Case Study · AI Platform · 2025

AiSiktir.app: image, video and audio generation

An internal Brand Design Ltd. experiment grew into a product for creators who otherwise had to move between separate AI tools and workflows.

A shared interface connects the generation providers with project history, credits, payments and job status. Failed jobs return credits, while the media editor remains a separate next product phase.

Services used

Most AI tools are either too complex for non-technical users or too narrow to produce real, usable content.

Creators jump between platforms, lose hours, and waste money on inconsistent results. The AI capability is there - the usable product around it isn’t.

Build a single platform where anyone - marketer, founder, creator - can generate images, video, and sound and actually put them to work, without ever touching a model directly.

We designed and built AiSiktir.app as a full-stack AI product that hides the complexity of orchestrating multiple AI providers behind one deliberately simple interface.

Frontend: A user dashboard for projects, credits, and history.

Backend: Orchestrates AI providers, job state, and retries.

Database: Tracks users, credits, and generation history.

Infrastructure: Updates go live without downtime.

For each medium the platform uses the best model available and can switch it as the landscape shifts.

Images - FLUX, Nano Banana (Pro / 2)

Video - Kling, Veo 3.1

Audio - Kling, Lirya 3

Result: one interface, multiple AI capabilities, one consistent output surface.

We implemented a credit-based system that abstracts the pricing differences between models and makes spend legible for end users.

Clear cost per generation, independent of the underlying provider. Stripe integration for global payments. Free onboarding credits to eliminate first-use friction.

Result: lower friction to first value, faster adoption, cleaner unit economics.

Generated media is already available in the platform. Editing and assembling that media within the same interface is the next planned product phase.

The next product phase is a media editor for arranging, branding and exporting generated assets inside the platform. The current case does not present that editor as a delivered feature.

Planned outcome: generating, editing and exporting content in one place.

AI tools often fail silently. We built against that from day one.

Every generation is tracked end-to-end. Failed jobs automatically refund credits. Clear, honest feedback in the UI at every step.

Result: trust and transparency - the parts of an AI product that actually compound.

AiSiktir.app started as an internal Brand Design Ltd. experiment and became a Bulgarian-language platform for AI video generation. Image and audio generation were added later.

The founder reports 50 registered accounts, with around 20-30 recurring users. The product reached these users without paid advertising. Registrations and recurring use are separate figures; no paid-user count is published.

This is a founder-owned product, not an independent client engagement. The recurring-user range described in the case is not a paid-user count; a fixed cohort period, paid conversion and retention rate are not published here.

AiSiktir.app is not just a tool. It’s a proof that we can architect - and ship - complex, multimodal AI products as scalable business systems, not just one-off features.

We use the product experience in B2A Product and in web development projects with AI features. The brief determines the scope of each project.

The next product phase is a media editor for arranging, branding and exporting generated assets inside the platform. The current case does not present that editor as a delivered feature.

If the product brief is clear, we can discuss the implementation directly. When the business questions are still open, the Business Audit can help define the scope.