CheatSheats on Principles

AI TESTING AGENT – ROLE DEFINITION & GUIDELINES

Sat, 05 Jul 2025 00:00:00 +0000

Absolutely. Here’s the generalized, reusable version of the AI Testing Agent role definition. You can plug in any project context by replacing [PROJECT DESCRIPTION], and it’s structured for universal application across projects requiring advanced technical validation:

🎯 ROLE PURPOSE

As the AI Testing Agent, your mission is to validate the functional, architectural, analytical, and usability quality of a system described as:

[PROJECT DESCRIPTION]

You are not a task executor—you are a technical quality engineer with strategic autonomy. You are expected to:

Mastering Vibe Coding! A Developer's Guide to AI-Assisted Programming

Mon, 23 Jun 2025 00:00:00 +0000

What is Vibe Coding?

Vibe coding is a term coined by AI legend Andrej Karpathy to describe the fluid, iterative way of programming alongside Large Language Models (LLMs). It’s that magical flow state where you generate code, tweak it, generate more, and make incredible progress by working collaboratively with AI tools like ChatGPT and Claude.

But here’s the thing: while vibe coding is incredibly powerful and fun, it’s easy to get led astray. Without proper technique, you might find yourself with 200 lines of broken code, wondering what went wrong.

Python Syntactic Sugar Cheatsheet

Mon, 23 Jun 2025 00:00:00 +0000

🟢 Core Patterns

List Comprehensions

When to use: Transform or filter a list of items

Basic Pattern:

[expression for item in list]

Simple Examples:

# Transform each number
numbers = [1, 2, 3, 4, 5]
squares = [x * x for x in numbers]
# Result: [1, 4, 9, 16, 25]

# Filter with condition
even_numbers = [x for x in numbers if x % 2 == 0]
# Result: [2, 4]

# Instead of this loop:
result = []
for x in numbers:
 if x % 2 == 0:
 result.append(x * x)

# Write this:
result = [x * x for x in numbers if x % 2 == 0]

Dictionary Comprehensions

When to use: Build dictionaries from existing data

Pydantic + LLM Structured Outputs Cheat Sheet

Sat, 21 Jun 2025 00:00:00 +0000

What is Pydantic?

A Python library for data validation and serialization that automatically:

Validates data types
Converts types when possible
Provides clear error messages
Serializes to/from JSON, dictionaries

Basic Pydantic Model

from pydantic import BaseModel

class Evaluation(BaseModel):
 is_acceptable: bool
 feedback: str

Using with LLMs

The Problem

LLMs return unstructured text
Hard to parse and validate
Inconsistent formats

The Solution

Use Pydantic models to enforce structure!

response = gemini.beta.chat.completions.parse(
 model="gemini-2.0-flash", 
 messages=messages, 
 response_format=Evaluation # Your Pydantic model
)

# Returns validated Evaluation object
print(response.is_acceptable) # bool
print(response.feedback) # str

How It Works Under the Hood

Your Pydantic Model → JSON Schema (automatic conversion)
JSON Schema → LLM API (as instructions)
LLM generates → JSON matching schema
Library parses → Validated Pydantic object

Example JSON Schema Generated

{
 "type": "object",
 "properties": {
 "is_acceptable": {"type": "boolean"},
 "feedback": {"type": "string"}
 },
 "required": ["is_acceptable", "feedback"]
}

Benefits

✅ Guaranteed structure - Always get expected fields
✅ Type safety - Fields are correct types
✅ Error handling - Validation catches format errors
✅ Easy processing - Use data immediately in code
✅ No manual parsing - Library handles conversion

The Culture Map Complete Study Guide

Sat, 21 Jun 2025 00:00:00 +0000

🎯 Core Concept

The Big Idea: Globalization has created unprecedented cultural complexity in the workplace. The Culture Map provides a systematic framework for navigating these differences through cultural relativity - understanding cultures in relation to each other, not as absolutes.

Why It Matters: Germans appear direct compared to Japanese colleagues but indirect compared to Dutch team members. This relative positioning makes cultural navigation practical and actionable.

📊 The 8 Cultural Dimensions

1. Communicating: Low-Context ↔ High-Context

Low-Context (Left): Messages are explicit, clear, and literal High-Context (Right): Messages rely on context, subtlety, and “reading between the lines”

Code Review practices

Tue, 10 Jun 2025 00:00:00 +0000

Introduction

A code review is a process where someone other than the author(s) of a piece of code examines that code.

At Google, we use code review to maintain the quality of our code and products.

This documentation is based on Google’s canonical description of their code review processes and policies.

Guide Structure

This page provides an overview of the code review process. There are two other comprehensive documents that are part of this guide:

Ownership Principles

Tue, 10 Jun 2025 00:00:00 +0000

Everything needs an owner
The owner doesn’t have to be the task executor
Ownership can change (but must be notified to the team)
The owner can have assistants but there is only one owner
Ownership must be actively accepted by the owner - you can’t assign ownership without their knowledge
The owner should actively communicate any changes, progress, or issues to the team and stakeholders
If the owner delegates tasks, they should ensure the delegate understands their responsibilities and has the necessary resources to fulfill them

N8N Advanced n8n Workflow Examples - Database & API Integration

Mon, 09 Jun 2025 00:00:00 +0000

Advanced n8n Workflow Examples - Database & API Integration

Complex workflows with error handling, data validation, and multi-step processing. These examples demonstrate enterprise-level automation patterns.

1. CRM Data Synchronization with Error Handling

Purpose: Sync external CRM data to local database with comprehensive error handling Use Case: Customer data synchronization, inventory management, data warehousing

{
 "name": "CRM to Database Sync with Error Handling",
 "nodes": [
 {
 "parameters": {
 "rule": {
 "interval": [
 {
 "field": "cronExpression",
 "expression": "0 */4 * * *"
 }
 ]
 }
 },
 "id": "schedule-sync",
 "name": "Every 4 Hours",
 "type": "n8n-nodes-base.scheduleTrigger",
 "typeVersion": 1.2,
 "position": [240, 400]
 },
 {
 "parameters": {
 "method": "GET",
 "url": "https://api.crm-system.com/v2/contacts",
 "authentication": "predefinedCredentialType",
 "nodeCredentialType": "httpHeaderAuth",
 "sendQuery": true,
 "queryParameters": {
 "parameters": [
 {
 "name": "limit",
 "value": "100"
 },
 {
 "name": "updated_since",
 "value": "={{ $workflow.lastSuccessTime || DateTime.now().minus({days: 1}).toISO() }}"
 },
 {
 "name": "include_deleted",
 "value": "true"
 }
 ]
 },
 "options": {
 "pagination": {
 "paginationMode": "updateAParameterInEachRequest",
 "paginationCompleteExpression": "={{ !$response.body.has_more }}",
 "limitPagesFetched": true,
 "maxRequests": 20,
 "pageSize": 100
 },
 "retry": {
 "enabled": true,
 "maxTries": 3,
 "waitBetweenTries": 2000
 },
 "timeout": 15000
 }
 },
 "id": "fetch-crm-data",
 "name": "Fetch CRM Contacts",
 "type": "n8n-nodes-base.httpRequest",
 "typeVersion": 4.2,
 "position": [460, 400],
 "credentials": {
 "httpHeaderAuth": {
 "id": "crm-api-credentials",
 "name": "CRM API Key"
 }
 }
 },
 {
 "parameters": {
 "conditions": {
 "options": {
 "leftValue": "={{ $json.contacts && Array.isArray($json.contacts) && $json.contacts.length > 0 }}",
 "operation": "equal",
 "rightValue": true
 }
 }
 },
 "id": "check-data-exists",
 "name": "Has Contact Data?",
 "type": "n8n-nodes-base.if",
 "typeVersion": 2,
 "position": [680, 400]
 },
 {
 "parameters": {
 "fieldToSplitOut": "contacts",
 "options": {}
 },
 "id": "split-contacts",
 "name": "Split Contact Array",
 "type": "n8n-nodes-base.itemLists",
 "typeVersion": 3.3,
 "position": [900, 320]
 },
 {
 "parameters": {
 "language": "javaScript",
 "jsCode": "// Validate and transform contact data\nconst validContacts = [];\nconst invalidContacts = [];\n\nfor (const item of $input.all()) {\n const contact = item.json;\n const errors = [];\n \n // Validation rules\n if (!contact.email || !/^[^\\s@]+@[^\\s@]+\\.[^\\s@]+$/.test(contact.email)) {\n errors.push('Invalid or missing email');\n }\n \n if (!contact.id || contact.id.toString().length < 1) {\n errors.push('Missing contact ID');\n }\n \n if (!contact.first_name || contact.first_name.trim().length < 1) {\n errors.push('Missing first name');\n }\n \n if (contact.phone && !/^[\\+]?[1-9][\\d\\s\\-\\(\\)]{7,15}$/.test(contact.phone.replace(/\\s/g, ''))) {\n errors.push('Invalid phone number format');\n }\n \n if (errors.length === 0) {\n // Transform valid contact\n const transformedContact = {\n external_id: contact.id.toString(),\n first_name: contact.first_name.trim(),\n last_name: (contact.last_name || '').trim(),\n email: contact.email.toLowerCase().trim(),\n phone: contact.phone ? contact.phone.replace(/[^\\d\\+]/g, '') : null,\n company: (contact.company || '').trim() || null,\n status: contact.status || 'active',\n tags: Array.isArray(contact.tags) ? contact.tags.join(',') : null,\n created_at: contact.created_date || contact.created_at,\n updated_at: contact.updated_date || contact.updated_at,\n is_deleted: contact.is_deleted || false,\n sync_timestamp: new Date().toISOString(),\n source: 'crm_sync'\n };\n \n validContacts.push({ json: transformedContact });\n } else {\n // Log invalid contact\n invalidContacts.push({ \n json: { \n original_contact: contact, \n validation_errors: errors,\n rejected_at: new Date().toISOString()\n } \n });\n \n console.log(`Invalid contact ${contact.id}: ${errors.join(', ')}`);\n }\n}\n\nconsole.log(`Processed ${$input.all().length} contacts: ${validContacts.length} valid, ${invalidContacts.length} invalid`);\n\n// Store invalid contacts for later review\nif (invalidContacts.length > 0) {\n $workflow.staticData.invalidContacts = invalidContacts;\n}\n\nreturn validContacts;"
 },
 "id": "validate-transform",
 "name": "Validate & Transform Data",
 "type": "n8n-nodes-base.code",
 "typeVersion": 2,
 "position": [1120, 320]
 },
 {
 "parameters": {
 "operation": "select",
 "schema": {
 "__rl": true,
 "value": "public",
 "mode": "list",
 "cachedResultName": "public"
 },
 "table": {
 "__rl": true,
 "value": "contacts",
 "mode": "list",
 "cachedResultName": "contacts"
 },
 "where": {
 "values": [
 {
 "column": "external_id",
 "condition": "equal",
 "value": "={{ $json.external_id }}"
 }
 ]
 },
 "options": {}
 },
 "id": "check-contact-exists",
 "name": "Check if Contact Exists",
 "type": "n8n-nodes-base.postgres",
 "typeVersion": 2.4,
 "position": [1340, 320],
 "credentials": {
 "postgres": {
 "id": "postgres-db-connection",
 "name": "PostgreSQL Database"
 }
 }
 },
 {
 "parameters": {
 "conditions": {
 "options": {
 "leftValue": "={{ $('Check if Contact Exists').itemMatching($itemIndex).json }}",
 "operation": "isNotEmpty"
 }
 }
 },
 "id": "contact-exists-check",
 "name": "Contact Exists?",
 "type": "n8n-nodes-base.if",
 "typeVersion": 2,
 "position": [1560, 320]
 },
 {
 "parameters": {
 "operation": "update",
 "schema": {
 "__rl": true,
 "value": "public",
 "mode": "list"
 },
 "table": {
 "__rl": true,
 "value": "contacts",
 "mode": "list"
 },
 "updateKey": "external_id",
 "columns": {
 "mappingMode": "defineBelow",
 "value": {
 "first_name": "={{ $json.first_name }}",
 "last_name": "={{ $json.last_name }}",
 "email": "={{ $json.email }}",
 "phone": "={{ $json.phone }}",
 "company": "={{ $json.company }}",
 "status": "={{ $json.status }}",
 "tags": "={{ $json.tags }}",
 "updated_at": "={{ $json.updated_at }}",
 "sync_timestamp": "={{ $json.sync_timestamp }}",
 "is_deleted": "={{ $json.is_deleted }}"
 }
 },
 "options": {}
 },
 "id": "update-contact",
 "name": "Update Existing Contact",
 "type": "n8n-nodes-base.postgres",
 "typeVersion": 2.4,
 "position": [1780, 220],
 "credentials": {
 "postgres": {
 "id": "postgres-db-connection",
 "name": "PostgreSQL Database"
 }
 }
 },
 {
 "parameters": {
 "operation": "insert",
 "schema": {
 "__rl": true,
 "value": "public",
 "mode": "list"
 },
 "table": {
 "__rl": true,
 "value": "contacts",
 "mode": "list"
 },
 "columns": {
 "mappingMode": "defineBelow",
 "value": {
 "external_id": "={{ $json.external_id }}",
 "first_name": "={{ $json.first_name }}",
 "last_name": "={{ $json.last_name }}",
 "email": "={{ $json.email }}",
 "phone": "={{ $json.phone }}",
 "company": "={{ $json.company }}",
 "status": "={{ $json.status }}",
 "tags": "={{ $json.tags }}",
 "created_at": "={{ $json.created_at }}",
 "updated_at": "={{ $json.updated_at }}",
 "sync_timestamp": "={{ $json.sync_timestamp }}",
 "is_deleted": "={{ $json.is_deleted }}",
 "source": "={{ $json.source }}"
 }
 },
 "options": {
 "ignoreDuplicates": true
 }
 },
 "id": "insert-contact",
 "name": "Insert New Contact",
 "type": "n8n-nodes-base.postgres",
 "typeVersion": 2.4,
 "position": [1780, 420],
 "credentials": {
 "postgres": {
 "id": "postgres-db-connection",
 "name": "PostgreSQL Database"
 }
 }
 },
 {
 "parameters": {
 "mode": "combine",
 "combinationMode": "multiplex",
 "options": {}
 },
 "id": "merge-results",
 "name": "Merge Update/Insert Results",
 "type": "n8n-nodes-base.merge",
 "typeVersion": 2.1,
 "position": [2000, 320]
 },
 {
 "parameters": {
 "language": "javaScript",
 "jsCode": "// Generate sync summary report\nconst allResults = $input.all();\nconst totalProcessed = allResults.length;\n\nconst summary = {\n sync_completed_at: new Date().toISOString(),\n total_contacts_processed: totalProcessed,\n successful_operations: totalProcessed,\n failed_operations: 0,\n invalid_contacts: $workflow.staticData.invalidContacts?.length || 0,\n sync_duration_seconds: Math.round((Date.now() - new Date($('Every 4 Hours').first().json.timestamp || Date.now()).getTime()) / 1000),\n next_sync_scheduled: DateTime.now().plus({ hours: 4 }).toISO()\n};\n\n// Log invalid contacts if any\nif ($workflow.staticData.invalidContacts?.length > 0) {\n console.log('Invalid contacts found:', JSON.stringify($workflow.staticData.invalidContacts, null, 2));\n}\n\nreturn [{ json: summary }];"
 },
 "id": "generate-summary",
 "name": "Generate Sync Summary",
 "type": "n8n-nodes-base.code",
 "typeVersion": 2,
 "position": [2220, 320]
 },
 {
 "parameters": {
 "resource": "message",
 "operation": "post",
 "channel": "#data-sync",
 "text": "✅ CRM Sync Completed Successfully\n\n📊 *Sync Summary:*\n• Total Contacts: {{ $json.total_contacts_processed }}\n• Successful: {{ $json.successful_operations }}\n• Failed: {{ $json.failed_operations }}\n• Invalid: {{ $json.invalid_contacts }}\n• Duration: {{ $json.sync_duration_seconds }}s\n• Next Sync: {{ DateTime.fromISO($json.next_sync_scheduled).toLocaleString() }}\n\n🕐 Completed: {{ DateTime.fromISO($json.sync_completed_at).toLocaleString() }}",
 "otherOptions": {
 "username": "CRM Sync Bot",
 "icon_emoji": ":arrows_counterclockwise:"
 }
 },
 "id": "success-notification",
 "name": "Send Success Notification",
 "type": "n8n-nodes-base.slack",
 "typeVersion": 2.1,
 "position": [2440, 320],
 "credentials": {
 "slackApi": {
 "id": "slack-api-credentials",
 "name": "Slack API Token"
 }
 }
 },
 {
 "parameters": {
 "resource": "message",
 "operation": "post",
 "channel": "#alerts",
 "text": "❌ CRM Sync Failed\n\n*Error Details:*\n• Workflow: {{ $workflow.name }}\n• Error: {{ $json.error?.message || 'Unknown error' }}\n• Time: {{ new Date().toISOString() }}\n• Node: {{ $json.error?.node || 'Unknown' }}\n\n*Stack Trace:*\n```{{ $json.error?.stack || 'No stack trace available' }}```",
 "otherOptions": {
 "username": "Error Bot",
 "icon_emoji": ":x:"
 }
 },
 "id": "error-notification",
 "name": "Send Error Alert",
 "type": "n8n-nodes-base.slack",
 "typeVersion": 2.1,
 "position": [900, 580],
 "credentials": {
 "slackApi": {
 "id": "slack-api-credentials",
 "name": "Slack API Token"
 }
 }
 }
 ],
 "connections": {
 "Every 4 Hours": {
 "main": [
 []
 ]
 },
 "Split Contact Array": {
 "main": [
 [
 {
 "node": "Validate & Transform Data",
 "type": "main",
 "index": 0
 }
 ]
 ]
 },
 "Validate & Transform Data": {
 "main": [
 [
 {
 "node": "Check if Contact Exists",
 "type": "main",
 "index": 0
 }
 ]
 ]
 },
 "Check if Contact Exists": {
 "main": [
 [
 {
 "node": "Contact Exists?",
 "type": "main",
 "index": 0
 }
 ]
 ]
 },
 "Contact Exists?": {
 "main": [
 [
 {
 "node": "Update Existing Contact",
 "type": "main",
 "index": 0
 }
 ],
 [
 {
 "node": "Insert New Contact",
 "type": "main",
 "index": 0
 }
 ]
 ]
 },
 "Update Existing Contact": {
 "main": [
 [
 {
 "node": "Merge Update/Insert Results",
 "type": "main",
 "index": 0
 }
 ]
 ]
 },
 "Insert New Contact": {
 "main": [
 [
 {
 "node": "Merge Update/Insert Results",
 "type": "main",
 "index": 1
 }
 ]
 ]
 },
 "Merge Update/Insert Results": {
 "main": [
 [
 {
 "node": "Generate Sync Summary",
 "type": "main",
 "index": 0
 }
 ]
 ]
 },
 "Generate Sync Summary": {
 "main": [
 [
 {
 "node": "Send Success Notification",
 "type": "main",
 "index": 0
 }
 ]
 ]
 }
 },
 "active": false,
 "settings": {
 "executionOrder": "v1",
 "saveDataErrorExecution": "all",
 "saveDataSuccessExecution": "all",
 "saveManualExecutions": true,
 "callerPolicy": "workflowsFromSameOwner",
 "errorWorkflow": {
 "id": "error-handler-workflow"
 }
 },
 "versionId": "crm-sync-advanced-v1",
 "meta": {
 "templateCredsSetupCompleted": true
 },
 "id": "crm-database-sync-advanced",
 "tags": ["crm", "database", "synchronization", "error-handling", "validation"]
}

2. Multi-Step Order Processing Pipeline

Purpose: Complex order processing with inventory checks, payment processing, and fulfillment Use Case: E-commerce order management, supply chain automation

N8N Developer Cheatsheet

Mon, 09 Jun 2025 00:00:00 +0000

n8n Developer Cheatsheet

A comprehensive reference guide for building n8n workflows based on official documentation from docs.n8n.io.

Node Architecture Fundamentals

Data Flow Model

All data in n8n flows as arrays of JSON objects with this structure:

[
 { "json": { "key1": "value1", "key2": "value2" } },
 { "json": { "key1": "value3", "key2": "value4" } }
]

Key Requirements:

Data must be an array of objects
Each object requires a json key wrapping actual data
From v0.166.0+, n8n auto-adds json key for Function/Code nodes
Custom nodes must ensure proper structure

Node Types

Trigger Nodes (⚡ icon)

N8N Simple n8n workflow examples

Mon, 09 Jun 2025 00:00:00 +0000

Simple n8n Workflow Examples - Ready to Import JSON

Complete, working JSON examples for basic n8n workflows. Copy and import these directly into your n8n instance.

1. Webhook to Slack Notification

Purpose: Receive webhook data and send notification to Slack Use Case: Simple alert system, form submissions, external service notifications

{
 "name": "Webhook to Slack Alert",
 "nodes": [
 {
 "parameters": {
 "httpMethod": "POST",
 "path": "webhook-alert",
 "options": {}
 },
 "id": "webhook-node",
 "name": "Webhook",
 "type": "n8n-nodes-base.webhook",
 "typeVersion": 1.1,
 "position": [240, 300],
 "webhookId": "12345678-1234-1234-1234-123456789abc"
 },
 {
 "parameters": {
 "resource": "message",
 "operation": "post",
 "channel": "#alerts",
 "text": "🚨 New Alert Received!\n\n*Message:* {{ $json.message || 'No message provided' }}\n*Source:* {{ $json.source || 'Unknown' }}\n*Time:* {{ new Date().toLocaleString() }}",
 "otherOptions": {
 "username": "Alert Bot",
 "icon_emoji": ":warning:"
 }
 },
 "id": "slack-node",
 "name": "Send Slack Message",
 "type": "n8n-nodes-base.slack",
 "typeVersion": 2.1,
 "position": [460, 300],
 "credentials": {
 "slackApi": {
 "id": "slack-credentials",
 "name": "Slack API Credentials"
 }
 }
 }
 ],
 "connections": {
 "Webhook": {
 "main": [
 [
 {
 "node": "Send Slack Message",
 "type": "main",
 "index": 0
 }
 ]
 ]
 }
 },
 "active": false,
 "settings": {
 "executionOrder": "v1"
 },
 "versionId": "simple-webhook-slack-v1",
 "meta": {
 "templateCredsSetupCompleted": true
 },
 "id": "webhook-slack-simple",
 "tags": ["webhook", "slack", "alerts", "simple"]
}

2. Daily API Data Fetch

Purpose: Schedule daily API calls to fetch and process data Use Case: Daily reports, data synchronization, monitoring