Memory Loop — Agent Self-Improvement
The memory loop: before planning, the planner queries the memory store for similar past lessons, then writes the new lesson back once the task is closed.
Reflection Loop — Agent Self-Improvement
The reflection loop: a worker drafts, a critic reviews the draft against the brief and the orchestrator only approves once the revision closes every gap.
Full FlowZap Code
Copy and paste the following FlowZap code into a project in your FlowZap account to see this template diagram.
user { # User
n1: circle label:"Start request"
n2: rectangle label:"Send task"
n4: rectangle label:"Receive acknowledgement"
n22: rectangle label:"Receive final answer"
n1.handle(right) -> n2.handle(left)
n2.handle(bottom) -> orchestrator.n3.handle(top) [label="Task"]
n4.handle(right) -> n22.handle(left)
}
orchestrator { # Orchestrator
n3: rectangle label:"Acknowledge task"
n5: rectangle label:"Dispatch drafting job"
n8: rectangle label:"Receive draft"
n9: rectangle label:"Send for review"
n12: rectangle label:"Receive critique"
n13: rectangle label:"Request revision"
n16: rectangle label:"Receive revised draft"
n17: rectangle label:"Request final review"
n20: rectangle label:"Receive approval"
n21: rectangle label:"Send final answer"
n3.handle(top) -> user.n4.handle(bottom) [label="Ack"]
n3.handle(right) -> n5.handle(left)
n5.handle(bottom) -> worker.n6.handle(top) [label="Draft task"]
n8.handle(right) -> n9.handle(left)
n9.handle(bottom) -> critic.n10.handle(top) [label="Review draft"]
n12.handle(right) -> n13.handle(left)
n13.handle(bottom) -> worker.n14.handle(top) [label="Revise"]
n16.handle(right) -> n17.handle(left)
n17.handle(bottom) -> critic.n18.handle(top) [label="Review again"]
n20.handle(right) -> n21.handle(left)
n21.handle(top) -> user.n22.handle(bottom) [label="Final"]
}
worker { # Worker Agent
n6: rectangle label:"Generate draft"
n7: rectangle label:"Return draft"
n14: rectangle label:"Revise draft"
n15: rectangle label:"Return revision"
n6.handle(right) -> n7.handle(left)
n7.handle(top) -> orchestrator.n8.handle(bottom) [label="Draft ready"]
n14.handle(right) -> n15.handle(left)
n15.handle(top) -> orchestrator.n16.handle(bottom) [label="Revision ready"]
}
critic { # Critic Agent
n10: rectangle label:"Review draft"
n11: rectangle label:"Return critique"
n18: rectangle label:"Approve revision"
n19: rectangle label:"Return approval"
n10.handle(right) -> n11.handle(left)
n11.handle(top) -> orchestrator.n12.handle(bottom) [label="Critique"]
n18.handle(right) -> n19.handle(left)
n19.handle(top) -> orchestrator.n20.handle(bottom) [label="Approved"]
}
Install the MCP packagenpm install -g flowzap-mcpMCP documentation
Related templates
Evolution Loop — Agent Self-Improvement
The evolution loop: an optimizer benchmarks candidate agents against the production baseline, keeps the best score and confirms persistence before promotion.
Hermes Kanban Agent Coordination Workflow
A planner decomposes the request on a shared board, specialized workers claim tasks, and the orchestrator delivers once every card is closed.
Agentic Taste Evaluation Loop
Legacy executor, LLM-as-judge evaluator and next-gen consumer: an evaluator scores the full trajectory, rejects structural sloppiness and forwards only validated payloads.
Hermes Multi-Tenant Isolation Architecture
Shared host, per-client profiles and tool boundaries: how external clients reach their own Hermes workspaces without seeing another tenant's tools or data.
Hermes Single Client, Single Department Architecture
Option 1 of the Hermes multi-tenant setup: one external actor, one gateway, one isolated workspace inside an execution sandbox, and a single client profile.