When Should the AI Speak?

At 14:40 a candidate arrives: a new paper that may contradict an assumption in the code Priya has open in her editor. The system’s account of it is solid. The match is plausible, the evidence is attached, a brief is the right resolution, and the item is new to her. It also knows something else. She is presenting in a design review until 15:30, and the deployment the paper might affect is not until 18:00.

Delivering it now means a buzzing phone, a glance, a derailed sentence in front of colleagues. The information would be consumed at the worst possible moment, its value converted into damage. Delivering it at 15:35 means she finishes the review, opens the editor, and meets the item exactly when she can act on it, with hours to spare. Nothing was lost by waiting, and something was saved.

The earlier chapters of this part settled what could be settled about the item itself. It matters to her purpose. It is new to her. It matches a relation she asked about. It has a resolution that preserves what it must. What remains is the question this chapter takes on:

Once several items qualify for attention, when should each one be surfaced?

relevance
   ↓
qualification
   ↓
resolution
   ↓
delivery timing

Three decisions, kept apart

By now the channel is making three decisions about each item, and they are different decisions:

WHAT should be shown?      selection
HOW MUCH should be shown?  resolution
WHEN should it be shown?   timing

Keeping them separate matters because each is wrong in its own way, and a system that merges them cannot be repaired. Timing does not decide worth. An item has already qualified for attention by the time it reaches this stage, and the timing question only asks about the moment. A critical contradiction can be best held for the morning because nothing changes by waiting, while a modest note that an API has been renamed can deserve to interrupt now because she is mid-edit on exactly that call. The reverse also holds: timing must not quietly rewrite earlier decisions. A system that squeezes an item down to a glance because the queue is long, or promotes it in relevance because it is urgent, has let the last stage overrule the earlier ones without saying so.

Four ways to deliver

Delivery has at least four states, and it helps to define them by what they do, not only by when they happen.

NOW         interrupt, because delay has a meaningful cost
QUEUE       place next in line for the active task
DIGEST      accumulate for a periodic review
AVAILABLE   keep accessible, without competing for attention

NOW is the only one that takes the floor. QUEUE holds the item for the next natural break in what the person is doing, such as the end of the meeting or the moment the build finishes. DIGEST gathers items into a scheduled round-up, a morning list for example. AVAILABLE places the item where it can be found if she goes looking, in the sidecar or a list, without asking for her eyes. These states refine the three acts from the start of the part: show now, make available, withhold. Withholding remains separate: it means the item is not surfaced at all, and is not just late.

The central separation of the chapter follows:

qualifies for attention  ≠  deserves interruption

Most items that qualify should not interrupt. That is not a loss of value. It is how the channel keeps interruption meaningful.

Urgency and the cost of interrupting

Two quantities decide where an item goes, and neither alone is enough:

URGENCY              how costly is delay?
INTERRUPTION COST    how costly is surfacing now?

Urgency is about the item: how quickly its value decays. A replication of a paper she already trusts loses nothing by waiting a week. A deprecation of the function she is calling today loses value by the hour. Interruption cost is about the moment: what it costs to put something in front of her now. In the middle of a presentation it is high. In the idle minutes after a build it is low.

The two combine as starting points, not as rules:

high urgency, low cost       NOW
high urgency, high cost      NOW only if the cost of delay is larger,
                             otherwise QUEUE for the nearest break
low urgency, low cost        QUEUE or DIGEST
low urgency, high cost       DIGEST or AVAILABLE

So something highly relevant can belong in a digest if nothing changes by waiting, and something only moderately important can deserve to interrupt when a deadline or an irreversible action is close. Two more separations keep the picture clear:

importance  ≠  urgency
urgency  ≠  confidence

The first says that how much something matters is not how soon it matters. The second is easy to lose. An item can be urgent and uncertain at the same time, and when it is, the uncertainty must travel with it. A system that is unsure whether a paper contradicts Priya’s assumption, and sure only that the deployment is tonight, should say: “Possible contradiction affecting tonight’s deployment; relation unconfirmed.” It should not say: “Your assumption has been disproved.” Urgency raises the priority of surfacing an item. It does not raise the evidence for it.

What the system may know about the moment

Judging interruption cost needs some picture of the person’s situation, and this is where the question deferred from earlier chapters returns. The rule is to use the least that will do, and to use only what is declared or can be observed:

declared task        current activity       available time
deadline             device                 notification mode
calendar state       explicit do-not-disturb
consequence of delay

observable context  ≠  inferred inner state

Priya’s calendar says she is in a review. Her declared focus mode says she wants to be interrupted only for blockers and expiring information. The deployment time is a fact in the item. All of that can be used. What should not be used is an inference about her mood, stress, boredom or mental load, drawn from how she types or what her face shows. Such inferences are sensitive, error-prone, and unnecessary when a declared mode or an observable constraint will do.

The person should be able to set the policy herself, in plain terms, and change it:

Focus mode: interrupt me only for
[x] blockers on my current task    [x] information that expires soon
[ ] contradictions                 [ ] new implementations
Everything else: morning digest

Every interruption explains itself

An interruption that cannot say why it happened is a machine making a judgement the person cannot check. So each one should answer a plain question: why did this appear now?

Why did you interrupt me?
Because: it affects the function you have open; it expires before
your next digest; the match is moderate and unconfirmed.
[send these later]   [never interrupt for this relation]

An account like that exposes what matched, which standing interest it served, why waiting would have cost something, what confidence the system had, and why this delivery mode was chosen. It makes delivery inspectable, and it gives the person something to correct. Corrections such as “send these later” or “not for this kind of thing” are the system’s best evidence about whether its policy is right. They are better evidence than whether she opened the notification, because an item opened at once may have been a bad interruption that she was too polite, or too curious, to ignore.

How delivery goes wrong

The failures are easy to name:

too eager       everything becomes NOW
too timid       urgent items wait in AVAILABLE
wrong urgency   importance mistaken for time sensitivity
wrong context   the system interrupts at a high-cost moment
opaque timing   she cannot tell why this appeared now

The first is the one to watch. If everything interrupts, the whole routing system has collapsed, because interruption carries information only while most things do not. A neighbouring failure is subtler: a single priority score, built by multiplying everything together, that quietly takes over the decision. Once one number dominates, the separate judgements about relevance, novelty, resolution and urgency stop being separate, and no one can tell which one decided.

Where this leaves us

Delivery is its own decision, alongside selection and resolution. Items that qualify can be delivered now, queued, gathered into a digest or left available, and qualifying for attention is not deserving interruption. The choice balances the cost of delay against the cost of surfacing, with importance kept separate from urgency and urgency from confidence, so that uncertainty travels with the item. Context should be declared or observable and never an inference about inner states, and every interruption should be able to say why it appeared now.

With those three decisions, what, how much and when, a channel can handle a single item well. The harder case is the usual one. In any real hour several items qualify at once, each with its own urgency and its own cost, and some of them compete: two deadlines, a contradiction and a blocker, a standing interest that fires while she is dealing with another. The system still has to decide what happens when its obligations collide. That is where the pieces of this part have to be put together and set against one another.