Skip to main content
Back to Prompt Library
implementation

Build AutoGen MHS Hardware Allocation Agent

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

Linked challenge: AutoGen MHS Workload Profiler & Accelerator Allocation Engine

Format
Code-aware
Lines
5
Sections
4
Linked challenge
AutoGen MHS Workload Profiler & Accelerator Allocation Engine

Prompt source

Original prompt text with formatting preserved for inspection.

5 lines
4 sections
No variables
0 checklist items
import autogen

config_list = [{'model': 'deepseek-reasoner', 'api_key': 'YOUR_API_KEY', 'base_url': 'https://api.deepseek.com/v1'}]

user_proxy = autogen.UserProxyAgent(name='user_proxy', human_input_mode='NEVER')
hardware_agent = autogen.AssistantAgent(name='hardware_analyst', llm_config={'config_list': config_list})

# Construct prompt to parse MHS device profiles and calculate roofline model limits

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.