Back to Prompt Library
planning
LangGraph Workflow & Agent States Design
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: AI Journalist for Government Meeting Analysis
Format
Text-first
Lines
1
Sections
1
Linked challenge
AI Journalist for Government Meeting Analysis
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Design the LangGraph workflow, defining the nodes (e.g., 'Transcribe', 'ExtractEntities', 'Summarize', 'GenerateInsights') and edges, including conditional transitions. Describe the state object for the graph, outlining what information will be passed between nodes. Detail how Claude Sonnet 4 will be used in each node for its specific NLP capabilities. Ensure the design supports extended thinking for complex insight generation.
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.