Back to Prompt Library
implementation
Configure AutoGen Design Team
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: AutoGen Design Orchestrator with TensorRT-LLM and BentoML
Format
Text-first
Lines
1
Sections
1
Linked challenge
AutoGen Design Orchestrator with TensorRT-LLM and BentoML
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Set up an AutoGen GroupChat with two agents: 'Designer' (Claude Sonnet 4.6.6) and 'Reviewer' (GPT-5.4 Pro). The Designer should focus on creating SVG/Slide layouts, and the Reviewer should critique for brand alignment based on the Techmeme headline about World (identity verification).
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.