implementation

Agent Initialization and Tool Definition

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

Linked challenge: Multi-modal Dexterity Planner for Humanoid Grippers using OpenAI Agents and o3

Format

Text-first

Lines

Sections

Linked challenge

Multi-modal Dexterity Planner for Humanoid Grippers using OpenAI Agents and o3

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Initialize an OpenAI Agent using the `openai-agents` SDK. Define a set of tools: `get_scene_state()`, `calculate_inverse_kinematics()`, and `apply_motor_torque()`. Use the o3 model to decide which motor torque to apply based on a text description of a fragile object's position.

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

Multi-modal Dexterity Planner for Humanoid Grippers using OpenAI Agents and o3

Inspired by the recent advancements in human-level dexterity from KinetIQ Ascend and the HIVE Physical AI initiatives, this challenge tasks you with building an autonomous robot controller. You will use the OpenAI Agents SDK and the o3 model to create a system that can interpret complex visual scene descriptions and orchestrate high-precision manipulation tasks. The goal is to bridge the gap between high-level reasoning (LLM-based planning) and low-level physical control. You will implement a tool-calling architecture where the agent interacts with a simulated environment. The agent must analyze a 'scene state' (textual representation of a visual scene graph), determine the optimal grasp strategy, and invoke specific Reinforcement Learning (RL) policy functions. This mimics real-world scenarios where humanoids must 'read the room' and adapt their dexterity dynamically based on object geometry and environment constraints.

Open challenge

Related prompts

Browse library

Problem Definition and Requirements Gathering

To establish a clear understanding of the problem space and define comprehensive requirements for the AI solution.

AI Solution Architecture and Strategy

To create a comprehensive technical architecture and AI strategy that guides the implementation of the solution.

Implementation Plan and MVP Development

To provide a clear, actionable roadmap for implementing the AI solution from concept to deployment.