AI Learning Center
for Tech Leaders
You’ve heard a lot about the transformative power of AI. But what does that mean for your organization? What are the building blocks for success? And what does success with AI even look like?
In working with hundreds of customers, we’ve developed a playbook for helping organizations move from zero to production with agents and generative AI applications.
Unlock the Full Potential of GenAI for Your Organization!
AI Agents
Simply put, an AI agent is software that relies on a large language model, a set of tools it can use autonomously, and an orchestration layer that manages the process of information intake, reasoning, and executing an action.
Key Functions in Context
Tool Use
External functions, APIs, or tools extend an agent’s capabilities and enables it to perform specific tasks. This can include calling predefined functions or interfacing with external services (like making web requests using cURL or accessing RESTful APIs) to obtain context or execute actions beyond its inherent functionalities.
Decision-Making
An agent can evaluate available information and select the most appropriate action to achieve its goals. This involves analyzing context, weighing possible outcomes, and choosing a course of action that aligns with desired objectives.
Planning
An agent can formulate a sequence of actions or strategies to achieve a specific goal.
Reasoning
The agent analyzes available context, draws conclusions, predicts outcomes of actions and makes informed decisions about the optimal steps to take to reach the desired outcome.
Vector Embeddings
Vector embeddings are the assembly language of AI. They’re how you go from a natural language query to an accurate, relevant response. They enable developers to operate on unstructured data, whether it's coming from the user in the form of a prompt or coming from documents, PDFs, and files that form the knowledge base that you're building your app on.
Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) is a GenAI architecture that applies semantic similarity to automatically discover information relevant to a query.
Distinguishing RAG Systems from AI Agents
RAG systems, as the name suggests, differ from AI agents in that they sharpen responses by accessing external data to enhance the output of language models. AI agents, on the other hand, make decisions and execute tasks autonomously.
Combining the two can turbocharge agents, enabling them to make decisions or take actions based on highly relevant information.
How Our Customers Succeed with GenAI
In healthcare, finance, and a range of other industries, DataStax customers are transforming their businesses with AI agents and RAG. Read these stories to learn how they’ve put GenAI into production.
Some Things to Share with Your Dev Team
There are lots of ways to help your developers roll up their sleeves and get started quickly with AI agents and RAG. Here are a few.
