Back to Prompt Library
implementation

Implement ReAct Agents with Hybrid Reasoning & MCP Tools

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Robotic Safety Oversight System with Langroid and Claude Opus 4.1 for Lyte

Format
Text-first
Lines
1
Sections
1
Linked challenge
Robotic Safety Oversight System with Langroid and Claude Opus 4.1 for Lyte

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Implement the 'Sensor Interpreter' and 'Risk Assessor' agents using Langroid with ReAct patterns. The Sensor Interpreter should use MCP tools to access simulated sensor data (e.g., 'get_lidar_readings', 'analyze_camera_feed') and use OpenAI o3 for quick interpretations. The Risk Assessor should receive these interpretations, query Haystack for relevant safety protocols, and use Claude Opus 4.1 for deeper reasoning to identify hazards and potential risks.

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.