All work

Case study 06

Ad intelligence SaaS

Refractr AI

E-commerce brands waste ad spend validating products and campaigns by hand.

The actual website

Try it for yourself.

refractrai.com

Opening Refractr AI…

Open the website in a new tab ↗

Explore the actual website. Scroll and click inside the frame.

Open full website

01 The project

What we
built.

An ad library with product-validation metrics and AI-generated strategy briefs, with credit-based billing through Stripe. Third-party data enrichment and full technical SEO complete the platform.

02 In practice

Inside the product.

Follow the experience from first step to outcome. These interactive illustrations use example data.

Explore Refractr AI
Start with the source

A library
to look through.

Search ads and inspect the creative before deciding what to explore.

Creative
Example video ad
▷

See the product
in a new light.

Illustrative walkthrough. Example data.

1 of 3

Explore the ad library

A searchable collection of ads gives a brand a place to start its research. Creative formats shown here are illustrative examples.

03 Design & engineering

Behind the build.

The decisions, the working parts and what connects them.

Refractr AI centres on an ad library: a searchable collection of ads enriched with product-validation metrics, so a brand can judge what is worth pursuing before committing spend. Third-party data enrichment feeds those metrics instead of manual research.

On top of the library, the platform generates strategy briefs with AI — using Gemini and OpenAI models — turning raw ad data into something a marketer can act on directly. Billing is credit-based through Stripe, so cost tracks usage.

The build also covered full technical SEO across the site. Refractr AI is live as a SaaS today.

The working parts.

How the build is organised.

  1. Client

    • Web app
  2. Server

    • Ad library
    • Strategy briefs
    • Credit billing
  3. Services

    • Gemini / OpenAI
    • Supabase
    • Stripe

Built with

  • Next.js
  • Supabase
  • Stripe
  • Gemini / OpenAI

For a similar project

The decisions
that matter.

Connect research to an output a marketer can use. The enriched ad library supports product evaluation, then AI-generated briefs turn that information into a next step. Stripe credit billing sits around the work so usage and access belong to the same product.

Refractr is a live SaaS product. The case connects the research library, generated output and billing system in one workflow. For a similar tool, define the source data, what a useful brief contains and how usage is charged before expanding the feature list.

AI features for SaaS products

By Alwan Technologies · Updated

Have a project like this in mind?