Back to Prompt Library
implementation
Implement Hybrid Reasoning with MCP Tools
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Agentic Robotics Control
Format
Text-first
Lines
1
Sections
1
Linked challenge
Agentic Robotics Control
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Implement the core logic for your Planner agent to use hybrid instant/deep reasoning. For routine movements or immediate safety checks, use OpenAI o3 via an MCP tool for rapid responses. For complex pathfinding, object recognition, or generating novel manipulation sequences, trigger Gemini 2.5 Pro's Deep Think mode. Develop simulated MCP tools for basic robot actions like 'get_current_pose', 'move_linear', 'check_collision_risk'.
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.