Generative AI and agents

Generative AI is a branch of AI that enables software applications to generate new content; often natural language dialogs, but also images, video, code, and other formats.

For example, a computing history web site could provide a generative AI chat interface into which users can enter questions about key figures, technologies, and events in the history of computing.

The ability to chat with the site and have it generate original responses to questions creates a compelling interactive experience for users.

How does generative AI work?

The ability to generate content is based on a language model, which has been trained with huge volumes of data - often documents from the Internet or other public sources of information.

Users interact with generative AI language models through prompts - natural language statements of questions. The language model in a generative AI solution uses the prompt to initiate the generation of a meaningful response.

Generative AI models encapsulate semantic relationships between language elements (that's a fancy way of saying that the models "know" how words relate to one another), and that's what enables them to generate a meaningful sequence of text.

There are large language models (LLMs) and small language models (SLMs) - the difference is based on the volume of data and the number of variables in the model. LLMs are powerful and generalize well, but can be more costly to train and use. SLMs tend to work well in scenarios that are more focused on specific topic areas or that require easily deployed small models for local applications and agents on devices.

What are agents?

Agents are software applications built on generative AI that can reason over and generate natural language, automate tasks by using tools, and respond to contextual conditions to take appropriate action.

AI agents have three key elements:

• A large language model: This is the agent's brain; using generative AI for language understanding and reasoning.
• Instructions: A system prompt that defines the agent’s role and behavior. Think of it as the agent’s job description.
• Tools: These are what the agent uses to interact with the world. Tools can include:
  • Knowledge tools that provide access to information, like search engines or databases.
  • Action tools that enable the agent to perform tasks, such as sending emails, updating calendars, or controlling devices.

With these capabilities, AI agents can take on the role of digital assistants that intelligently automate tasks and collaborate with you to work smarter and more efficiently.

Generative and agentic AI scenarios

Common uses of generative AI and agents include:

• Creating chat bots that answer user questions or engage in conversation.
• Implementing AI assistants that assist human users by automating tasks.
• Creating new documents or other content (often as a starting point for further iterative development)
• Automated translation of text between languages.
• Summarizing or explaining complex documents.