# DinoAI

DinoAI is Paradime's AI platform — a suite of agents and tools that help data teams move faster, write better code, and keep their pipelines healthy. Rather than a single feature, DinoAI is a set of surfaces you can use depending on where and how you work.

### DinoAI Surfaces

| Surface                 | What it does                                            | Best for                                                    |
| ----------------------- | ------------------------------------------------------- | ----------------------------------------------------------- |
| **Copilot**             | AI assistant inside the Paradime IDE                    | Interactive development, writing and reviewing dbt™ code    |
| **MCP Server**          | Expose Paradime context to any MCP-compatible AI client | Using DinoAI from external tools like Claude or Cursor      |
| **Slack Agent**         | AI agent that runs in the background and posts to Slack | Async monitoring, alerts, and team-wide visibility          |
| **Programmable Agents** | YAML-defined agents triggered via the Paradime API      | Automated, version-controlled, composable AI workflows      |
| **Bolt AutoPilot**      | AI agent embedded in Bolt pipeline runs                 | Summarising logs, fixing errors, and self-healing pipelines |

***

### Key Concepts

Before diving into a specific surface, it helps to understand a few concepts that apply across DinoAI.

#### .dinorules

`.dinorules` is a file you commit to your repo that defines rules and constraints for DinoAI agents. Use it to enforce coding standards, naming conventions, or any project-specific guidance that should apply across all agent interactions.

#### .dinoprompts

`.dinoprompts` lets you define reusable prompt templates, stored in your repo alongside your dbt™ project. Reference them in agent runs to keep prompts consistent and version-controlled.

#### Context

DinoAI agents are context-aware. Depending on the surface, they can read your dbt™ project files, query your data warehouse, access run logs, and more. Each surface page documents what context is available.

***

### Choosing the Right Surface

* **Working in the IDE?** → [Copilot](/app-help/products/dino-ai/copilot.md)
* **Using an external AI client?** → [MCP Server](broken://pages/4zr2PhElcO4giJnb3mi4)
* **Want async updates in Slack?** → [Slack Agent](/app-help/products/dino-ai/slack-agent.md)
* **Building automated pipelines?** → [Programmable Agents](/app-help/products/dino-ai/programmable-agents.md)
* **Dealing with failing Bolt Pipelines?** → [Bolt Pipeline Agent](/app-help/products/dino-ai/bolt-pipeline-agent.md)


---

# 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.paradime.io/app-help/products/dino-ai.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.