Context

• Login screen → Login using credentials of a “AWS-Sales”
• Chatbot UI opens, and user is greeted with a prompt stating “Hello xyz, how can I help you today?”: (INSERT IMAGE HERE)

Prompt 1: Knowledge Mapping

• AWS-Sales asks: “Can you tell me more about the TransferWise case study?”
  • UI displays the relevant content, and provides PDF attached for reference for the sales person to review
  • Also provides an option to regenerate or create a knowledge/context map

Prompt 2: Accessing to restricted content

• AWS-Sales asks: “Can you tell me more about Magic Quadrant for Cloud AI?”
  • Chatbot responds with: “You currently don’t have access to this data. Would you like to request ”AWS-SA” for access to this content?”
  • Present two options of “Yes” and “No”
  • Once User presses Yes, send automated email to placeholder email id, and deliver a message saying “Your request to access data for Magic Quadrant for Cloud AI is currently pending”, while giving an option to press “Exit”
  • Us: Show that you received an email, and press “Authorize” button to give access
  • Chatbot response automatically changes consequently to “AWS-SA just gave you access to the data you requested. Would you like me to summarize it?”
  • User responds with Yes, and the chatbot returns a summary, with a pop-up box to create a knowledge map (showcase this as well)

Prompt 3: Diagramming

• AWS-Sales asks: “I am trying to make the quarterly report to publish in the NYT’s feature article about Stripe. Can you provide me with some insights or figures from the Stripe Spending report?”
• Bot responds: “Of course, I found a document that you have access to called “Stripe Q3 Financial Spend”. I went ahead and generated a pie-chart representing the spending in various categories as follows: INSERT IMAGE FROM BACKEND”

curl --location 'localhost:5000/concept-map' \\
--header 'Content-Type: application/json' \\
--data '{
    "prompt":"In summary, both Amazon DynamoDB and Apache HBase define data models that allow efficient storage of data to optimize query performance. Amazon DynamoDB imposes a restriction on its item size to allow efficient processing and reduce costs. Apache HBase uses the concept of column families to provide data locality for more efficient read operations. Amazon DynamoDB supports both scalar and multi-valued sets to accommodate a wide range of unstructured datasets. Similarly, Apache HBase stores its key/value pairs as arbitrary arrays of bytes, giving it the flexibility to store any data type. Amazon DynamoDB supports built-in secondary indexes and automatically updates and synchronizes all indexes with their parent tables. With Apache HBase, you can implement and manage custom secondary indexes yourself. From a data model perspective, you can choose Amazon DynamoDB if your item size is relatively small. Although Amazon DynamoDB provides a number of options to overcome row size restrictions, Apache HBase is better equipped to handle large complex payloads with minimal restrictions."
}'