Back to Prompt Library
planning
Design LangGraph Workflow Architecture
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: LangChain-Powered Megaproject Procurement Risk Agent for Qiddiya Infrastructure
Format
Text-first
Lines
1
Sections
1
Linked challenge
LangChain-Powered Megaproject Procurement Risk Agent for Qiddiya Infrastructure
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Design a stateful LangGraph workflow for evaluating procurement risks in megaprojects like Qiddiya. Define the state object using Pydantic (`ProcurementState`), including fields for `po_data`, `risk_score`, `risk_factors`, and `messages`. Write Python code initializing `StateGraph` from `langgraph.graph` and configuring nodes for `document_parsing`, `compliance_check`, and `risk_scoring`.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Tune next
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Verify after
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.