Skip to content
DarkPrint
Aautogenoutcome-delivery1.0.0

Outcome Delivery

Get card

Clone

npx -y darkprint clone outcome-delivery@1.0.0

There is no repository and no history behind a card. Download hands you the document as it stands, and Clone fetches the same document by name.

↓ 0 downloads

Report the finished run to the people who set it going, and record that it went.

used in 1 blueprint

Specification

93 words · handed to the agent

Take what arrives on on_track and report it to the owner and to the person accountable for the measure. Report what the run actually did, step by step, including any step that was corrected on the way: a run that reached its objective after two corrections is a different result from one that reached it first time, and both are worth reporting as what they were. Do not restate the measure in the report. Emit a receipt on receipt saying what was reported and when. Report nothing that did not arrive on on_track.

Interfaces

1 in · 1 out

Inputs

1
Inputs declared by this node card
NameData typeRequiredDescription
on_trackjson requiredThe progress the monitor accepted, unchanged since it accepted it.

Outputs

1
Outputs declared by this node card
NameData typeDescription
receiptstatusWhat was reported and when, or the reason nothing was.

Dependencies

1

The upstream nodes this card expects to receive from. Whenever a blueprint pins this card, each name is checked against a real edge in that graph. A name without a link is not a published card; it refers to a node inside some graph.

Card values

17 declared

Who the node is. The id is the key the DOT pins.

id
outcome-delivery
name
Outcome Delivery
type
tool
phases
Deployment
Behaviourcard spec →

What it does, and the prose the agent is handed when the graph runs.

action16 words
Report the finished run to the people who set it going, and record that it went.
spec93 words
Take what arrives on on_track and report it to the owner and to the person accountable for the measure. Report what the run actually did, step by step, including any step that was corrected on the way: a run that reached its objective after two corrections is a different result from one that reached it first time, and both are worth reporting as what they were. Do not restate the measure in the report. Emit a receipt on receipt saying what was reported and when. Report nothing that did not arrive on on_track.in full above
model
whatever the graph supplies
agent
Delivery
skill
not named
tools
Messaging
mcp
slack
params
none
Interfacescard spec →

What arrives, what leaves, which nodes it expects to hear from, and what may not.

inputs
on_track : json
outputs
receipt : status
dependencies
progress-monitor
cannot
acceptance-criteria
will_not
restate the measure in the report it sends, hide a correction the run needed on the way
Evaluation metadatacard spec →

The keys the static analysis reads. Nothing here instructs the agent.

risk_markers
irreversible-action
notes
none
Service fieldscard spec →

The card's own version, and who wrote it.

version
1.0.0
author
autogen
provenance
not stated

Definitions for every card field

Version history

1 version published
  1. outcome-delivery@1.0.0currentsha256:082945eb3e86304f3c7b39504c3f2a742b9eeebdaffde2a9f659cf119d1dd524

    pinned byObjective Trackerautogen/objective-tracker

A digest is a fingerprint (SHA-256) of the card's content, computed without the author and provenance fields. The same card from two people gets the same digest; any edit gets a new one.

First published version, so there is nothing to compare yet. Versions are never edited in place: the next change arrives as a new version, and the differences between the two documents are listed here.

Community notes (0)

No notes yet.

Nobody has posted about this node card yet.

Sign in to post a note.