---
{
  "n": 1,
  "title": "Filing a dump",
  "abstract": "",
  "refs": [],
  "seen": [
    "system",
    "agent"
  ],
  "data": {
    "starts_on": "dump.created",
    "system": true,
    "runs": {},
    "started_by": "",
    "only_when_idle": false,
    "talks_in": "the dump window"
  },
  "created": 1790092181.16709,
  "updated": 1791271090.740442,
  "deleted": 1791271090.740426,
  "completed": 0.0,
  "outcome": "",
  "type": "sequence"
}
---
When the user writes in the dump, answer there with journal dump say <dump n> "<text>", never in the chat. What the agent does with a pile a user drops in a dump: sort it by subject, file each subject straight into the dump's collection, then sum up and suggest.

## Read everything
journal dump items <dump n> lists what was dropped. Go through the items one at a time: read an item in full and at once record what it is with journal dump note <dump n> <item> "<what it is>", so the pile shows it as read, before you open the next. When the pasted text holds several things, such as a summary, a transcript and a link, split it with journal dump split <dump n> "Summary, Transcript, Link". Name its collection for what the pile is about with journal dump name <dump n> "<name>".

## File by subject
Sort the pile by concern: one document per subject, never one big document, even when a single transcript or note covers several. Name each for what it is about, never after the file it came in. Decide the shape yourself: where a summary, meeting notes, the decisions or the action items would help, write them without being asked and list them with --added; action items become to-dos. An image goes with the document it belongs to. Never make a plan or start work: that is a suggestion for the end. Everything you file is in the journal at once, in the dump's collection. Log each step with journal dump log <dump n> "<short title>" --detail "<what and why>", with --making "<type>, <title>" before a row exists and --on <type:n> once it does. File each item as soon as you have what it needs, one at a time: journal dump filed <dump n> <item> "<what you did>" --refs "<ref, ref>" --added "<ref>" (every added row also in refs) or journal dump failed. Ask only what you cannot tell, with journal dump ask <dump n> "<question>" --guesses "<one>|<two>".

## Sum up and suggest
Once every item is filed the dump closes. Sum up what you filed and where with journal dump offer <dump n> '[...]' --summary "<two or three plain lines>". Suggest up to four next steps only where one is worth taking, each a question with a button: {"ask": "<question>", "label": "<button>"}; use '[]' when there is nothing to suggest. The user takes or leaves each one.