AI Transparency Notice

Published under Article 50 of the EU AI Act and as general good practice.

You are interacting with an AI system

When you use the BlueprintPro AI plugin chat or the web chat, your messages are processed by an AI system. This system can make mistakes. Review its output — especially changes it proposes to your Blueprints — before accepting.

Models we use

BlueprintPro AI currently routes requests to Claude models from Anthropic. The specific model used per run is shown in the run header in the web dashboard.

Known limits

• The AI can hallucinate Unreal Engine API calls that do not exist. Tool outputs ground it, but always compile before shipping.
• The AI may propose correct changes for the wrong asset. Use the approval modal's asset path line.
• The AI's knowledge of Unreal has a training cutoff; for the very latest engine features, tool-based reads are authoritative.

What we do not do

• We do not use your prompts, outputs, or project data to train any model.
• We do not profile you for advertising.
• We do not make automated decisions that produce legal or similarly significant effects about you.