How to Identify Keywords for Product with AI in conbase.ai
Introduction
- The Goal:
- By the end of this guide, you'll quickly generate relevant, high-intent keywords for hundreds or thousands of product records, streamlining your e-commerce SEO workflow.
- The Problem:
- Manually brainstorming and researching keywords for each product is slow, inconsistent, and doesn’t scale. Marketing teams spend hours per SKU, which delays product launches and hurts search visibility.
- The Solution:
- Conbase.ai’s AI-powered pipeline lets you identify keywords at scale using custom prompts tuned to your catalog and brand voice. You build a workflow once, then reuse it whenever new products arrive.
- Prerequisites:
- A Conbase.ai account
- A CSV with product data (name, description, category, price, existing tags)
- Basic knowledge of your SEO strategy
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
Log in to your Conbase.ai dashboard and click “New Project.” Name it "Keyword Identification – 2025" to keep things organized.
Upload Your Product Data (CSV)
Drag your CSV into the uploader. Conbase.ai detects headers automatically.
Data prep tips:
- Clear column names (Product_Name, Description, Category, Price)
- No strange characters or line breaks
- Include any fields that help describe the product (materials, brand, etc.)
Step 2: Build Your AI Generation Pipeline
Add an Action Step
Inside the project, click “Add Step.” Choose “Create New.” Name the step Identify Keywords and add it to your pipeline.
Set Up Your Custom Prompt: 3-Part Recipe
Part 1: Instruction
You are an e-commerce SEO specialist. Identify 5-10 high-intent, buyer-focused keywords for each product. Return them as a comma-separated list in lowercase. Avoid brand names and filler words.
Part 2: Context
Add dynamic data pills:
Product name: {Product_Name}
Description: {Description}
Category: {Category}
Price: {Price}
Part 3: Output
- Select or create a column called identified_keywords.
- Add an example:
wireless earbuds, bluetooth headphones, portable audio, noise cancelling, sports earbuds
Click “Save Changes.”
Step 3: Configure and Run the Pipeline
Fine-Tune 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" leaves available data untouched
Select Rows and Execute
- Choose 10 rows for a test run.
- Click “Run Pipeline.”
- Review the results. Tweak the prompt if any keywords look off.
- When happy, select all rows and run the full job.
Step 4: Review and Export Your Results
Quality Check
- Open random rows to ensure keywords match the product.
- Look for duplicates or generic terms like “best product.”
- Spot-fix any outliers by rerunning individual rows.
Export as CSV
- Click the export button in the lower right corner.
- Download the CSV containing your original data plus the identified_keywords column.
- Import it into your e-commerce platform or SEO tool.
Conclusion and Next Steps
You’ve automated keyword discovery for your entire product catalog. The pipeline is reusable, so when new SKUs arrive, just import the data and run the same workflow.
- Time saved: Hours per 100 products
- Consistency: AI follows your exact formatting rules
- Scalability: Process up to 10,000 rows in one go
Ready to tackle more tasks? Build additional pipelines for product descriptions, tag generation, or category mapping, all inside Conbase.ai.
Book Your Free Conbase.ai Demo and see how else you can streamline content operations.
