Skip to main content
Back to Prompt Library
implementation

AutoGen Agent Configuration

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

Linked challenge: AutoGen & Braintrust Trade Finance Audit Agent

Format
Code-aware
Lines
10
Sections
4
Linked challenge
AutoGen & Braintrust Trade Finance Audit Agent

Prompt source

Original prompt text with formatting preserved for inspection.

10 lines
4 sections
No variables
0 checklist items
import autogen
from braintrust import Eval

# Configure AutoGen GroupChat for Trade Finance Review
config_list = [{'model': 'gpt-4o', 'api_key': 'YOUR_KEY'}]
llm_config = {'config_list': config_list, 'temperature': 0}

# Implement Document Reviewer and Compliance Auditor agents
reviewer = autogen.AssistantAgent(name='DocReviewer', llm_config=llm_config)
auditor = autogen.AssistantAgent(name='ComplianceAuditor', llm_config=llm_config)
user_proxy = autogen.UserProxyAgent(name='UserProxy', human_input_mode='NEVER')

# Build the group chat workflow here

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.