Back to Prompt Library
implementation
Orchestrate Dynamic Decision Cycle with LangGraph
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Model-First Reasoning Agent for Multi-Tier Supply Chain Optimization using LangGraph & Llama 3.3
Format
Text-first
Lines
1
Sections
1
Linked challenge
Build a Model-First Reasoning Agent for Multi-Tier Supply Chain Optimization using LangGraph & Llama 3.3
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Implement the core LangGraph workflow. This should include states for 'Analyze_Demand', 'Assess_Inventory', 'Propose_Actions_Llama3.3', 'Execute_Order_Tool', 'Update_State', and a conditional edge to loop or conclude. Crucially, within 'Propose_Actions_Llama3.3', craft a detailed prompt for Llama 3.3 that provides the agent's current internal model (e.g., inventory, costs) and asks it to reason about the optimal next steps based on minimizing total cost and avoiding stockouts, explicitly requesting its reasoning trace.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.