Conga Product Documentation

Welcome to the new doc site. Some of your old bookmarks will no longer work. Please use the search bar to find your desired topic.

Show Page Sections

AiMe Q&A Agent Conversation Logs

You can review all user interactions with AiMe Q&A Agent, which are logged.

AiMe Q&A Agent logs all interactions with users by user and date for audits, quality of service improvements, maintenance, compliance, analytics, and other purposes. Every request and every response is recorded and available for audit. You can export AiMe conversation histories in 10,000-message CSV file batches, filtering by user or date range. You will receive an email notification when an export job is complete. File exports are purged after seven days. The underlying data persists unless deleted.

Logs are retained in comma-separated value (CSV) format and are retained as live data.

Accessing Conversation Logs

  1. Access the Advantage Studio.
    • From the Classic interface (Launch your Conga Experience), click Admin Console > Advantage Studio
    • From the Modern interface home page, click your username at bottom left, select Go to Administration from the pop-up menu, and then click Manage in the Advantage Studio tile.
    Advantage Studio opens with "Welcome to Advantage Studio".
  2. Click Audit Log in the left navigation bar.
    The Audit Logs screen opens.
  3. Find the user name of interest and click the Download hypertext in its row.
    Tip: You can filter the list of user logs by username or by last time used.
    A pop-up selector appears, listing all available logs for the selected user.
  4. Select or deselect logs as you will. Confirm your choice by clicking the Download button in the confirmation pop-up.
AiMe provides a zipped comma-separated value (.csv) file for you to download or unzip and open with your spreadsheet app.

Downloading Logs

An administrator can access and download logs of all user interactions with AiMe by user name and by the application the user was using when the log was recorded.

Use case: As part of an offboarding review, the Compliance team at a pharmaceutical company asks an administrator to produce a record of everything a departing employee asked AiMe over the past year. Opening Advantage Studio from the Conga Start window, the administrator clicks Audit Log, and searches for the departing employee’s user name. The administrator selects the applications the employee used AiMe from and clicks Download. Because the employee was a frequent AiMe user, the resulting Zip file takes several minutes to generate; once complete, it contains the employee’s entire chat history across all selected applications, which the administrator hands off to Compliance for review.

  1. From the Conga Start window, click Admin Console > Advantage Studio.
  2. Click Audit Log
  3. Select a user by name.
    You can pick, search, or filter user names.
  4. Click the Download hypertext next to the user’s name.
    This raises the “Select the app to download audit data for (username)” pop-up window.
  5. Select the app or apps for which you will download audit data for this user.
  6. Click Download.
  7. When prompted, tell your local machine’s file manager where to store the downloaded file or files.
    The entire chat history log for the selected user and applications downloads to your local system.
    Note: These logs can be quite voluminous and downloading them may take a while.
The logs are downloaded as a Zip file to the directory you chose.

Log Data Analysis

Downloading a log stores a Zip file to your local drive. This file unzips into several comma-separated value (CSV) files, named by each conversation's date and time.

The CSV file format opens in any spreadsheet application, and you can engage with the data using such tools. CSV is also a text-based file format as well, which means that in addition to the data sorting, formatting, and analysis tools available in such applications, you can use text-tool and programmatic data processing tools to analyze the log data you have downloaded.

Data is stored such that Excel and other spreadsheets open each file as a spreadsheet that offers the following basic information about each user conversation.

HeadingDescription
Serial NumberThis is a running cardinal number series indicating the sequence of messages in the session.
MessageThis column contains each verbatim question (or other interaction) that the user chatting with the AI entered, and the AI's replies.
TimeThis is the time of each chat transaction entry from the user, formatted as YYYY-MM-DD 12:59:59.123.
Message TypeThis field is the record of which party generated the entry: chat_message indicates a user request and assistant_message indicates an AI response.
User FeedbackThis is a record of the user’s feedback responses. Possible values are:
  • THUMBS_UP

  • THUMBS_DOWN

  • NO_FEEDBACK