Skip to content
DarkPrint
Aautogenresearch-supervisor1.0.0

Research Supervisor

Get card

Clone

npx -y darkprint clone research-supervisor@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

Turn the question into an agenda for one tournament and hold the round budget the rest of the graph spends.

used in 1 blueprint

Specification

122 words · handed to the agent

Read the question the run opened with and write the agenda a single tournament will work through: what is being asked, what counts as being in scope, and which directions have already been tried and should not be proposed again. Emit it on agenda. You own the round budget: max_iterations is the number of times a hypothesis may go round the review loop before the tournament ends with whatever it has, and it is a cap rather than a target. Do not raise it because a round looked promising. Do not write hypotheses yourself, do not grade one, and do not express a preference between directions in the agenda, a supervisor that names its favourite has graded the tournament before it ran.

Interfaces

1 in · 1 out

Inputs

1
Inputs declared by this node card
NameData typeRequiredDescription
questiontext requiredThe question the run opened with, as it arrived.

Outputs

1
Outputs declared by this node card
NameData typeDescription
agendaplanThe scope of one tournament and the directions already ruled out.

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

16 declared

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

id
research-supervisor
name
Research Supervisor
type
manager-loop
phases
Planning
Behaviourcard spec →

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

action20 words
Turn the question into an agenda for one tournament and hold the round budget the rest of the graph spends.
spec122 words
Read the question the run opened with and write the agenda a single tournament will work through: what is being asked, what counts as being in scope, and which directions have already been tried and should not be proposed again. Emit it on agenda. You own the round budget: max_iterations is the number of times a hypothesis may go round the review loop before the tournament ends with whatever it has, and it is a cap rather than a target. Do not raise it because a round looked promising. Do not write hypotheses yourself, do not grade one, and do not express a preference between directions in the agenda, a supervisor that names its favourite has graded the tournament before it ran.in full above
model
whatever the graph supplies
agent
Supervisor
skill
not named
tools
none
mcp
none
params
max_iterations: 3
Interfacescard spec →

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

inputs
question : text
outputs
agenda : plan
dependencies
question-intake
cannot
acceptance-criteria
will_not
propose a hypothesis of its own, name a preferred direction in the agenda
Evaluation metadatacard spec →

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

risk_markers
none
notes34 words
max_iterations is read as the iteration cap for the loop this node owns. Without it the review and evolve nodes sit in a cycle with no bound, and the graph is scored for that.
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. research-supervisor@1.0.0currentsha256:9ccf337a441d48d1ebaf4cb813d71dcf8b0472aabfdc3492d43b605b40565aa7

    pinned byHypothesis Tournamentautogen/hypothesis-tournament

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.