数据隐私和保留
Alteryx Copilot retains message history for 90 days and encrypts Copilot data in transit and at rest. This section defines Copilot access scope and usage controls with Google Gemini.
Alteryx 会保留 90 天内的消息历史记录。如需详细了解 Alteryx 的安全性和数据隐私，请查看 Alteryx Copilot 的常见问题解答，或访问 Alteryx Trust 页面。
Alteryx Copilot 如何使用 Google Gemini 生成响应
Alteryx Copilot 使用 Google Cloud 的 Vertex AI 平台上托管的 Google Gemini 模型来生成响应。因此，Copilot 的安全性、隐私保护及数据处理控制均基于 Google Cloud 提供的相关控制措施。
Alteryx 如何通过 Google Cloud 服务保护您的数据
Alteryx 配置 Google Cloud 服务，以便使用行业标准加密协议对 Copilot 数据（包括传输中数据和静态数据）进行加密。有关 Google Cloud 安全性与数据保护实践的权威且最新详情，请参阅：
Google Cloud 安全性：https://cloud.google.com/security
Vertex AI 数据治理与隐私：https://cloud.google.com/vertex-ai/docs/general/data-governance
Google Cloud 加密概览：https://cloud.google.com/security/encryption
其他详细信息
默认情况下，Alteryx Copilot 仅可访问工作流元数据、工作流 XML 和您的数据集元数据。只有在您发送新提示时，元数据才会发送到 Alteryx Copilot。如果您启用数据感知，Alteryx Copilot 也将能够访问您工作流中的数据。
Model Training and Prompt Engineering
Alteryx Copilot doesn't train, retrain, or fine-tune AI models with your workflows or data. These points clarify how Alteryx Copilot uses AI models:
What Alteryx Copilot Does Not Do
Train or retrain foundation models (large language models).
Fine-tune models using your data.
Build new models from scratch.
What Alteryx Copilot Does Do
Use pre-trained third-party models.
Improve responses through prompt design and system instructions.
Supply structured context with each request.
Retrieve relevant product or workflow information at runtime to ground responses.
Evaluate and refine prompts and orchestration logic to improve accuracy, safety, and usefulness.
Why This Matters
Model training and fine-tuning require large datasets and permanently change model behavior. Prompt engineering and retrieval don't modify the model. They shape individual requests and responses.
From a compliance perspective, this distinction is critical. Alteryx Copilot behavior is driven by runtime instructions and context, not by retraining models on your data.