Portfolio piece — no longer accepting signups. See what I'm building now

DocsChonk AIHow Chonk Codes

Talk to Chonk

Overview

Portfolio piece — no longer accepting signups. See what I'm building now

DocsChonk AIHow Chonk Codes

Chonk AI5 min readIntermediateUpdated Jan 2026

How Chonk Codes

Curious how I turn your requests into production-ready dbt code? Let me show you what happens behind the scenes - from understanding your request to delivering clean, tested SQL.

My Coding Process

When you ask me to generate code, I follow a structured process to make sure you get quality output that actually works.

Context Gathering

First, I review your project's knowledge graph - table schemas, relationships, and existing models I know about.

Pattern Selection

Based on what you need, I pick the right templates and patterns (staging, fact, dimension, etc.).

Code Synthesis

I write the SQL and YAML using Jinja templating and dbt best practices I've learned.

Quality Check

Before sending it to you, I check for syntax errors, undefined references, and best practice violations.

What I Generate

SQL Models

Clean CTEs with comments
Jinja for dynamic SQL
Consistent naming
Readable formatting

YAML Files

Schema definitions
Column descriptions
Tests (unique, not_null)
Documentation

Extra Goodies

Reusable macros
Seed files
Analysis queries
Custom tests

Customize My Output

Want me to code a certain way? Just tell me! Here's what you can customize:

SQL Style

CTEs vs subqueries, comment placement, line breaks

Try: "Use subqueries instead of CTEs"

Naming Conventions

Prefixes, suffixes, case style for models and columns

Try: "Name it stg_stripe__charges, not stg_charges"

Test Coverage

Minimal (keys only) vs comprehensive (all columns)

Try: "Add accepted_values tests for status columns"

Documentation Depth

Brief summaries vs detailed descriptions

Try: "Add detailed docs explaining the business logic"

My Quality Checks

I automatically validate my code before showing it to you. Here's what I look for:

SQL syntax errors (missing commas, unmatched parentheses)
Undefined references (refs to models that don't exist)
Circular dependencies (model A refs B which refs A)
Best practice violations (hardcoded values, missing tests)
Missing tests on primary keys (should always be unique + not_null)

If I catch an issue, I'll either fix it automatically or let you know what needs attention. I'd rather slow down than give you broken code!

Iterating Together

My generated code is a starting point. Here's how we can refine it together:

Request changes

"Add a filter for active customers only"

Tell me what to modify

Ask why

"Why did you use a left join here?"

I'll explain my reasoning

Try again

"Try a different approach using window functions"

I'll give you a fresh solution

Edit yourself

Make quick tweaks directly

Sometimes that's faster!

Chonk's Workflow Tip

Let me handle the boilerplate, then iterate on the business logic together. It's way faster than writing everything from scratch!

More About Chonk

Talk to Chonk

Learn how to write prompts that make my tail wag

Meet Chonk

Discover all the things I can help you with

Talk to Chonk

Overview

Chonk AI5 min readIntermediateUpdated Jan 2026

How Chonk Codes

Curious how I turn your requests into production-ready dbt code? Let me show you what happens behind the scenes - from understanding your request to delivering clean, tested SQL.

My Coding Process

When you ask me to generate code, I follow a structured process to make sure you get quality output that actually works.

Context Gathering

First, I review your project's knowledge graph - table schemas, relationships, and existing models I know about.

Pattern Selection

Based on what you need, I pick the right templates and patterns (staging, fact, dimension, etc.).

Code Synthesis

I write the SQL and YAML using Jinja templating and dbt best practices I've learned.

Quality Check

Before sending it to you, I check for syntax errors, undefined references, and best practice violations.

What I Generate

SQL Models

Clean CTEs with comments
Jinja for dynamic SQL
Consistent naming
Readable formatting

YAML Files

Schema definitions
Column descriptions
Tests (unique, not_null)
Documentation

Extra Goodies

Reusable macros
Seed files
Analysis queries
Custom tests

Customize My Output

Want me to code a certain way? Just tell me! Here's what you can customize:

SQL Style

CTEs vs subqueries, comment placement, line breaks

Try: "Use subqueries instead of CTEs"

Naming Conventions

Prefixes, suffixes, case style for models and columns

Try: "Name it stg_stripe__charges, not stg_charges"

Test Coverage

Minimal (keys only) vs comprehensive (all columns)

Try: "Add accepted_values tests for status columns"

Documentation Depth

Brief summaries vs detailed descriptions

Try: "Add detailed docs explaining the business logic"

My Quality Checks

I automatically validate my code before showing it to you. Here's what I look for:

SQL syntax errors (missing commas, unmatched parentheses)
Undefined references (refs to models that don't exist)
Circular dependencies (model A refs B which refs A)
Best practice violations (hardcoded values, missing tests)
Missing tests on primary keys (should always be unique + not_null)

If I catch an issue, I'll either fix it automatically or let you know what needs attention. I'd rather slow down than give you broken code!

Iterating Together

My generated code is a starting point. Here's how we can refine it together:

Request changes

"Add a filter for active customers only"

Tell me what to modify

Ask why

"Why did you use a left join here?"

I'll explain my reasoning

Try again

"Try a different approach using window functions"

I'll give you a fresh solution

Edit yourself

Make quick tweaks directly

Sometimes that's faster!

Chonk's Workflow Tip

Let me handle the boilerplate, then iterate on the business logic together. It's way faster than writing everything from scratch!