How to Generate Product Tags with AI in conbase.ai

Published on July 08, 2025

By Daniel Manco

Introduction

The Goal:
- By the end of this guide, you'll be able to add accurate, SEO-friendly tags to hundreds or thousands of products in minutes, improving search and navigation on your store.
The Problem:
- Manually tagging each product is slow, inconsistent, and hard to scale. Teams often spend hours reviewing descriptions, which delays launches and hurts site performance.
The Solution:
- Conbase.ai lets you create a custom AI pipeline that understands your catalog and automatically suggests tags that match your store's style and rules.
Prerequisites:
- A Conbase.ai account
- A CSV file with your products (name, description, category, price, current tags)
- Basic knowledge of your tagging guidelines

Are you here for the first time ? Then watch a full conbase.ai workflow in action

This video walks you through a complete conbase.ai workflow, from input to final output, so you can see exactly how the platform works and how to get the most out of its features.

Step 1: Set Up Your Project and Import Data

Create a New Project

Upload Your Product Data (CSV)

Upload your CSV. Conbase.ai shows a preview so you can confirm columns look right.

Data prep tips:

Clear headers: product_name, description, category, price, existing_tags
Remove stray characters
Keep descriptions concise but detailed enough for good tagging

Step 2: Build Your AI Generation Pipeline

Add an Action Step

Click Add Step, then Create New. Name it Generate Product Tags and add it to the pipeline.

Create Your Custom Prompt

Your prompt has three parts: instruction, context, and output.

Part 1: Instruction

You are an ecommerce merchandising expert. Generate 5-8 concise product tags. Use lowercase, comma-separated words. Avoid duplicate or generic terms. Do not invent features.

Part 2: Context

Product Name: {product_name}
Description: {description}
Category: {category}
Price: {price}
Current Tags: {existing_tags}

Part 3: Output

Create a new column called generated_tags
Add two examples to set the style

Output Column: generated_tags
Output Example: bluetooth, over-ear, noise-canceling, travel, black

Output Column: generated_tags
Output Example: organic, cotton, crewneck, summer, women

Save the step.

Step 3: Configure and Run the Pipeline

AI Settings

Model: "GPT-4o"
Processing Mode: "Instant" for testing and for fast execution, "Scheduled" for large batches and 50% less API costs
Integration: "Fill if empty" keeps already available tags untouched

Test, Review, and Go Live

Select 10 rows and run a test.
Check the generated_tags column for accuracy and format.
Tweak the prompt if tags are off or too generic.
When happy, select all rows and run the full pipeline.

Step 4: Review and Export Results

Quality Check

Open random cells to ensure tags fit the product.
Look for duplicates or made-up features.
Spot-fix any outliers directly in the table.

Export

Click Export in the bottom right corner. Conbase.ai downloads a CSV with your original data plus the new generated_tags column.

Conclusion and Next Steps

You just automated product tagging for your entire catalog. Keep this pipeline handy for every new product drop.

Time saved: compare manual tagging hours vs minutes now
Consistency: every product follows the same tagging rules
Scalability: handle thousands of products without extra staff

Book Your Free Conbase.ai Demo and see how else you can streamline content operations.