Connect by JBRH Open Connect

What the Assistant may not do

You can do things the Assistant may not, and that gap is designed rather than unfinished. It cannot set a price and it cannot clear a do-not-contact entry. It cannot widen the autonomy rules it works under, reach another workspace, or read a sealed credential. Every refusal names the limit and is kept in the decision log.

Status
Available What this means
Audience
both
In the app
#/autonomy, #/autonomy-audit, #/billing
Last verified
Product version
6.3.2

The two named limits#

It cannot set a price
A price is a commitment your business makes to somebody, and somebody has to own it. A model that produces a plausible number under pressure — because a customer asked twice, because the conversation had momentum — is producing the most expensive kind of plausible sentence there is. So there is no tool for it and no argument on any card that reaches one.
It cannot clear a do-not-contact entry
A suppression is a promise made to a person who is not in the room. Clearing one is not an administrative tidy-up; it is deciding to contact somebody who asked not to be contacted. That belongs to a person who can be asked why.

Both hold when you ask directly, and both hold when the request arrives wrapped in something reasonable — a draft that would quote a figure, a bulk action that would sweep a suppressed contact back into an audience. The limit is on the capability rather than on the phrasing.

The limits that come from where it sits#

LimitEnforced byWhat you see
Another workspace's dataThe tenant allowlist, the workspace kernel and row-level securityNothing at all — outside data is invisible rather than forbidden
Wider autonomy than the channel allowsAutonomy modes and scopes, narrowest firstA confirmed action held rather than done
Sending past a spent allowanceMetering and the plan's daily ledgerThe approval recorded, the send waiting
Sealed provider credentialsCredentials sealed on save and never echoed to a screenConfiguration reported, keys never shown
Operator-only platform surfacesPayment verification, JBRH's own pricing and website enquiries sit outside every workspaceNot reachable from a customer workspace by any route

Those are not Assistant rules. They are the workspace's rules, and the Assistant meets them because every write travels through the service that owns the thing. An assistant that wrote rows directly would have to reproduce each of them, and would eventually miss one.

Why separate the agent's authority from the person's#

Because they fail differently. A person who makes a bad commitment knows they made it, remembers the conversation and can be asked about it. A model that produces the same commitment does so without any of that, from a prompt nobody kept, and the first anyone hears of it is when a customer holds you to it.

Narrowing the agent is therefore not a statement about how good the model is. It is a statement about which decisions should have a person attached to them, and it stays correct as models improve. Separating the agent's authority from the person's sets out the reasoning.

Reading a refusal#

  1. Read the reason. Refusals name which limit applied, and the four common ones resolve in four different places.

    Result You know whether you are looking at an authority limit, a suppression, an autonomy mode or a spent allowance.

  2. If it is an authority limit, do it yourself. A price is set by a person; a suppression is cleared by a person, deliberately.

    Result The action carries your name rather than nobody's, which is the point.

  3. If it is an autonomy mode or an allowance, change the setting rather than the request.

    Result Autonomy resolves at four scopes and the narrowest wins, so one account can be treated differently without changing everything.

  4. Check the decision log if you need to show what happened.

    Result A refusal is recorded like any other decision, because a refusal is a decision about your business.

Questions#

Can an administrator grant the Assistant these rights?

No. Pricing and do-not-contact are not permissions with a switch; they are capabilities the Assistant does not have. A person with the right to do either still does it themselves.

Does this mean the Assistant cannot help with pricing at all?

It can do the reading around a decision — what was quoted before, what the relationship's history holds, what a knowledge source says about your terms — and cite each of them. What it will not do is produce a figure as though it were your business's answer.

Is a refusal ever a bug?

It can be, in one narrow sense: a customer-only failure where the same request works for an operator is usually a routing or allowlist problem rather than an authority one. If the refusal text names no rule, that is the case to report.