implementation

MCP Tool Integration for Simulated Robot Control

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

Linked challenge: Human-Robot Team Collaboration

Format

Text-first

Lines

Sections

Linked challenge

Human-Robot Team Collaboration

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Develop mock MCP-enabled tools that simulate robot actions (e.g., 'move_gripper', 'pick_up', 'report_sensor_data') and interaction with a manufacturing execution system (MES). Detail the API endpoints and data schemas, and explain how AutoGen agents will invoke these tools to control the simulated robot and update task status securely.

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.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Human-Robot Team Collaboration

Addressing the challenges of Tesla's Optimus humanoid robots, this challenge focuses on enhancing human-robot collaboration in complex manufacturing or assembly tasks. You will build a multi-agent system using AutoGen, leveraging GPT-5 for sophisticated task planning, problem-solving, and natural language understanding. The system will feature MCP-enabled tool integration for robots to interact with simulated manufacturing execution systems (MES) and access operational knowledge via RAG with vector search. The emphasis is on creating a seamless human-in-the-loop experience, allowing human operators to provide natural language feedback that the agents use for continuous learning and adaptive task allocation. HappyPath AI Engineering Tooling will be instrumental in visualizing, debugging, and optimizing these complex human-robot workflows, ensuring efficient and error-resilient operations.

Open challenge

Related prompts

Browse library

AutoGen Multi-Agent Design for Collaborative Assembly

planning

RAG with Vector Search and MCP for Knowledge Access

implementation

HappyPath Workflow Optimization and Deployment

deployment