# Ask where it appears

> You decide what the work is for, as described in worth before work, while the shape of the work is left to the model.

Page: Methodology · Plan
Canonical: https://banes-lab.com/disciplined-methodology/plan#ask-where-it-appears

This section is stop 24 of 102 in the learning route. Previous: [14 - Execute the template](https://banes-lab.com/disciplined-methodology/plan/execute-the-template.md). Next: [16 - When rules collide](https://banes-lab.com/disciplined-methodology/plan/when-rules-collide.md). It builds on [02 - Who does what](https://banes-lab.com/disciplined-methodology/start/who-does-what.md).

You decide what the work is for, as described in [worth before work](https://banes-lab.com/disciplined-methodology/plan/worth-before-work.md), while the shape of the work is left to the model. When a question crosses from the model's side to yours, the model is asked to raise it at the point where it appears, before any work that depends on it, because a decision the model makes without asking is an assumption. [D1·a three fates](https://banes-lab.com/disciplined-methodology/plan#ask-where-it-appears-panel-a) shows where an uncertainty can go.

### The pause, not the rework

A question that is never asked turns into an assumption, and the work then rests on a decision that neither you nor the model made on purpose, which the ontology calls [unowned risk](https://banes-lab.com/records/arch/unowned-risk.md). The model guesses the missing decision, builds a day of work on the guess, and mentions the guess in a footnote at the end. Asking feels like slowing down, and the model and the developer both tend to prefer momentum to a pause.

For this reason the model is asked to raise a question where it appears, and to state an assumption where it makes one. The cost of the pause is paid at the uncertainty, rather than the cost of the rework after it. In practice, the model is asked to raise an uncertainty as soon as it would change what gets built, with a recommendation placed first and its reasoning given, and with the other options as real alternatives whose cost is stated. While the answer is pending, the model is asked to do the parts that do not depend on it. When the model runs as a bounded agent with no channel back to you, it is asked instead to state the uncertainty and the assumption it took, name what would settle it, and return it as one of the [handoff signals](https://banes-lab.com/pag/orchestration/handoff-signals.md) typed on the grammar page.

To check this, look at the questions the model raised in a session and where in the work each one landed. A question that arrived after the work depending on it was an assumption reported late. A bounded task with a clear contract returns a result rather than a question, since questions are for decisions that belong to you, not for ones the contract has already made. A question about what the project is for is almost always yours, while a question about how something should be shaped rarely is.

Questions go through the harness's question tool, which has a fixed shape, and a question that does not go through the tool is treated as not asked. The reason is practical: a question in chat prose is easy to scroll past, while the tool presents it as a decision you can take in one read. Each call carries only a few questions, each with options you can hold in mind at once. The first option is the recommendation, and its description gives the reasoning as well as the choice. The other options are genuine alternatives that say what happens if chosen, including the cost. *It depends* does not count as an answer, and a weak recommendation is marked as weak, together with what would make it stronger.

The same uncertainty reads differently depending on when it is raised. Asked late, it reads *done, note that I assumed the second shape, let me know if you wanted the first*. Asked where it appears, it reads *two shapes fit here, I recommend the second because the first needs a second config, which one, and meanwhile I am doing the parts both share*. The first leaves you a day of work to undo, while the second leaves you a decision to make.

D1·a three fates

```mermaid
flowchart TB
appears["An uncertainty appears"]
changes{"Does the answer change what gets built?"}
contract{"Does the contract already decide it?"}
seat{"Is there a channel to ask?"}
ask["Ask now, with a recommendation first"]
state["State the assumption, name what would settle it, return"]
shared["Do the parts every answer shares"]
proceed["Return a result, no question"]
assume["Assume, and the work rests on a guess"]
appears --> changes
changes -- no --> proceed
changes -- yes --> contract
contract -- yes --> proceed
contract -- no --> seat
seat -- yes --> ask --> shared
seat -- no, a bounded run --> state
changes -. skipped .-> assume
```

## Links to

- [Worth before work](https://banes-lab.com/disciplined-methodology/plan/worth-before-work.md)
- [Handoff signals](https://banes-lab.com/pag/orchestration/handoff-signals.md)
- [Unowned Risk](https://banes-lab.com/records/arch/unowned-risk.md)

## Linked from

- [The developer and the model](https://banes-lab.com/disciplined-methodology/collaborate/the-human-and-the-ai.md)
- [Agents as executed contracts](https://banes-lab.com/disciplined-methodology/collaborate/agents-as-executed-contracts.md)
- [A turn never ends to wait](https://banes-lab.com/disciplined-methodology/collaborate/a-turn-never-ends-to-wait.md)