AnalogicalReasoningTask
Solve complex problems by mapping structural relationships and insights from diverse source domains (e.g., biological systems, urban planning, music).
Reasoning
GPT-4 Preferred
Non-Destructive
⚙️ AnalogicalReasoningConfig.json
{
"source_domain": "Biological Systems",
"target_problem": "Scaling a distributed microservice architecture",
"num_analogies": 3,
"validate_mappings": true,
"input_files": ["docs/architecture_spec.md"],
"related_files": ["src/main/kotlin/com/system/Core.kt"]
}
→
👁️ Session UI: Synthesis & Recommendations
Synthesis: Mycelial Network Analogy
Key Insight: Decentralized resource allocation via chemical signaling mimics service discovery in high-latency environments.
Conceptual Mapping:
Fungal Hyphae → Network Routes
Nutrient Flow → Data Packets
Spore Distribution → Container Deployment
Nutrient Flow → Data Packets
Spore Distribution → Container Deployment
Recommended Approach: Implement a "Gossip Protocol" for state propagation based on the Mycelial signaling model to reduce central orchestrator load.
Workspace Explorer
Browse generated reasoning artifacts, transcripts, and synthesis reports in the task workspace.
TaskExecutionConfig Fields
| Field | Type | Description |
|---|---|---|
| source_domain * | String | The domain to draw analogies from (e.g., 'biological systems', 'urban planning'). |
| target_problem * | String | The specific problem to solve using analogical reasoning. |
| num_analogies | Int | Number of analogies to generate and explore. Default: 3. |
| validate_mappings | Boolean | Whether to perform a secondary validation pass for structural consistency. |
| input_files | List<String> | Glob patterns for files providing context for the target problem. |
| related_files | List<String> | Additional context files to inform the reasoning process. |
Token Usage: Medium-High (Depends on num_analogies and context size).