Your senior people can’t be in every review.
Their judgment can.
Your strongest people already answer these questions well. Put how they decide on a shelf only your team can open, and every colleague’s AI consults them before it answers — without booking an hour of their week.
- Invited addresses onlyexact emails you type, never a whole domain
- Never in the public marketplacenot in the catalog, the sitemap or search
- Access ends when you remove someonemembership is re-read on every call
Free during beta.
What changes for the team
The standard travels
One person’s way of reviewing a contract, scoping a release or pricing a deal stops being something the rest of the team gets by working next to them. Their AI reads it instead, on the decisions the rest of the team is making today.
The answer is your answer
A general model answers with the average of the internet. A colleague’s Decision Model carries the calls your company actually made — including the ones where you departed from the obvious answer, which is the only place the advice can differ.
It says where you have no position
Outside what the model covers, the agent is told to say so rather than improvise in your senior person’s voice. Coverage is a statement, not a guess.
Nobody is on call
No notification reaches the expert, no queue forms, and nothing waits on them being free. What their colleagues consult is the model.
How it works
Start a workspace
Name it and you own it. The person who creates it is the owner; nothing is shared until they invite someone.
Invite by work address
Exact addresses, up to fifty at a time — no domain wildcards, because inviting everyone at a domain invites contractors, aliases and whoever registers next.
Your experts publish to the shelf
They build a model from decisions they already made, in the AI assistant they already use, and choose your workspace instead of the marketplace at the moment they publish.
Colleagues connect their own AI
Each member takes their own connection from the workspace page and adds it to Claude, Cursor, ChatGPT or whatever they already work in.
Who can read it
Enforced on the wire, on every call — not by a listing preference.
- The uninvited get the answer a wrong address gets. Not “forbidden”, which would confirm the model is there. The same 404 a slug that never existed returns.
- Removing someone ends it on their next call. Membership is re-read every time, so access stops when you remove them rather than when their key expires.
- Each connection is bound to one member. A workspace connection opens that workspace’s models and nothing else; an ordinary personal connection opens none of them.
- avva never receives your source material. Your expert’s own assistant reads their work in place. Only decisions they approved are used to fit the model, and what we store is the finished model.
Full detail in the Privacy Center. We do not claim perfect automatic anonymization, because nobody can — review before publishing stays with the expert, and the page says so at the moment they publish.
Roles, and there are two
Written out rather than implied, because the gap matters more to an evaluator than a grid of capabilities would.
Owner
Invites and removes members, sees who is on the list, and sees how often the shelf’s models are consulted. One owner: the person who created the workspace.
Member
Opens the shelf, takes their own connection, and consults any model on it. They do not see the member list, and they do not see usage.
There is no third tier, no group and no per-model permission yet. Single sign-on, directory sync and exportable audit logs do not exist — if your review needs them, tell us what it needs before you start.
What it costs
Free during beta. Your experts build their models on the AI subscription they already pay for, and avva runs no model of its own in the middle — so nothing here is metered against a plan.
Buying for yourself rather than a team? Read that half.