II.
Responsibility overview
Reference · liveresponsibility:ai-tooling-evaluation
AI Tooling Evaluation overview
Evaluate new AI agent products, models, and SDKs for fit — run benchmarks, assess integration cost, and publish recommendations.
Attributes
displayName
AI Tooling Evaluation
cadence
on-demand
description
Evaluate new AI agent products, models, and SDKs for fit — run
benchmarks, assess integration cost, and publish recommendations.
Outgoing edges
held_by2
- role:ai-champion·RoleAI Champion
- role:ml-engineer·RoleMachine Learning Engineer
requires_expertise2
- skill-area:eval-driven-development·SkillAreaEval-Driven LLM Development
- skill-area:tool-use·SkillAreaLLM Tool Use
Incoming edges
holds_responsibility1
- role:ai-champion·RoleAI Champion
supports_work4
- tool:ora-agent-readiness·ToolOra Agent Readiness
- tool:zapier·ToolZapier
- tool-server:mcp-smithery-registry-candidate·ToolServerSmithery MCP registry candidate
- tool-server:ora-feedback-mcp·ToolServerOra feedback MCP
triggers_responsibility6
- workflow:rag-pipeline-evaluation·WorkflowRAG Pipeline Evaluation
- workflow:ai-agent-adoption-rollout·WorkflowAI Agent Adoption Rollout
- workflow:trend-forecasting-cycle·WorkflowTrend Forecasting Cycle
- workflow:llm-eval-pipeline·WorkflowLLM Evaluation Pipeline
- workflow:support-tooling-review·WorkflowSupport Tooling Review
- workflow:ai-agent-adoption-rollout·WorkflowAI Agent Adoption Rollout