# Introduction

Karini's Agentic AI foundation platform empowers users to build, deploy and monitor end-to-end generative AI applications with a few simple clicks. The following diagram illustrates how Karini AI delivers a comprehensive [Agentic AI foundational platform](https://www.karini.ai/insights/navigating-genaiops-in-enterprises) encompassing the entire application lifecycle. This platform delivers a holistic solution that accelerates time to market and optimizes resource utilization by providing a unified framework for development, deployment, and management.<br>

<figure><img src="/files/43aM1IedZXCEoY5zgpG6" alt=""><figcaption></figcaption></figure>

* **Access to Cutting-Edge LLMs and VLMs:** Seamlessly integrate state-of-the-art models from Amazon Bedrock, Amazon SageMaker, Databricks,  Azure OpenAI, Google Vertex, and private model providers.
* **Prompt Engineering:** Create straightforward or agentic prompts using templates, evaluate them across different models for latency, cost, and quality, and maintain a record of historic runs.
* **Knowledge Bases:** Connect to enterprise data sources, object stores, business applications, databases, or data warehouses to build or access knowledge bases in real-time.
* **No-Code Recipes:** Deploy agents, multi-agent systems, generative BI, RAG, or batch workflows in minutes using intuitive no-code recipes.
* **Deploy and Collect Feedback:** Easily deploy agents as chatbots with customizable styles, feedback settings, and audio controls.
* **Observability:** Offers built-in tracing and tracking of all conversations to construct a semantic knowledge base, analyze performance and cost trends, and export conversations for model fine-tuning.

## Installing Karini AI

* [Pre-requisites](/karini-ai-documentation/installation.md#pre-requisites)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://karini-ai.gitbook.io/karini-ai-documentation/introduction.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.