In the devlog-ist/landing project, we're focused on delivering high-quality content. A crucial part of this is ensuring that AI-generated content meets our standards before it's published.

The Problem: Silent Content Truncation

AI models, particularly when generating longer pieces of content, can sometimes be cut short due to token limits or other constraints.

The devlog-ist/landing project focuses on creating landing pages. Recently, we tackled a performance bottleneck during the LinkedIn publishing process. The issue arose from sending large base64 encoded images directly within the publish request, leading to 413 errors from Nginx due to exceeding the maximum request size.

The Problem

LinkedIn's API has limits on request size. Sending a

Introduction

This post explores the implementation of cost tracking and budget limits for AI operations within the devlog-ist/landing project. We'll examine how per-request costs are tracked in EUR, how pricing is stored per model, and how monthly cost limits are enforced per plan.

Cost Tracking in EUR

The system now tracks the cost of each AI operation in EUR. This involves:

The devlog-ist/landing project focuses on creating landing pages and managing content for various platforms. This post details the addition of an independent LinkedIn random mode for post generation.

The Problem

Previously, the application used a single random mode toggle that controlled whether random post examples and prompts were used across all platforms.

This post details the recent enhancements to the content generation process within the devlog-ist/landing project, focusing on the integration and management of LinkedIn prompts for improved content quality and platform-specific tailoring.

The Goal

The primary objective was to enhance the content generation workflow by incorporating LinkedIn-specific prompts, allowing for more targeted and

When developing tools for content generation, flexibility is key. A recent update to the devlog-ist/landing project focuses on providing more granular control over how content is generated for different platforms. Specifically, we've decoupled the random mode setting for LinkedIn from the portfolio's random mode.

The Problem: One Size Doesn't Fit All

Previously, a single "random mode"

The devlog-ist/landing project helps users track their development activity. We recently improved how the application handles revoked or expired GitHub API tokens. Previously, a 401 error would trigger a generic error log and continuous retry attempts during data synchronization. This led to unnecessary server load and delayed data updates.

Now, when a 401 error (Bad Credentials) is received

Introduction

We're enhancing the integration capabilities within our Filament-based application, specifically focusing on providing users with more control over syncing their GitHub activity. This feature aims to streamline the process of keeping user activity data up-to-date, providing a more seamless experience within the application.

Integrating the Sync GitHub Activity Action

Efficiently managing and synchronizing data is crucial for application performance. Recently, we enhanced the GitHub activity syncing process in our application by replacing a single-date picker with a more flexible date range calendar. This improvement, combined with a significant refactor, streamlines the synchronization logic and enhances user experience.

Enhanced Date Range Selection

Introduction

We've recently enhanced our platform to allow users to automate content publishing to external platforms like LinkedIn and Dev.to. This feature aims to simplify the content creation and distribution process by enabling users to set default publishing preferences.

Implementation Details

This enhancement introduces the ability for users to manage their auto-publishing