Getting Started with CLAIRE GPT > Conversations
  

Conversations

CLAIRE GPT has a simple natural language conversation interface. You can start a conversation and send prompts to easily discover and manage data across Intelligent Data Management Cloud services. You can also create multiple conversations.
Type a prompt in the prompt text box or click a sample prompt, modify the prompt, and press Enter or click Submit. You can also type # in the prompt text box to view the sample prompts.
You can rename, delete, and pin a conversation. You can also search for conversations. You can clear the context established in a conversation with a natural language prompt such as clear conversation memory and follow up with the next request.
The following image shows a conversation page with a response from CLAIRE GPT:
A conversation with a response from CLAIRE GPT displaying catalog sources of type Snowflake, Databricks, and Oracle. The answer contains a summary, response, explanation, and suggestions.
CLAIRE GPT provides answers that contain the following sections:
  1. 1Summary. A brief statement to summarize the response.
  2. 2Response. Data or metadata details based on your prompt.
  3. 3Explanation. A comprehensible statement about how the response is derived. The Explanation section appears for applicable data discovery, metadata exploration, and data exploration related prompts. The Explanation section won't appear if you submit prompts like "Who is the stakeholder of the <asset name>?".
  4. 4Suggestions. CLAIRE GPT suggests new prompts that you can send based on your conversation history.
You can interact with the responses and switch between charts and the raw data in tabular format to meet your business requirements. You can compare and engage with data. For example, the responses appear in a comparative tabular format, and you can copy an entire table or specific sections of the table. You can download the responses for further analysis.
Data discovery responses include explanations for each item in the response. The explanation provides information such as why particular items appear in the response, as well as unique insights for different asset types.
You can rate the responses in a conversation and provide feedback.