Back to Prompt Library
implementation
Develop Extended Thinking Risk Assessor Agent
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Autonomous EU Chips Act Project Monitoring with Claude Opus 4.1 & LangGraph MCP
Format
Text-first
Lines
1
Sections
1
Linked challenge
Autonomous EU Chips Act Project Monitoring with Claude Opus 4.1 & LangGraph MCP
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Create a LangGraph agent node (e.g., 'RiskAssessor') that uses Claude Opus 4.1 with an extended thinking pattern. This agent should receive project status and identified issues, then perform a multi-step reasoning process (e.g., 'Analyze Impact', 'Consult Policy RAG', 'Formulate Mitigation') to determine risk level and suggest solutions. Use DSPy to define the prompt for this multi-step process.
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.