I Asked Gemini to Grade My App Store Screenshots. Everything Scored 78–85.
Ask Gemini Vision to grade App Store screenshots out of 100 and good candidates and deliberately broken ones both land at 78–85. Here is how I measured the judge's discrimination power, dropped absolute scoring, and rebuilt it as debiased pairwise comparison.
Splitting Bulk Image Generation Cost in Two with Nano Banana 2 Lite: A Draft-and-Render Design
A two-tier cost design that routes first-pass generation to Nano Banana 2 Lite and final renders to the standard Nano Banana 2, with a minimal Python router you can adapt.
Putting Gemini image generation to work: from prompt design to thumbnails generated from video
A practical playbook for running Gemini image generation as a repeatable workflow instead of a lucky dip. From decomposing prompts into reproducible parts to the video-to-image automation unlocked by the Nano Banana 2 GA, with working code, a pre-publish quality gate, and a design that survives preview shutdowns.
When Revenue and Cost Don't Line Up in a Gemini-Powered Niche SaaS — Field Notes on Metering Usage and Reconciling with Stripe
In a niche SaaS built on the Gemini API, monthly revenue is visible but per-user usage cost is not, so your margin stays a mystery until month-end. These notes cover a metering layer that converts tokens to money in real time, monthly reconciliation against Stripe, early detection of unprofitable users, and idempotent webhooks.
Watching the 'Voice' of Generated Text: Catching a Silent Default-Model Swap Through Style Drift
When the default model changes over your head, the output can stay factually correct while its voice quietly shifts. This walks through fingerprinting the style of generated text and detecting drift statistically, with a dependency-free implementation you can drop into your pipeline.
Automating App Localization QA with the Gemini API: A Structured-Output Pipeline That Catches Translation Drift Early
Lessons from running 14-language localization across a 50M-download personal app portfolio, distilled into a production-ready Gemini 2.5 Pro structured-output evaluation pipeline that catches translation drift before users do.
Auto-Generating App Metadata in 30 Languages with Gemini API — Lessons from Beautiful HD Wallpapers
How I used Gemini API to auto-generate App Store and Google Play metadata in 30 languages for a 50M+ download wallpaper app. Covers prompt design, character limit handling, and real results from 3 months of production use.
Automating Pre-Release UI Checks with Gemini 3.2 Flash Vision — A Personal Dev Story
How I used Gemini 3.2 Flash's multimodal input to automatically QA iOS/Android app screenshots before each release. Detect text overflow, dark mode contrast issues, and layout breaks with a 30-line Python script — and why this works for indie developers without a QA team.
Turning my own artworks into 120 wallpaper variants in 30 days with Gemini 3.2 Pro and Imagen 4 — an artist-developer's content supply pipeline
A 30-day production log of building a pipeline that takes one of my own paintings and expands it into a 120-piece wallpaper series, using Gemini 3.2 Pro for structural analysis and Imagen 4 for variations. Includes real costs, quality gates, and downstream app KPIs.
Launching a Paid Service on Gemini API — A 2026 Roadmap
A practical 2026 roadmap for monetizing a service built on Gemini API — covering model selection, unit economics, pricing models, and the architectural decisions that decide whether your low API costs become a competitive edge or a price-war trap.
Gemini API Prepaid Billing Migration 2026 — Impact and Pre-Flight Checklist
Gemini API is moving to a prepaid billing model. Here's exactly what changes, what breaks if you ignore it, and the pre-flight checklist I used for my own production services.
Auto-Categorizing 3,000 Wallpaper Images With Gemini Vision API — A Real Production Account
Manually categorizing thousands of wallpaper images doesn't scale. This is a hands-on account of building an auto-classification pipeline with Gemini Vision API — covering design, implementation, actual cost, and the failure patterns I hit running 3,000 images through it.