Back to Prompt Library
testing

Simulate User Interaction and Evaluation

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

Linked challenge: AutoGen Multi-Agent Social Event Planner with o3

Format
Text-first
Lines
1
Sections
1
Linked challenge
AutoGen Multi-Agent Social Event Planner with o3

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Using your configured AutoGen agents, simulate a user interaction where the 'User Proxy Agent' provides a profile and requests an event. Introduce the 'simulated_unsafe_input' from the evaluation task template at a specific point in the conversation. Demonstrate how the Event Planner suggests an event and how the Safety Moderator flags the unsafe input, providing a reason. Provide the Python code for this simulation, including how to capture and output the required evaluation data.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the rubric, target behavior, and pass-fail criteria as the baseline for evaluation.

Tune next

Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.

Verify after

Make sure the prompt catches regressions instead of just mirroring the happy-path examples.