> ## Documentation Index
> Fetch the complete documentation index at: https://josephfajen.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Essential Cardano AI Assistant

> An accuracy-first RAG chatbot indexing 2,572 documents across eight documentation sites of the Cardano ecosystem

## The Project

At Input Output Global (IOG), there are many documentation sites covering multiple projects and knowledge sources. A common question was, "Which doc site should I look at to find what I'm looking for, and how do I find it?"

To address that reader pain point, I designed and built the Essential Cardano AI Assistant — a RAG chatbot that could synthesize answers, with citations, from 2,572 files across eight documentation sites:

| Source                   | URL                                                                             | Files |
| ------------------------ | ------------------------------------------------------------------------------- | ----- |
| Essential Cardano        | [essentialcardano.io](https://essentialcardano.io)                              | 979   |
| IOG Research             | [iog.io/en/research](https://iog.io/en/research)                                | 625   |
| Intersect Knowledge Base | [docs.intersectmbo.org](https://docs.intersectmbo.org)                          | 354   |
| Developer Resources      | [developers.cardano.org](https://developers.cardano.org)                        | 251   |
| Intersect News           | [intersectmbo.org/news](https://intersectmbo.org/news)                          | 100   |
| IOG News                 | [iog.io/news](https://iog.io/news)                                              | 95    |
| Plinth User Guide        | [plutus.cardano.intersectmbo.org](https://plutus.cardano.intersectmbo.org/docs) | 85    |
| Cardano Docs             | [docs.cardano.org](https://docs.cardano.org)                                    | 83    |

***

## What I Delivered

### 1. Full-Stack RAG Pipeline

I built a complete retrieval-augmented generation system from the ground up:

* Indexed 2,572 documents from 8 sources across the Cardano ecosystem
* Semantic search with citation generation — every answer links back to the source document
* Next.js with the Vercel AI SDK and assistant-ui component library for the chat interface, styled with Tailwind
* Deployed on Railway with a live demo interface

**Result:** [Live Demo](https://powerful-motivation-production.up.railway.app/)

<Note>Live demo — knowledge base current as of December 2025.</Note>

### 2. Citation-First Design

Every response links back to source documents — users can verify claims with one click. To make citations meaningful, I built date awareness into the knowledge base:

* Extracted and normalized publish dates across 2,500+ source files
* Prioritized recent content in retrieval to avoid stale answers
* Consistent date citation format so users know how current the information is
* 20+ system prompt iterations to enforce citation standards and IOG's editorial style

### 3. Documentation

Created comprehensive documentation for the system:

* User guide for developers
* System architecture overview
* Prompt engineering decisions and rationale
* Limitations documentation (what the assistant will and won't answer)

<CardGroup cols={2}>
  <Card title="2,572 Documents" icon="file-lines">
    Indexed across 8 sources: Essential Cardano, IOG Research, Intersect Governance, Developer Portal, and more.
  </Card>

  <Card title="Date-Aware Pipeline" icon="calendar-check">
    Publish dates extracted, recent content prioritized, consistent citation format.
  </Card>

  <Card title="Citation Generation" icon="quote-right">
    Every answer links back to source documents. Users can verify and dive deeper.
  </Card>

  <Card title="20+ Prompt Iterations" icon="sliders">
    System prompt refined to enforce citation standards, date formatting, and IOG's editorial style.
  </Card>
</CardGroup>

***

## Tech Stack

`Python` · `Vector Databases` · `RAG Pipelines` · `Prompt Engineering` · `Railway` · `Anthropic Claude`