Security Overview

AgenticFlow AI is SOC 2 Type II compliant and works with trusted vendors.

Commitment to Security

AgenticFlow AI takes your privacy seriously. We are committed to achieving SOC 2 Type II compliance, ensuring that your data is handled with the highest standards of security and confidentiality.

Regions

AgenticFlow AI is available in three regions to cater to users around the world:

• US (N. Virginia)

• EU (London)

• AU (Sydney)

You can choose the region that best suits your needs when setting up your AgenticFlow AI account.

Key Features

AgenticFlow AI offers three key features: Workflows, Agents, and Data. Each feature has its own data retention and storage policies, detailed below.

Workflows

Workflows in AgenticFlow AI are powerful sequences that allow you to transform and process input data. It’s important to note that neither the input nor the output of these workflows is logged by AgenticFlow AI. However, some actions within the workflows may require the use of external vendors for processing. For example, LLM actions utilize different vendors depending on the specific model being used.

Agents

Agents in AgenticFlow AI enable conversations and maintain a history of interactions for the benefit of the user. These conversations are private to your project and can be deleted at any time by you. Conversations are stored securely within the region you have chosen for your AgenticFlow AI account.

Data

Data is a feature in AgenticFlow AI that allows you to store knowledge and datasets, enabling bulk runs of workflows on entire datasets. You have full control over your stored data and can delete it at any time. Similar to agents, your data is stored securely within the region you have selected for your AgenticFlow AI account.

LLM Models

AgenticFlow AI offers several LLM models to enhance your AI applications. Our GPT models are hosted on our own Azure OpenAI deployment within the same region you have chosen. It’s important to note that no data is stored or trained on in this process.

If you provide an OpenAI API Key, it will be passed through OpenAI’s API service. No data is stored or trained on during this process. You can review the Data Processing Agreement (DPA) on our website for more information.

Anthropic models are offered through their API, and once again, no data is stored or trained on during this process. You can review the DPA on our website for further details.

LLM Models Available

LLM Model	Vendor	Data Logged	Used for Training	DPA
GPT	Azure	No	No	Yes
Claude	Anthropic	No	No	Yes