Glossary

Active Users: A user with a minimum of one interaction (question & answer) over a defined period of time

Unique Users: A user counted only once no matter how many times they interacted (question & answer) over a defined period of time.

Available Reports

Usage statistics

• Chat Interactions

• Active Users

• Document Reference Statistics

Data Leakage Post-Processing

Main article: Data Leakage Prevention (DLP)

The user-chat-export subsection of the analytics API exposes an interface to post-process prompts and thus works as a form of DLP.

Unique offers this API that can be integrated with the existing DLP systems to monitor the data being processed. The API is designed to work with the FSI clients existing security infrastructure to log queries and extract them for DLP inspection. The DLP system will scan the prompts during post-chat analysis. This approach allows for a balance between user experience and security, ensuring that sensitive information is not inadvertently exposed during interactions. You can read on other DLP approaches in Data Leakage Prevention (DLP).

Work with Reports

Download Reports

An user with the required role is able to request an analytics export. This will create an order entry in the Analytics order table. After the order is finished the user is able to download the resulted request and can also delete it after it has been processed and downloaded.

Open

Analytics page with three finished and one created order which can be started and buttons to request a new export

Interpret reports

Chat Interactions

With this analytics you can evaluate the following:

• Which is the most used assistant?

• How many interactions per assistant?

• Who is the most active user?

Open

• Email: The email of the user, who interacted with the assistant

• Date: The date of the interaction

• Assistant: The assistant used for the interaction

• Count: Number of interactions (question & answer) the user had on the indicated date with the selected assistant

Active Users

With this analytics you can evaluate the overall engagement of the users on the platform:

• How many unique daily active users (DAU) are on the platform?

• How many unique weekly active users (WAU) are on the platform?

• How many unique monthly active users (MAU) are on the platform?

• How did the DAU/WAU/MAU develop over time?

• Period: month (relevant for MAU), week (relevant for WAU), day (relevant for DAU)

• Date: The date of the interaction. The date for the weekly interaction always indicates the end of a 7-day period, e.g. week 10.02.24 means the week 04.02.-10.02.2024.

• Value: Number of unique users who had at least one interaction (request) in the specified period. A user who has 10 interactions ( questions & answers) within one day is only counted once (unique user).

Reference Statistics

With this analytics you can evaluate the overall engagement of the users on the platform:

• Who uploaded which documents?

• Which documents are most asked about?

• Which documents are uploaded to which scopes?

• File Uploaded Date: The date the file was initially ingested (connected via Sharepoint or manually uploaded)

• File name: The name of the file (as also shown in the knowledge center)

• File uploader: The email address of the user who uploaded or connected the file. For Sharepoint it is currently just one generic user ID, which will be changed in the future.

• Source: UNIQUE_BLOB_STORAGE refers to the manual upload of files and MICROSOFT_365_SHAREPOINT to documents ingested via Sharepoint

• Reference Count: The number a document was referenced on the platform when answering a question.

• Scope: The scope a file was uploaded to

Detailed Chat Interactions

This report gives you a detailed export of the chat interactions. The report contains mainly every message of the user and answer of Unique FinanceGPT in the specified time frame. The user is as default anonymised. But on special request by a customer Unique can change this to contain the users data. (Not available on multi tenant instance)

This exported data can help identify frequently asked questions/prompts and also missing knowledge when Unique FinanceGPT is not able to provide an answer.

• Username: The name of the user or anonymised: Unknown

• Timestamp: The date and time the user sent the message

• Space: Which space the user has used for this message

• Chat ID: Identifying which messages belongs together (the same chat)

• Message: The message that was sent

• Answer: The answer of Unique FinanceGPT

• Device Category: Which device the user used (mobile, desktop, tablet)

Work with Chat Exports

Log Fields Configuration

Each entry logged by the Unique API will contain the following mandatory fields:

• timestamp: The date and time of the query, formatted as DD-MM-YYYY; HH:MM:SS GMT+X.

• username: The identifier of the user who initiated the query.

• prompt: The user's query to Unique, excluding any sensitive prompt engineering sections.

Example Log Entry

DLP Policy Configuration

To ensure compliance with privacy laws and regulations, the following considerations must be taken into account when configuring DLP policies:

• Privacy Compliance: Ensure that monitoring practices are compliant with GDPR, CCPA, and other applicable regulations.

• Encryption Handling: Configure SSL interception to inspect encrypted traffic while managing trust certificates responsibly.

• Policy Definition: Clearly define what constitutes sensitive data and the conditions under which it is monitored and blocked.

• Ethical Transparency: Maintain transparent communication with users regarding the extent and purpose of monitoring.

Scan/Extract Frequency

The API is configured to allow paginated daily scans of log files, aligning with the operational practices of Security Operations Center (SOC) teams. This frequency supports efficient management and timely response to potential data leakage incidents.

Review by Clients Compliance teams

Output / findings of DLP scans should be regularly reviewed (regular sample checks) by the respective client’s compliance and/or data protection team. It is not the responsibility of Unique to check output (not allowed by contractual terms and also not part of the Unique service offering). Clients should make sure that the output/ findings are handled according to internal guidelines, policies and regulations.

Reporting issues

Please report if you experience any issues to enterprise-support@unique.ch