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

# Overview

> Build and manage the file-system context your analytics agent uses for reliable, optimized answers.

## Why a Context Builder?

1. **Make it reliable for users** - Ensure consistent, accurate responses
2. **Make it optimized** - Reduce costs, tokens usage, and improve speed

Context is built with dazense using a CLI. The CLI will initialize your context repository and sync your context within this repo.

## How It Works

dazense uses a file-system approach to organize context:

```
your-project/
├── dazense_config.yaml                    # Main configuration
├── RULES.md                           # Agent behavior rules
├── agent/                             # Agent tools and integrations
│   ├── mcps/                          # Model Context Protocols
│   └── tools/                         # Custom tools
├── databases/                         # Database context
├── docs/                              # Documentation files
├── repos/                             # Cloned repositories
├── semantics/                         # Semantic model + business rules
├── datasets/                          # Dataset bundles (trusted modes)
├── policies/                          # Enforcement policies (trusted modes)
├── contracts/                         # Runtime contracts/audit artifacts
└── queries/                           # Example queries
```

## Build Your Context

Learn how to add different types of context:

* **Databases** - Connect databases and sync schemas
* **Repositories** - Add dbt projects and documentation
* **Rules** - Define how your agent should behave

## Next Steps

* **Context Configuration** - Learn how to initialize and configure your dazense project
* **Context Principles** - Core principles for optimizing your agent's performance
* **Context Engineering Playbook** - Step-by-step guide to building effective context for your analytics agent
* **Evaluation** - Test and evaluate your agent with unit tests