Documenting code, one commit at a time.
Managing costs associated with AI-powered features, such as text, image, and video generation, can be complex. Our platform needed a unified system to convert these costs into credits, manage profit margins, and track consumption effectively.
Previously, our credit system lacked a standardized approach. Calculating costs for various AI services (text, image,
The Breniapp project is integrating fal.ai to provide queue-based asynchronous image generation. This enhancement expands the platform's AI capabilities by introducing a new provider for image creation, offering a scalable and efficient solution for content generation.
Traditional synchronous image generation can be slow and resource-intensive,
Breniapp is enhancing its AI capabilities by integrating with Fal.ai to offer a broader range of image and video models. This update focuses on expanding the selection of available models and incorporating their pricing for credit consumption, enabling users to leverage advanced AI functionalities directly within the platform.
The update introduces several new
Campaign emails often require localization for diverse audiences. The landing project recently tackled this challenge by automating the translation process using AI, significantly improving efficiency and reach.
Previously, translating campaign emails was a manual and time-consuming process. Each email subject and body needed to be translated into multiple languages, requiring
In the Breniapp project, we've been focused on improving the user experience through AI-powered content generation. A key part of this is crafting effective prompts for the AI. Recently, we enhanced how the system uses onboarding data to create these prompts, leading to more relevant and personalized outputs.
Initially, the AI prompt generation
The Breniapp project focuses on streamlining brand development. A new feature enhances the onboarding process by incorporating AI-driven analysis of visual references. This allows users to define their brand's visual style through an intuitive, keyword-driven interface.
The new "Visual DNA" step in the onboarding process leverages AI to analyze uploaded
The Breniapp platform now offers per-tenant AI model assignments, providing more control and predictability in generation flows.
Previously, the system relied on a fallback mechanism to select an AI model. This could lead to inconsistent results and required users to manually pick a model for each generation. The new approach eliminates this ambiguity by allowing administrators to explicitly
When connecting quick actions to an AI service, developers must move beyond simple string manipulation and leverage the power of AI for more sophisticated content transformations.
Initially, basic functionalities like shortening content or changing a call to action (CTA) might seem achievable through simple string truncation or concatenation.
Reporting on tenant AI usage is crucial for understanding resource consumption and billing in Breniapp, a multi-tenant application. However, overly complex reports can obscure key metrics. We recently simplified the tenant AI usage table to focus on the most essential data points.
The original tenant AI usage table contained redundant information and unnecessary
This post delves into recent improvements made to the onboarding process in Breniapp, focusing on a more intuitive and user-friendly experience. These changes align the onboarding flow with the Lovable specification, specifically targeting CTA selection and copy style options.
Previously, the process of selecting primary and secondary Call-to-Action (CTA) options during
