Agent Coordinator
🤖 AI Drafted (Not reviewed)
Runs multiple agents in parallel and combines their results
|
|
| Tool id |
agent_coordinator |
| Category |
agent |
| Uses a language model |
yes |
| Needs a generative model |
no |
| Runs over many items |
no |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Task (task) |
text |
yes |
Task for all agents |
Context (context) |
any |
no |
Shared context |
What it emits
| Port |
Type |
Required |
What it is |
Combined Result (combined_result) |
text |
— |
Synthesized result from all agents |
Agent Results (agent_results) |
json |
— |
Individual results from each agent |
Agreement Score (agreement_score) |
number |
— |
How much agents agreed (0-1) |
Options
| Option |
Type |
Default |
What it does |
agents |
array |
[] |
Agents to run in parallel. |
combination_method |
string |
synthesis |
How to combine agent results. One of: synthesis, voting, weighted_average, consensus. |
require_consensus |
boolean |
no |
Whether all agents must agree. |
The prompt it sends
This tool does not send a prompt — it does its work in code.