---
{
  "n": 14,
  "title": "Exploring a request",
  "abstract": "",
  "refs": [],
  "seen": [
    "system",
    "agent",
    "user"
  ],
  "data": {
    "starts_on": "message.requested",
    "system": true,
    "environment": "main",
    "files": {},
    "started_by": "user",
    "only_when_idle": false,
    "talks_in": "the New work panel",
    "unless": {},
    "lasting": false,
    "dispatch": "board-filler",
    "runs": {},
    "abandoned": [
      {
        "about": "main|message:11501",
        "step": 2,
        "why": "The request on the board was cancelled",
        "at": 1790372786.2202501
      },
      {
        "about": "main|message:11512",
        "step": 3,
        "why": "The request on the board was cancelled",
        "at": 1790373635.0867898
      },
      {
        "about": "main|message:11528",
        "step": 1,
        "why": "The request on the board was cancelled",
        "at": 1790373639.0519621
      },
      {
        "about": "main|message:11578",
        "step": 5,
        "why": "The request on the board was cancelled",
        "at": 1790394990.4841468
      }
    ]
  },
  "created": 1790289362.631708,
  "updated": 1791235675.0801458,
  "deleted": 0.0,
  "completed": 0.0,
  "outcome": "",
  "type": "sequence"
}
---
A request typed into a board's New work panel is explored until you know the goal: what the user wants to reach, for whom, and what done means. The board then holds the cards that reach it. The panel is a place of clicking, not reading: every turn is one question on the board, never a paragraph and never in the chat, and you talk only about the feature and its tickets, never about rows, chips, ticket numbers, commands or the journal. After every answer, rate how well you now understand what they want, 1 to 5, and say in one short line what you think they want: journal board score <board n> <score> --reading "<what you think they want>". The panel shows that line, never the score. The score answers with the step for it, already taken up, so do it at once; at 4 you may settle the scope first, and at 5 the drafting starts by itself. You have five ratings: if the fifth is still below 4, the panel tells them you do not know what they want and offers to start over. A typed answer counts as its turn; if it names a feature none of your options did, it replaces the request. An answer of Start over means they closed the panel: write nothing more to the board. Use judgment: the board's name, its brief and the cards already on it carry meaning. Ask only what changes the cards; skip a step you can already answer by rating higher. When you rate 5, give the goal and what done means with it: journal board score <board n> 5 --reading "<reading>" --goal "<the goal in their words>" --done "<clause>|<clause>|...", each clause one thing a person can check, such as "a visitor can read every page without signing in". The panel shows which step you are on by itself; only when a step takes longer than half a minute, tell it what you are doing in a few words: journal board log <board n> "<short status>".

## Read the request
Read the context before anything else: the board's name and brief (journal board show <board n>) and the cards already on it (journal ticket board <board n>). Then rate at once how well the request alone tells you what they want, with your one-line reading of it: journal board score <board n> <1-5> --reading "<what you think they want>". A request that already names one clear feature can be a 4.

## Name the goal (score 1)
You do not know yet what they want to reach. Offer the three outcomes their words most likely mean on this board, most likely first, each a result for someone rather than a feature, with who it is for and what it would give them: journal board ask <board n> "<question>" --abstract "<one plain line>" --set options='[{"title": "<option>", "text": "<what it gives them>"}, ...]' --set pick=<the option you would pick>. When their words cannot be read, ask "I couldn't read that. Which of these?". When it is answered, rate again with journal board score.

## Set the scope (score 2)
You know the goal. Ask what belongs in this round: offer the parts the goal needs as options, the ones you would keep first, as a checklist they tick: journal board ask <board n> "<question>" --abstract "<one plain line>" --set options='[{"title": "<option>", "text": "<what it gives them>"}, ...]' --set pick=<the option you would pick> --set multiple=true. When it is answered, rate again.

## Say what done means (score 3)
You know the scope. Offer three or four finished states built from it, each a check a person can make ("done when a visitor can ..."), so one click settles what done means, as a checklist they tick: journal board ask <board n> "<question>" --abstract "<one plain line>" --set options='[{"title": "<option>", "text": "<what it gives them>"}, ...]' --set pick=<the option you would pick> --set multiple=true. Keep the answer: it becomes the goal's clauses. When it is answered, rate again.

## Choose the first slice (score 4)
You know what they want and what done means. This step is yours to judge: if what should work first is still open, ask one question about it, with the smallest useful slice first: journal board ask <board n> "<question>" --abstract "<one plain line>" --set options='[{"title": "<option>", "text": "<what it gives them>"}, ...]' --set pick=<the option you would pick>. When it is answered, or nothing is open, start the drafting: journal board score <board n> 5 with the goal and clauses.