AccessControl
Per-document permissions that filter answers, not just pages.
What it does
Every folder and every leaf document carries an access policy: public, signed-in, or owner-approved. These policies resolve into a per-session envelope that filters what an agent can retrieve before it answers. A capability registry gates entire features per tenant, and the critical access checks fail closed.
Why it matters
Retrieval-augmented answers turn a permissions bug into a data leak with a friendly tone. Filtering the corpus before generation, rather than trying to redact afterwards, is the only version of this that holds. You cannot un-say a sentence.
How it works
The access envelope filters grounding, not just routes
Permissions narrow what the agent can retrieve, so a document you cannot open also cannot be paraphrased at you.
Critical checks fail closed
When policy cannot be resolved, the safe answer is refusal. The embed policy, for instance, falls back to "frame nowhere" rather than "frame anywhere".
Capabilities are gated per tenant
A feature registry with presets and bundles decides what a workspace can even reach, independent of document permissions.
Questions
- Can I make one document public and keep the rest private?
- Yes: policy is per leaf as well as per folder, and it applies to what the agent can retrieve, not only to what a browser can open.
- How fast does a permission change take effect?
- Policy is cached per session for performance and invalidated on change. It is fast, but it is not a guarantee about requests already in flight.
The rest of the bag
Your agent has its own inbox, not a share of yours.
Inbound arrives by webhook from an email provider. We do not run our own MX or SMTP servers.
Package
Export, share and install agents as portable archives.
Export, import, handoff links and showcase all work. There is no marketplace, no package versioning, and no signed packages.
Memory
Grounded retrieval over your own material, with receipts.
This is retrieval, not persistent agent memory. Vector grounding is code-complete; the vector deployment is still pending.
That was step 4 of 6: access narrows the corpus. Next, retrieval over your own material, documents, and whatever tools it has been given; each call priced as it happens.