179babea68
Extracted from: https://github.com/jwwelbor/AgentMap.git Score: 1.0
26 lines
1.8 KiB
JSON
26 lines
1.8 KiB
JSON
{
|
|
"name": "conditional-review-workflow",
|
|
"version": "1.0.0",
|
|
"goal": "Process a user request through branching logic to approve or reject it, producing a routed decision result",
|
|
"inputs": [
|
|
"request: string - The user's request or input collected at runtime via the input agent"
|
|
],
|
|
"steps": [
|
|
"Start: Input agent collects the user request and stores it in the 'request' state field, then routes to Classify node",
|
|
"Classify: Branching agent evaluates the 'request' field and routes to Approve node on success or Reject node on failure (on_failure)",
|
|
"Approve: Default agent formats an approval message using the request and stores it in the 'result' output field",
|
|
"Reject: Default agent formats a rejection message using the request and stores it in the 'result' output field"
|
|
],
|
|
"outputs": [
|
|
"result: string - Final message indicating whether the request was approved or rejected, containing the original request"
|
|
],
|
|
"failure_modes": [
|
|
"Input collection failure - user provides no or invalid input (no explicit on_failure defined for Start node in example)",
|
|
"Branching classification failure - if branching agent cannot evaluate, it routes to Reject via on_failure configuration",
|
|
"LLM provider unavailability - if branching or agents rely on LLM backends that are misconfigured or offline"
|
|
],
|
|
"confidence": 0.85,
|
|
"explanation": "Extracted from AgentMap's documented CSV workflow example (ReviewFlow). This is a reusable conditional routing pattern that can be adapted for any approval/rejection, triage, or binary-decision scenario by modifying the branching prompt and agent types. The CSV-based declarative format makes it portable across the AgentMap framework.",
|
|
"source_repo": "https://github.com/jwwelbor/AgentMap.git",
|
|
"score": 1.0
|
|
} |