SDAC Prompt Tuner Agent
Overview
The Prompt Tuner Agent is an analysis-only agent used exclusively within the Prompt Tuning Workflow. It analyzes user feedback patterns and proposes targeted revisions to other agents' system prompts.
- Registry ID:
sdac_prompt-tuner-agent - Profile ID:
sdac-prompt-tuner - Tools: None (analysis-only -- all data provided directly in the input)
How It Works
The agent receives a JSON payload containing:
- Target agent ID -- Which agent's prompt to revise
- Feedback statistics -- Aggregate ratings, category breakdown, distribution
- Recent feedback -- Individual feedback items with response previews
- Current prompt -- The target agent's current system prompt
It analyzes feedback patterns across these categories:
| Category | What It Detects |
|---|---|
| Accuracy | Agent provided incorrect information or misinterpreted data |
| Clarity | Confusing, overly verbose, or hard to parse responses |
| Relevance | Missed the point or addressed wrong concerns |
| Helpfulness | Failed to provide actionable guidance |
| Tone | Communication style inappropriate for audience |
Output Format
The agent returns strict JSON:
{
"promptProposed": true,
"revisedPrompt": "Complete revised system prompt...",
"rationale": "Explanation of changes and why",
"confidenceScore": 0.85,
"feedbackSummary": "Summary of feedback patterns found",
"changesApplied": ["Improved clarity of fringe analysis instructions", "Added example format"]
}
Revision Rules
The agent follows strict constraints when revising prompts:
- Preserves all tool usage instructions, parameter descriptions, and report ID extraction logic
- Preserves the target agent's fundamental role and domain scope
- Focuses changes on communication style, response structure, specificity, and examples
- Makes minimal, targeted changes -- every change must be traceable to specific feedback
- Conservative by default -- mixed or contradictory feedback produces smaller changes
Decision Logic
| Condition | Action |
|---|---|
| Overwhelmingly positive feedback (avg > 4.0) | promptProposed: false -- no changes needed |
| Mixed/contradictory feedback | Minimal changes, confidenceScore < 0.3 |
| Clear improvement patterns | Targeted revisions, confidenceScore > 0.5 |
| Errors preventing analysis | promptProposed: false with explanation |
Integration
This agent is not invoked directly. It is called by Step 3 of the Prompt Tuning Workflow, which handles all orchestration, safety gates, and audit logging.