save_improvement_run
Save a full AI prompt improvement cycle for a company, including original and new prompts, client feedback, analysis, and test results, to track and refine performance.
Instructions
Save a complete improvement cycle with prompts, analysis, and test results for a specific company
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"company_name": "<company_name>",
"original_prompt": "<original_prompt>",
"new_prompt": "<new_prompt>",
"client_feedback": "<client_feedback>",
"analysis": "<analysis>",
"test_results": "<test_results>"
},
"name": "save_improvement_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| analysis | Yes | Structured feedback analysis | |
| metadata | No | Additional context (iterations, timestamps, etc.) | |
| model_used | No | Model used for testing (e.g., 'google/gemini-2.5-flash') | |
| new_prompt | Yes | Final improved system prompt text | |
| company_name | Yes | Company name in kebab-case (e.g., 'technical-life-care') | |
| test_results | Yes | Test execution results with full details | |
| client_feedback | Yes | User's description of what went wrong | |
| original_prompt | Yes | Starting system prompt text |