amplify

MANDATORY PREPARATION

Amplification Strategies

• Add few-shot examples for edge cases the model currently mishandles
• Add chain-of-thought for tasks where reasoning quality matters
• Add negative instructions for common mistakes
• Upgrade output schema with more structured fields

• Add tools for capabilities the model currently lacks
• Improve existing tool descriptions for better selection accuracy
• Add confirmation steps for high-stakes operations
• Add tools for verification/validation of outputs

• Add RAG for domain-specific knowledge
• Add real-time data sources for current information
• Add user profile/history for personalization
• Add project documentation as reference context

• Upgrade to a more capable model for critical steps
• Use model cascading (cheap model for simple, capable model for complex)
• Add vision capabilities if processing images/documents
• Add code execution capabilities if generating code

Amplification Process

1. Identify the gap: What can't the workflow do that it should?
2. Choose the strategy: Which amplification approach addresses the gap?
3. Implement incrementally: Add one capability at a time
4. Verify: Run the evaluation suite to confirm improvement without regression

Impact Assessment

Amplification Checklist

• Gap identified with concrete evidence (not assumption)
• Single strategy selected (don't amplify everything at once)
• Baseline quality score recorded before change
• Change implemented and tested
• Quality score improved without regression
• Cost/latency impact documented

Recommended Next Step

{{command_prefix}}evaluate

{{command_prefix}}iterate

• Amplify without a specific gap to address (amplification without purpose is bloat)
• Add capabilities without testing them
• Upgrade models without recalculating cost
• Add tools without updating tool descriptions