UNPKG

@cloudkinetix/bmad-enhanced

Version:

Cloud-Kinetix enhanced fork of BMAD-METHOD - Breakthrough Method of Agile AI-driven Development with robust versioning and unified validation.

39 lines (38 loc) 1.86 kB
workflow: id: llm-agent-enhancement name: Research-Driven LLM Agent Enhancement description: Streamlined workflow for improving existing AI agents using research-driven optimization and enhancement techniques. type: enhancement project_types: - performance-optimization - feature-enhancement - safety-improvement - integration-upgrade - model-migration - cost-optimization approach: Research current enhancement techniques and apply evidence-based improvements with systematic validation key_phases: assess: description: Research and analyze current agent performance agents: [llm-engineer, llm-safety-governance] actions: - Research current optimization techniques and assessment methodologies - Analyze existing agent performance and identify improvement opportunities - Investigate enhancement patterns relevant to the specific use case - Prioritize improvements based on impact and feasibility enhance: description: Apply research-backed enhancement techniques agents: [llm-engineer, llm-architect] actions: - Research and implement optimization techniques based on current best practices - Apply enhancement strategies appropriate for the identified opportunities - Validate improvements using research-backed testing methodologies - Document enhancement rationale and implementation approach validate: description: Test and verify enhancement effectiveness agents: [qa, llm-safety-governance] actions: - Execute comprehensive testing using current validation standards - Verify safety and compliance requirements are maintained - Validate performance improvements against established benchmarks - Document results and lessons learned for future enhancements