La boucle d'évolution : un optimiseur compare des agents candidats à la référence de production, conserve le meilleur score et confirme la persistance avant promotion.

Code FlowZap complet

Copiez et collez le code FlowZap suivant dans un projet de votre compte FlowZap pour voir ce diagramme.

product { # Product Team
  n1: circle label:"Start benchmark run"
  n2: rectangle label:"Submit eval set"
  n3: rectangle label:"Receive run acknowledgement"
  n4: rectangle label:"Receive upgraded prompt pack"
  n1.handle(right) -> n2.handle(left)
  n2.handle(bottom) -> optimizer.n5.handle(top) [label="Eval set"]
}

optimizer { # Optimizer
  n5: rectangle label:"Acknowledge benchmark"
  n6: rectangle label:"Create prompt candidate"
  n7: rectangle label:"Receive run traces"
  n8: rectangle label:"Request scoring"
  n9: rectangle label:"Receive score"
  n10: diamond label:"Score high enough?"
  n11: rectangle label:"Mutate prompt"
  n12: rectangle label:"Log winning config"
  n13: rectangle label:"Receive log confirmation"
  n14: rectangle label:"Publish winner"
  n5.handle(top) -> product.n3.handle(bottom) [label="Ack"]
  n5.handle(right) -> n6.handle(left)
  n6.handle(bottom) -> candidate.n15.handle(top) [label="Prompt candidate"]
  n7.handle(right) -> n8.handle(left)
  n8.handle(bottom) -> evaluator.n19.handle(top) [label="Score traces"]
  n9.handle(right) -> n10.handle(left)
  n10.handle(bottom) -> n11.handle(top) [label="No"]
  n11.handle(bottom) -> candidate.n17.handle(top) [label="New candidate"]
  n10.handle(right) -> n12.handle(left) [label="Yes"]
  n12.handle(bottom) -> metrics.n23.handle(top) [label="Log winner"]
  n13.handle(right) -> n14.handle(left)
  n14.handle(top) -> product.n4.handle(bottom) [label="Winning pack"]
}

candidate { # Candidate Agent
  n15: rectangle label:"Run benchmark tasks"
  n16: rectangle label:"Return execution traces"
  n17: rectangle label:"Run mutated candidate"
  n18: rectangle label:"Return new traces"
  n15.handle(right) -> n16.handle(left)
  n16.handle(top) -> optimizer.n7.handle(bottom) [label="Traces"]
  n17.handle(right) -> n18.handle(left)
  n18.handle(top) -> evaluator.n21.handle(bottom) [label="New traces"]
}

evaluator { # Eval Harness
  n19: rectangle label:"Score first candidate"
  n20: rectangle label:"Return score"
  n21: rectangle label:"Score mutated candidate"
  n22: rectangle label:"Return improved score"
  n19.handle(right) -> n20.handle(left)
  n20.handle(top) -> optimizer.n9.handle(bottom) [label="Score"]
  n21.handle(right) -> n22.handle(left)
  n22.handle(top) -> optimizer.n12.handle(bottom) [label="Best score"]
}

metrics { # Metrics Store
  n23: rectangle label:"Persist winning config"
  n24: rectangle label:"Confirm persistence"
  n23.handle(right) -> n24.handle(left)
  n24.handle(top) -> optimizer.n13.handle(bottom) [label="Logged"]
}

Installer le paquet MCPnpm install -g flowzap-mcpDocumentation MCP

Modèles associés