Back to Prompt Library
planning

Initial System Architecture Design

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

Linked challenge: MCP-Enabled AI for Luxury Authenticity on TikTok Shop

Format
Text-first
Lines
1
Sections
1
Linked challenge
MCP-Enabled AI for Luxury Authenticity on TikTok Shop

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design the overall architecture of your multi-modal luxury item authenticity verification system. Detail the LangGraph nodes, their responsibilities (e.g., Image Analyzer, Metadata Validator, Provenance Tracer, Decision Maker), and how they communicate. Specify the role of Gemini 2.5 Pro within these nodes and how MCP will facilitate tool integration for external data sources (e.g., blockchain, product databases).

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 role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.