implementation

Tool Integration for Trading Actions

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

Linked challenge: OpenAI o3 Smolagents for AI Infrastructure Energy Optimization

Format

Text-first

Lines

Sections

Linked challenge

OpenAI o3 Smolagents for AI Infrastructure Energy Optimization

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Develop simple Python functions that simulate 'buy_energy(units, price)' and 'sell_energy(units, price)' on a mock energy exchange. Show how your 'Trader Agent', powered by OpenAI o3, would integrate and use these tools to execute trading decisions based on market analysis from other agents.

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

OpenAI o3 Smolagents for AI Infrastructure Energy Optimization

Inspired by Meta's strategic move into electricity trading to power its AI infrastructure, this challenge focuses on building an agentic system for real-time energy procurement and consumption optimization. You will deploy a swarm of lightweight Smolagents, powered by OpenAI o3, to act as 'Energy Traders' and 'Infrastructure Managers.' These agents will dynamically interact with a simulated energy market, making informed decisions to minimize costs and ensure reliable power for AI data centers. The system will leverage Haystack for efficient RAG, allowing agents to ingest and analyze real-time energy market data, weather forecasts, and historical consumption patterns. Agents must employ adaptive thinking budgets to react swiftly to market fluctuations and make optimal trading decisions, demonstrating tool integration for interacting with mock energy APIs and internal consumption monitoring systems.

Open challenge

Related prompts

Browse library

Design Smolagent Swarm Roles

planning

Haystack RAG for Market Data

implementation

Adaptive Thinking Budget Strategy

planning