What Do I Want to Keep?

A colleague’s meeting request arrives. Suppose the system can notice it, interpret the request, check a calendar, suggest a response and send one. Even suppose it can predict which response Priya would choose. Those capabilities leave a question unanswered:

Which parts of this activity does Priya want to keep doing herself, and which does she want the system to do?

She says: “Check when I’m free and prepare a reply. I’ll decide whether this meeting belongs in the week. Show me the draft before sending.”

Her request gives different roles to different parts of the activity. She wants help gathering information and preparing a response; she keeps the judgement about the meeting and the decision to send. A single label such as “assisted” would leave those differences unspecified. The question here is how to express the division she wants without treating it as a property of her personality or mistaking it for unlimited permission.

Three questions

Three things need to be kept apart.

capability  ≠  desire  ≠  permission

Capability asks whether the system can perform a step. Desire asks whether Priya wants it to take that role. Permission asks whether it has authority to perform the particular operation. This chapter concentrates on the second question. The next examines the third.

The answers can differ. A system might be capable of selecting a meeting time while Priya wants to select it herself. A standing permission might allow calendar replies within certain bounds, while her instruction for this request requires the draft to come back to her. An allowed operation is not automatically the operation she wants performed now.

desired role  ≠  permission for every operation that could serve it

This distinction does not require two separate conversations or a special permission ceremony. “Compare these options; leave the purchase to me” can both authorise a comparison and express a division of work. The meanings remain distinct even when one sentence carries them.

Nor does the distinction make her retained steps optional until a formal grant exists. “Do not send” constrains the current interaction now. “Leave the final choice to me” cannot be ignored because the system has filed it as a preference. A desired role does not supply every positive permission, but an explicit instruction to retain a step already limits what the system can do.

Allocation across steps

The meeting request contains several distinguishable parts:

notice and interpret the request
check possible times
judge the meeting's importance
choose a response
prepare the reply
send it

Priya’s instruction assigns information gathering and drafting to the system. It keeps the judgement about importance with her and places a handoff before sending. She might also want to choose the response before any wording is prepared, or ask for two drafts while she decides. Those are different divisions of the same activity.

One possible vocabulary for describing such roles is:

observe  ·  propose  ·  prepare  ·  decide  ·  execute

These are candidate terms, not a universal ladder of autonomy. Preparing a reply need not lead to permission to send it. A new fact may send the activity back to a judgement Priya kept: the meeting turns out to require a commitment she has not considered. Progress through the task does not silently transfer that judgement to the system.

The division makes her chosen roles explicit in this example. Whether this vocabulary helps people express their wishes better than manual, assisted or automatic modes remains an open question. More detail also asks more of the person. There is no need to allocate every keystroke; the useful distinctions here are the ones that change who judges, what is prepared and where a handoff occurs.

A division of work must preserve the steps the person has chosen to keep.

One task, worked through

For a trip to Berlin, Priya wants help finding a flight. Searching, comparing, narrowing, recommending, preparing a booking and purchasing are possible parts of the activity. But their labels do not settle who supplies the criteria or decides which trade-offs matter.

agency allocation = activity + steps + conditions

She gives the dates and airports, asks the system to compare flights and says she will choose how much an earlier arrival is worth. After choosing, she wants a booking prepared for her review. She has not asked it to purchase. The division can be written down without calling every desired role a grant:

Desired participation for this Berlin trip

Activity:
- choose and arrange a flight for the stated dates and airports

Priya keeps:
- setting or revising the search criteria
- choosing the trade-off between price and arrival time
- approving the final purchase

Desired system role:
- search under the stated criteria
- compare and present relevant alternatives
- prepare a booking after Priya chooses

Conditions and handoff:
- preserve alternatives needed for the retained trade-off
- return changed terms to Priya before proceeding
- wait for the required purchase approval

This records the roles she wants for one trip. Her actual instruction supplies the comparison task and the boundary before purchase. The broader description does not, by itself, authorise every account access, reservation or transaction that might make arranging the trip easier. Those operations still need authority appropriate to them.

The handoff matters as much as the role labels. Suppose the system treats “find a good flight” as “find the cheapest flight” and removes every earlier, more expensive option. It presents three cheap departures and asks Priya to approve one. The final click remains hers, but the price-versus-arrival decision has already been made upstream.

In this constructed case, keeping the trade-off means receiving alternatives that make the trade-off possible: the cheaper later flight and the more expensive earlier one, with the relevant prices, arrival times and qualifications. If a fare is provisional or an option’s availability is uncertain, that belongs in the handoff too. Priya must be able to revise the criteria and ask for a different comparison.

This need not mean showing every flight. Filtering by criteria she has settled can serve her decision. Silently replacing an unsettled trade-off with the system’s preferred ranking can take it away. A recommendation should remain a recommendation where she has kept the choice.

Now suppose preparation reveals that the selected fare has different cancellation terms. The earlier choice does not settle the new one. Returning those changed terms to Priya preserves the judgement she retained; presenting a completed purchase for acknowledgement would not.

human handoff  ≠  approval click after the substantive choice is gone

Why someone keeps a step

Priya might keep a judgement because she has information the system lacks. But missing information is not the basis of her right to keep it. Even if a model predicts her choice correctly, she can still want to make the choice herself. Capability does not answer the participation question.

She might say, “I want to write this part because I’m practising,” or “Help me compare, but I want this commitment to be my decision.” She might enjoy the work or want to remain involved in something she owns. These are possible declared reasons for retaining a step. They are not a diagnosis inferred from her hesitation or a justification she has to supply before her instruction counts.

A declared learning objective also does not establish a learning result. Keeping a step might serve the way she wants to practise; this example does not show that the division improves skill, understanding, ownership or outcomes. It gives the system a stated objective to respect. The book has no demonstrated optimal division of human and system work to substitute for it.

Allocation belongs to the activity

The Berlin division applies to an activity under stated conditions. It does not establish that Priya is a person who “prefers low autonomy”. That would repeat Part III’s mistake of turning scoped evidence into a theory of the person.

The relevant conditions can be concrete:

activity          routine scheduling or choosing a consequential commitment
cost              a stated amount or a materially different expense
reversibility     refundable or non-refundable terms
familiarity       an established procedure or an unfamiliar one
declared time     an ordinary review or a stated deadline
stage             initial comparison or changed terms during preparation

Agency allocation belongs to the activity, not to the person as a permanent trait.

This does not require starting from nothing on every occasion. Priya can deliberately accept a division for a bounded class of activities: “For refundable hotels below this amount, prepare a comparison and ask me before purchase.” Such a standing instruction can persist within its scope. It is still different from “Priya delegates travel”.

A temporary departure needs its own bounds. “For this trip, bring every choice back to me” changes participation for this trip. It does not silently rewrite the standing division for later trips or reveal a durable psychological trait. A declared deadline may be relevant to what Priya requests; it does not license the system to infer stress and transfer decisions away from her.

The case that shows why

Suppose earlier hotel bookings were inexpensive and refundable. The system completed them under the confirmations or scoped permissions that applied at the time. Now it finds a non-refundable hotel costing €1,800. The amount and circumstances are illustrative.

It remembers the earlier bookings correctly. But if it converts them into “Priya hands hotel booking over to me”, it has invented a present allocation from a history of completed acts. If it then purchases this hotel, it has also treated that inferred allocation as authority. Neither transition is justified by the history alone.

previously authorised acts  ≠  current desired division  ≠  current authority

Even an explicitly accepted division for smaller refundable bookings would not settle this case. The new cost and terms put it outside that scope. The system should return the particular unresolved choice to Priya: consider this expense and these terms, or search for alternatives? It need not ask her to restate the dates and every already-settled criterion.

Legitimately retained observations of repeated choices might support a bounded proposal: “Would you like this division to apply to refundable hotels below the same amount?” They do not silently become a standing rule. Behaviour under a temporary mode also carries that provenance; it cannot be promoted as though it described ordinary participation.

If Priya declines the proposal, the promotion is refused. The system does not update the standing division anyway, keep learning toward that rejected update, or treat later repetition as grounds to increase its own role. Reconsideration remains something she can initiate or explicitly accept, rather than an escalation earned by frequency.

Two kinds of preference

“Use a table for exact comparisons” concerns presentation. “Research this, but let me implement it” concerns participation. The first does not determine the second. A concise view can still support a decision Priya keeps; a detailed explanation can accompany work she has chosen to hand over.

The same boundary applies to temporary context. “Be brief; I have five minutes” changes the communication request. It does not mean “Make the decision for me.” A deep-study mode does not automatically reserve every operation to her either. When a current instruction changes the division, that change has its stated scope. The system must not manufacture it from an inferred mood, fatigue or appetite for autonomy.

Communication policy can shape how a handoff is presented. It must still preserve what the retained judgement needs. Brevity is not permission to remove the alternative that makes the choice meaningful.

Where this leaves us

For the Berlin trip, the desired division is now explicit. Priya keeps the criteria, the price-versus-arrival judgement and the final purchase decision. The system’s desired role is to compare under those criteria and prepare her chosen option. The handoff must preserve the alternatives and changed terms needed for her decisions to remain real.

That is an allocation for an activity, its steps and its conditions. It is not an autonomy score for Priya. Nor does its explicitness establish that this way of describing roles is generally easier or better than broader controls; that comparison still needs evidence.

what Priya wants to keep and what she wants help with
        ↓
what the system is actually permitted to do

Her present instructions already matter. A step she has explicitly retained cannot be taken away while the system waits for a more formal account of permission. But wanting help with an activity does not authorise every operation that could advance it. Even once she has settled who should do which part, the system still has to ask a separate question about the operation before it: what has it actually been permitted to do, and within what bounds?