What people ask before signing.

The workspace where your company keeps what it knows. Documents live as Markdown files inside a folder that belongs only to your company, organized by department, with per-person permissions. On top of those files runs an AI agent that reads and writes them under the same rules a teammate follows, and every bit of usage is metered company by company.

No. Each agent chat is confined to its own project's file subtree. Parent projects and connected projects are not mounted: the agent knows them only through the summary we inject, which is the description, the memory, the open tasks and a file listing. We hardened this after finding and fixing a case where a session with no assigned path mounted the whole company folder.

Two tiers. The company role, from owner down to viewer, and the seat you hold in each department. A manager of a parent department also manages its children, because authority inherits down the tree. Sharing a single file only ever adds access, never removes it, so an exception cannot accidentally lock someone out.

Your agents' work for the month, for the whole company rather than per seat: two companies on the same plan pay the same whether they have ten people or fifty. What changes between one plan and the next is how much work fits inside, and each plan says so on its card in the measure that belongs to it. Inside the application you can see at any moment how much of your plan the month has used, which is what keeps the invoice from surprising you.

Only your agents' new work. When an agent re-reads what it already had in front of it in order to keep working, we do not charge you for that re-reading, and it is most of what happens while it works. Neither do we charge for uploading documents, indexing them, searching them, walking the graph, re-reading past conversations or messaging a colleague, because all of that runs on our own server without calling a paid model. Billed outside the plan, at what they cost: image generation, video generation and any servers you contract.

Your agents keep working: we do not cut the service off and we do not stop to ask you for anything mid-month. Work beyond the plan costs double what it costs inside the plan and it is charged on the following month's invoice, never in the middle of the month. If what you would owe for going over comes to less than 25 dollars, we do not charge it. And when it keeps happening we tell you, because past a certain point the plan above costs you less than paying the surcharge.

In a folder exclusive to your company on the server, at mode 0700. No other tenant on the platform can read it, not even at the filesystem level. Inside there is standard Markdown and the original files you uploaded. The search index and the graph are rebuildable views of that folder: delete them and they regenerate.

Yes, and it is a consequence of the design rather than a contractual promise. Your notes are .md files with wiki links and YAML metadata, readable in any text editor. The database is standard PostgreSQL and there is a daily pg_dump backup. We hand you the folder and the dump, with no paperwork and no exit fee.

Yes. Every tool the agent dispatches leaves a row with the hash of its arguments, whether it finished cleanly, how long it took, and the previous row's hash chained into this one. Editing or deleting a row breaks the chain and shows. Raw arguments are never stored, only their hash. Separately, every AI call appends a line to a monthly log file on disk that you can download.

Through the pricing page. On Basic and Pro you pick the plan, leave your company details and a work email and verify the email; a person sets up your company and writes back within one business day. On Enterprise the first step is a conversation with sales, because the volume is sized with you before anything is signed. Either way, what decides the outcome is the first week: which departments, who sees what, and which documentation goes up first.