teams of 10–50: set up by hand within a week, $150/month per team.

We already use Dust.

Dust's MCP server lets Claude and other clients search the Spaces a Dust user can access. If your team mostly needs company knowledge inside Claude, ChatGPT or Cursor rather than Dust's own agents, Roleplane gives each role its pages for $150/month per team, including sources Dust has no built-in connection for: Trello, servers and Kubernetes. If you build agents in Dust, keep Dust.

We already have an MCP gateway.

Gateways decide which tools a role can call. Roleplane decides which pages, channels and folders those tools return, as one more MCP server per role next to your gateway.

Can't we set up one integration or bot per role ourselves?

Yes — that's how the pilot works under the hood. What you get: someone sets it up and keeps it in sync, one place to see what each role's AI can reach, and the same setup for every assistant.

Which tools can the pilot connect?

Live and read-only: Notion, Slack, Google Drive, Trello, GitHub, Linear, servers over SSH and Kubernetes. On request, with your admin: Jira, Confluence, SharePoint, HubSpot, Salesforce, Zendesk, Intercom, GitLab and read-only database views. Anything else goes in as a role's knowledge pack. Before handing over access, we try what each role's AI must not do and send you the log of refusals.

Is it safe to let an AI read our servers?

Pilots are read-only. You create a separate user or Kubernetes service account for each role; it can run only the whitelisted commands (logs, status, the configs you pick) and cannot read secrets. The key lives on our server, not on laptops, and every command is logged. Delete the user and access is gone.

Is it safe to give you access to our docs?

Read-only, only what you pick, access deleted after the pilot, agreed in writing before we start.

What happens after the pilot?

If it works, you keep it at the founding price. If it doesn't, you pay nothing and we delete the access.

Your team's AI sees everything they can. Make it see only what it should.

One context setup for every assistant your team uses.

Decide which servers each role's AI may reach.

Engineering's AI can read