OAS - 8a - ServiceNow Invokes Generative AI ????

This topic's a biggie, so I've split it up into several posts. Hang tight and follow along to really get the scoop on the new ServiceNow feature! ????

What is Generative AI?

Generative AI ?? refers to an artificial intelligence system that can produce various types of content, such as text, images, audio, and other data formats, based on inputs provided to it.?

ServiceNow offers a Generative AI ?? Controller that enables you to integrate this functionality into your existing workflows.

Common Terms ??

Lets learn few of the important terms that can be utilised throughout the article which are very much helpful to understand the Generative AI concepts.

AI ?? - AI is the simulation of human intelligence in machines, enabling them to perform tasks that typically require human thought.

Models ?? - An AI model is a computational structure trained to make predictions or decisions based on data we have trained.

LLM's ?? - An AI LLM (Language Model) is a machine learning model designed to understand, generate, and manipulate human language.

Generative Models ?? - AI Models that can generate new data/output based on input.

Capability ?? - Capability refers to the model's ability to create content, such as text, images, or music, based on its data training.

Capability Definition ?? - It refers to the specified criteria or metrics determining a model's proficiency in producing and controlling creative content.

Token ?? - A single entity (Word) / a smallest unit of a input that a LLM will process called token.

Prompt ?? - The textual input provided to the LLM to process and generate content.

How to Utilise Best Capabilities using Generative AI?

In order to utilise the capabilities of AI, we have to train the models with good-quality of data. The accuracy of the models depends upon the quality of data we train.

How to choose the good quality data?

The data required is depend on the capability we are expecting using Generative AI. A quick look of below table can provide us more information.

1. To get the best out of Generative AI models, we need data that's top-notch and doesn't have any mistakes. It helps make sure the stuff they create is spot on!
2. The data should be relevant to the requested task. For example, if the goal is to answer user questions with knowledge articles, your knowledge base should include a variety of articles that cover common user questions, concerns, or issues.
3. Input to generative AI should be clear and concise.

Best part is ServiceNow Generative AI can integrates with Azure Open AI & Open AI ??? using OOB Spokes available which will enable support to generate content using text-davinci-003 & New models such as ChatGPT-4

Which modules of ServiceNow can utilise Generative AI Capabilities?

• IT Service Management
• IT Operations Management
• IT Asset Management
• Strategic Portfolio Management
• Security Operations
• App Engine
• Flow Designer ( Spokes & Workflows )
• HR Service Delivery
• Customer Service Management
• Field Service Management

etc......

Capabilities Supported by ServiceNow Out-Of-The-Box

Generate Capability: This capability can help to create a KB Article automatically using Prompt. The can be based on topic specified as input through Virtual Agent.

Summarize: This capability can summarize the Input text provided. For example an incident description can be summarized and add into the worknotes using flow designer flows.

Generic Prompt: This capability enables to invoke chatGPT directly into the Virtual Agent.

QnA: This QnA capability will enable us to send questions as prompt to ServiceNow and provide necessary articles or prompt back.

PS ?? : I've split this article into two parts for easier digestion. Stay tuned for the upcoming continuation, and thanks for your support! ???? #StayUpdated #PartTwoComingSoon