Evaluate And Improve Agent

Diagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rubrics and LLM-as-judge scoring (agent-evaluation), then diagnoses architectural problems like task-model mismatch and pipeline bottlenecks (agent-project-development), redesigns the agent topology — supervisor, swarm, or specialized agents (multi-agent-patterns), adds the right memory framework when persistence is the gap (memory-systems), and re-evaluates against the original baseline to prove improvement. Use when an existing agent is underperforming, producing inconsistent results, failing on edge cases, or costing too much per interaction. NOT for building a new agent from scratch — use the build-ai-agent workflow instead. NOT for prompt-only fixes — use prompt-engineering directly.

viktorbezdek Updated 14 repo stars

File contents

viktorbezdek/skillstack commit 6a15692491 Runs: viktorbezdek/agent-evaluationviktorbezdek/agent-project-developmentviktorbezdek/multi-agent-patterns

Frequently asked questions

npx get-skill add viktorbezdek/evaluate-and-improve-agent