Symbl.ai is excited to announce a Private Beta launch of Nebula, our LLM for natural human conversations. Nebula is intended for businesses and developers who are interested in building generative AI powered experiences and workflows that involve human conversations including sales calls, meetings, customer calls, interviews, emails, chat sessions and other scenarios.
In mid July Symbl.ai will start making the Nebula LLM available to developer communities through our Private Beta program. During this Private Beta program, developers can experience a hands-on preview of Nebula’s performance under a variety of use case scenarios (visit our technical documentation for a full list of use case scenario descriptions here).
Use Case Examples:
Response:
Response:
Response:
The Symbl.ai Nebula model takes two inputs in its prompt – an instruction which is a command or question to model, and a conversation transcript. Nebula is a large language model (LLM) trained to understand nuances in human conversations and perform instructed tasks in the context of the conversation. Human conversations typically involve multiple participants and complex interactions between them across long and distant dialogues.
Key Highlights:
- Nebula takes into consideration input instructions, questions, conversation transcripts, and context to generate the output that reflects the intended task result provided in the instruction. This enables the model to generate responses in context of the provided conversation.
- Nebula can create human-like text, based on the inputs provided, which makes Nebula effective in handling a wide variety of use case scenarios.
- Nebula provides developers the ability to adjust the generation parameters of the model that control characteristics such as diversity, randomness, and repetition to change the model’s behavior to satisfy a specific use case.
- Developers can easily integrate Nebula through an easy REST API
import requests
import json
url = 'https://api-nebula.symbl.ai/v1/model/generate'
headers = {
'Content-Type': 'application/json',
'ApiKey': 'YOUR_API_KEY',
}
data = {
"prompt": {
# Your question or instruction
"instruction": "What are the customer pain points based on this conversation?",
# Your conversation transcript
"conversation": {
"text": "Representative: Hello, How are you?nCustomer: Hi, good. I am trying to get access to my account but ..."
}
}
}
response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.text)Model Playground
We’ve created a Model Playground that allows developers to test the Nebula LLM, without writing any code, against various conversations and tasks. Model Playground is a great way to start exploring Nebula’s capabilities.
- Get started with already available conversation transcripts and prompt suggestions.
- Use your transcript by pasting your transcript or uploading a text file.
- Fine tune parameters to find the right combination of generation parameters for your use case.
To request access to Model Playground, please visit our sign up page here
Using Nebula in your applications
Nebula can analyze conversation transcripts and generate responses based on the conversation along with the instruction or question in the prompt. Furthermore, developers can provide Nebula with instructions such as request summaries, follow-up questions, draft emails, issues to review, qualify sales leads, identify and recommend resolutions to customer issues, or even recommend business opportunities. Nebula can also respond to specific questions about the conversation as part of the instruction. Check out docs to learn more.
For example, Nebula powers generative AI capabilities in Symbl.ai’s Sales Intelligence solution that provides context-aware sales coaching experiences to business organizations. In this example, Nebula performs various tasks via Model API to analyze a conversation with a prospect, identifying themes, sentiments, next steps, questions and answers, and objections, to help generate follow-up responses and identify potential sales opportunities.
Call for Developers
At Symbl.ai, we believe that there’s tremendous value in human conversations especially in businesses, and Nebula can help harness that value across various conversation types. We are excited to see what you build with Nebula. We have been working with developers and businesses who have been pushing boundaries by leveraging advanced generative AI for conversation intelligence and we’re eager to offer the power of Nebula to this inspired community. In the same spirit, we encourage you to apply for our Startup program if you are working at a startup or sign up to become a model tester and accelerate your access to the Nebula model. We’d love to see our current and future developers push the boundaries of conversation understanding with Nebula use cases in following areas:
– Sales
– Customer Support
– Meeting Productivity
– Recruitment
– Training and Education
– Workflow Automation
– Data Analytics and Sciences
– Healthcare Technology
– Finance and Insurance Technology
To register for the Nebula LLM Private Beta Preview, please visit our sign up page.
For more information on use case scenarios, see our technical API documentation page.
We’re very excited to work with more AI developers and businesses to bring your vision to life.
