Batch Product Research

For each keyword compute:

• search volume
• total niche revenue
• average price
• average reviews
• average revenue per seller
• top-seller dominance
• estimated margin using conservative assumptions
• opportunity score and verdict

Use verdicts:

• VIABLE
• MARGINAL
• NOT RECOMMENDED
• ERROR

4. Optional deeper passes

For VIABLE or MARGINAL keywords only:

• run research_products(... focus="financial")
• optionally run amazon_keyword_research on the top 2-3 ASINs if keyword depth matters for the user’s goal

5. Present ranked results

Always include a comparison table first.

Then provide concise cards or sections for the strongest keywords.

6. Write artifacts when useful

If the user asked for files, or a file materially improves the result:

• write an HTML report
• write a CSV export

Keep the file generation deterministic. Prefer Python for CSV writing.

Output

At minimum return:

• number of keywords processed
• ranking table
• top recommendations
• artifact paths when files were written