Back to Prompt Library
implementation
Extended Thinking Workflow Refinement
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Context-Aware Personal Knowledge Agent
Format
Text-first
Lines
1
Sections
1
Linked challenge
Build a Context-Aware Personal Knowledge Agent
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 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.
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.