Back to prompt library
Extended Thinking Workflow Refinement
Linked challenge: Build a Context-Aware Personal Knowledge Agent
Prompt source
implementation1 lines1 sectionsNo variables0 checklist items
Refine your LangGraph workflow to incorporate extended thinking. Implement a mechanism where the agent can decide whether a query requires deeper, multi-step reasoning (e.g., using GPT-5 Pro's full capacity) or a quick, instant response (e.g., using Claude Sonnet 4). Design an 'adaptive budget' component that monitors token usage and reasoning depth, adjusting the LLM call chain dynamically.