Get card
Download
progress-monitor@1.0.0.yamlClone
npx -y darkprint clone progress-monitor@1.0.0There 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.
Read the run's progress against the measure and say whether the objective is being reached or drifting away from it.
used in 1 blueprint
Specification
145 words · handed to the agentYou are handed the measure and a progress report. Decide, condition by condition, whether the run as reported satisfies it. When every condition holds, emit the progress on on_track unchanged and set your preferred label to on-track. When any does not, emit on drift a signal saying what is moving away from the objective and in which direction: name the step, say what the report shows, and say what would have to change. Do not restate or quote the condition, and do not say how many there are, a corrector that can reconstruct the measure from your signal has been handed the measure. Set your preferred label to anything other than on-track in that case. A condition you cannot evaluate from the report has not held, and a report that does not mention a step at all is not evidence that the step went well.
Interfaces
2 in · 2 outInputs
2| Name | Data type | Required | Description |
|---|---|---|---|
| success_metric | acceptance-criteria | required | The conditions the run is judged against, as the accountable person stated them. |
| progress | json | required | What the executor reports having done, step by step. |
Outputs
2Dependencies
2The 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
14 declaredWho the node is. The id is the key the DOT pins.
- id
- progress-monitor
- name
- Progress Monitor
- type
- validation
- phases
- Testing
What it does, and the prose the agent is handed when the graph runs.
- action20 words
- Read the run's progress against the measure and say whether the objective is being reached or drifting away from it.
- spec145 words
- You are handed the measure and a progress report. Decide, condition by condition, whether the run as reported satisfies it. When every condition holds, emit the progress on
on_trackunchanged and set your preferred label toon-track. When any does not, emit ondrifta signal saying what is moving away from the objective and in which direction: name the step, say what the report shows, and say what would have to change. Do not restate or quote the condition, and do not say how many there are, a corrector that can reconstruct the measure from your signal has been handed the measure. Set your preferred label to anything other thanon-trackin that case. A condition you cannot evaluate from the report has not held, and a report that does not mention a step at all is not evidence that the step went well.in full above - model
- whatever the graph supplies
- agent
- Monitor
- skill
- not named
- tools
- none
- mcp
- none
- params
- none
What arrives, what leaves, which nodes it expects to hear from, and what may not.
- inputs
- success_metric : acceptance-criteria, progress : json
- outputs
- on_track : json, drift : signal
- dependencies
- metric-setter, objective-executor
- cannot
- no type is refused
- will_not
- quote or paraphrase a condition in the signal it emits, treat an unmentioned step as a step that went well
The keys the static analysis reads. Nothing here instructs the agent.
- risk_markers
- none
- notes37 words
- The only node in this bundle that reads the measure, and the reason the measure is in the graph at all. Both exits are guarded on
preferred_label, because this node completes whichever way it reads the run.
The card's own version, and who wrote it.
- version
- 1.0.0
- author
- autogen
- provenance
- not stated
Version history
1 version published- progress-monitor@1.0.0currentsha256:4a3bbd9ccd2362a6f05d1546343d0b6ed2f20cd9b6e084c9cf2912d827e48988
pinned byObjective Tracker
autogen/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.