Set up .dinorules using your project as context

Writing .dinorules from a blank file is hard when you don’t know which standards to define. Point DinoAI at representative files from your existing dbt™ project so it can identify your established conventions and generate rules that capture your team’s actual practices.

Prerequisites

A DinoAI Copilot session open in the Code IDE.
Representative dbt™ files that reflect your best practices (well-structured models, dbt_project.yml, and schema files).

Estimated time: 10 minutes.

Steps

Open DinoAI in Agent Mode

Open DinoAI from the icon in the right panel and select Agent Mode if it is not already selected.

Add representative files as context

Add files as context using the @ icon in the DinoAI panel. Select files from different folders that represent your best practices, for example:

Staging models (such as stg_customers.sql, stg_orders.sql)
Intermediate models (such as int_customer_orders.sql)
Marts models (such as dim_customers.sql, fct_sales.sql)
Your dbt_project.yml file
Existing schema.yml files from each folder

For best results, select files that represent your team’s current best practices rather than legacy code that might not follow your preferred standards.

DinoAI panel with multiple dbt project files added as context via the @ icon

Enter your prompt

Ask DinoAI to create a .dinorules file based on the selected files.Example prompt:

Analyze my selected dbt™ project files and create a .dinorules that captures my existing SQL formatting, naming conventions, folder structure, and documentation patterns.

Review the generated .dinorules

Review the generated .dinorules file preview.

Example .dinorules file

Project Context
- Domain: E-commerce analytics
- Data Stack: dbt™ with Snowflake
- Project Structure: source → staging → intermediate → marts hierarchy

SQL Formatting Standards (Based on Analyzed Files)
- Keywords: Always uppercase (SELECT, FROM, WHERE, etc.)
- Indentation: 4 spaces, no tabs
- Comma Style: Trailing commas in SELECT statements
- Aliasing: Always alias tables (use 'u' for users, 'o' for orders)
- CTEs: Prefer CTEs over subqueries for readability
- Comments: Add comments for complex business logic

Naming Conventions (Extracted from Current Models)
- Models: snake_case with prefixes (stg_, int_, dim_, fct_)
- Columns: snake_case, descriptive names
- Tables: Singular nouns (user, not users)
- Primary Keys: Always end with '_id' (user_id, order_id)

Folder Structure and Materializations
- staging/: Views only, basic transformations
- intermediate/: Views, complex business logic
- marts/: Tables or incremental, final business models
- All models tagged by domain and layer

Documentation Requirements
- All models require descriptions
- Business-critical columns need descriptions
- Primary keys need unique and not_null tests
- Foreign keys need relationships tests

Business Logic Patterns
- Always use UTC for timestamps
- Standardize null handling with COALESCE
- Use consistent date formatting (YYYY-MM-DD)
- Apply consistent rounding rules (2 decimal places for currency)

Quality Standards
- All models must compile without warnings
- Use consistent test patterns across similar model types
- Maintain referential integrity through proper testing

Accept and test the rules

Accept the changes to create the file in your project root, then test the rules by generating new models and confirming they follow the established patterns.

After you send your prompt, DinoAI analyzes the structure and patterns in your selected files, identifies consistent naming conventions, SQL formatting, and organizational patterns, and generates a .dinorules file that codifies them so future AI-generated code matches your standards.

You’ll know it worked when a .dinorules file appears in your project root and newly generated models follow your naming, formatting, and documentation conventions. If the rules feel generic, add more representative files as context and regenerate.

Update your .dinorules periodically as your project evolves and new best practices emerge. The file can be modified any time to reflect changing team standards.

Next steps

Provide context with PDFs

Add specs and reports as context alongside your rules.

Generate documentation

Let DinoAI document models in line with your standards.

All DinoAI use cases

Browse every DinoAI Copilot workflow.

DinoAI Copilot reference

Context, tools, and features that power these workflows.

Foundations

Automate with AI agents

Set up & configure

Orchestrate data pipelines

Migrate to Paradime

Develop in Paradime

Learn dbt™

Set up .dinorules using your project as context

Steps

Next steps

Provide context with PDFs

Generate documentation

All DinoAI use cases

DinoAI Copilot reference

​Steps

​Next steps

Provide context with PDFs

Generate documentation

All DinoAI use cases

DinoAI Copilot reference

Steps

Next steps