# Bring your data into AI

### Centralize your AI Knowledge&#x20;

If you want workflows involving AI to deliver great results, you need **strong contextual knowledge** to power them. That means giving your agents the right information so they can shine and extract the most value from automation processes. With that in mind, we built a system that lets you centralize your knowledge bases and use them in any AI-driven workflow.&#x20;

By storing essential prompts, documents, tables, and snippets in a unified space, your AI always has the context it needs to perform **consistently** and **accurately**.

### The Problem

Automation creators don’t fail because they can’t build workflows — they fail because they can’t **keep knowledge consistent** as workflows and AI agents multiply.

As teams add more automations, the “source of truth” gets duplicated everywhere: prompts copied into steps, instructions rewritten per agent, rules stored in docs, FAQs scattered across tools. The result is **context drift**: two workflows meant to do the same thing behave differently because they’re powered by slightly different information, examples, or assumptions.

#### Why this happens

* No single source of truth
* Knowledge gets copied, not shared
* Prompts drift over time
* More workflows, more copies
* Ownership becomes unclear
* Maintenance cost explodes
* Agents lose context

#### Governance adds friction

* Access must be controlled
* Sensitive data leaks easily
* Ownership isn’t clear
* Reviews slow teams down

### Knowledge Manager System&#x20;

Centralized knowledge is hard because information must be **structured, maintained, and safely reused** across many automations — not just stored in one place.

Snack Prompt addresses this problem by centralizing your data into a single knowledge layer that can be reused across agents, automations, and workflows. Instead of scattering information across tools, documents, and prompts, your knowledge becomes a shared foundation that AI can consistently rely on.

{% embed url="<https://www.youtube.com/watch?v=3vLcjaAOIfw>" %}

### What You Can Do

With the Snack Prompt AI Engine API, you can:

* **Ingest** — Send your data and let AI understand it
* **Search** — Find answers using natural language, not keywords
* **Chat** — Have conversations with your data and get accurate, sourced responses

### Get Started

* [Quickstart — Your first API call in 5 minutes](/bring-your-data-into-ai/get-started/how-to-use-your-knowledge-bases.md)
* [Endpoints Reference](/bring-your-data-into-ai/reference/endpoints.md)

### Support

Questions? Reach out to our support team.


---

# 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://docs.snackprompt.com/bring-your-data-into-ai/rag.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.
