Rayan

Rayan

Founder at FichaSync (fichasync.app)

About

Building FichaSync (https://fichasync.app) — an AI supplier catalog normalizer & Pre-CSV auditor for Shopify, WooCommerce, and PrestaShop stores and agencies. Turning messy vendor PDFs & Excels into clean, import-ready CSVs in 2 minutes.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Maker History

  • FichaSync
    FichaSyncTurn messy supplier Excel & PDFs into Shopify CSVs in 2m
    Nov 2026
  • 🎉
    Joined Product HuntNovember 17th, 2026

Forums

•

3h ago

Launching FichaSync today: supplier PDF/Excel to clean CSV

Hey Product Hunt!

I'm Rayan, solo founder building FichaSync. After seeing how many hours e-commerce stores and agencies lose fixing broken vendor spreadsheets (duplicate SKUs, "Call for price" rows, unitless specs, and 50-page PDFs), I built a tool that cleans and audits them side-by-side before import.

You can test it in 1 click with our sample broken catalog (no signup needed) and export clean Shopify, WooCommerce, or PrestaShop CSVs.

Would love your honest feedback on our launch today:

•

3h ago

How do you audit your email marketing sequences to improve subscriber retention rates?

Our newsletter open rate fell to fifteen percent over three months. Unsubscriptions climbed steadily. I reviewed past campaigns. Found dense paragraphs full of heavy industry jargon. The emails felt stiff and hard to read on mobile. I changed the format of email marketing sequences by cutting each email to three paragraphs, with one actionable tip each. Readers could finish in thirty seconds without scrolling. I also checked subscriber retention rates to see if the changes helped. Open rate returned to twenty-eight percent by the end of the month.

What subject line style works best for keeping your email audience engaged over time?

My LLM never crashed. It just told a marketing manager to claim 8 engineers.

I build LinkedInRank, which rewrites LinkedIn profiles and tailors resumes with an LLM. Nothing ever crashed. The output just read well and was quietly wrong.

Some real ones from my commit log:

  • A marketing manager's profile check suggested writing "Managed team of 8 engineers " with a 25% improvement. There were no engineers anywhere in that profile.

  • A nurse with 7 years of experience and a BSc was written up as "Aspiring".

  • Bullets came back as "Architected managing " and "Led led".

  • Connection notes took the recipient's job as the sender's own story.

  • Cover letters kept ending sentences with filler like " , ensuring consistent publishing".

Prompting alone never fixed these. What worked was checking after generation, in code: every number, skill and employer in the output has to appear in the person's own resume or profile, or it's flagged or dropped. A bullet has to be supported by the role it sits under, or it's removed. Example text uses [brackets] instead of plausible fake numbers. The prompt asks; the check enforces.

View more