Moving app AI work from runtime calls to a pre-ship batch pass
Where you put a Gemini call decides whether your request count scales with users or with assets. Here is the decision rule I used to move classification into a pre-ship batch pass, plus a resumable implementation.
Once You Pass Twenty Mediation Groups, How Do You Find the Setting That Went Missing?
As ad mediation groups multiply, missing sources and type drift accumulate quietly. Here is the split I settled on: normalize the settings into one matrix, let code confirm the gaps, and send Gemini only the cells that need judgment.
How Many Assistant-Dependent Lines Are Still in Your App?
On September 4th, Google Assistant on Android begins its replacement by Gemini. Here is how to grep your own project for every entry point an assistant can open, and how to turn that list into utterances you can actually test on a device.
Why My Length Limit Only Failed on the English Notifications, and the Width-Based Fit That Replaced It
I had Gemini write push notifications in Japanese and English, and only the English ones came out truncated on real devices. The culprit was measuring length in characters. Here are the measured widths and the post-generation fitting code that fixed it.
The Assistant Switch Is One-Way, So the Baseline Has to Be Captured Now
From September 4, Google Assistant is replaced by Gemini, and a device that has switched cannot go back. Here is how I started recording voice-originated launches inside my own apps, and the assumption about splitting before and after by date that turned out to be wrong.
The Strongest Gemini Is in Preview and the Cheap One Is GA. That Ordering Should Drive Your Model Choice
Sort the Gemini lineup by release stage instead of capability and the order inverts: the strongest reasoning model sits in preview while the fast, inexpensive Flash models are GA. Here is how a solo developer handles that, plus a 30-line script that counts how many preview models your code already depends on.
Before Adding New iPhone Widths, I Had Gemini Write Out the Branches I Already Had
Adding three new screen widths to four apps turned into an extraction job, not a rewrite. Here is why I let Gemini pull the branch table out of the source and kept every pass/fail decision in deterministic code.
Finding the questions your help docs never answer, by asking Gemini to write the quiz
When support keeps asking something your help page already covers, generate questions from that page and check whether the page alone can answer them. A two-pass audit pipeline with call design and cost math.
Don't Let the AI Studio Developer Log Be Your Source of Truth: A Two-Layer Way to Observe the Interactions API
The Interactions API developer log in AI Studio is a great triage lens, but it is not a system of record. Here is a two-layer observability design with self-hosted structured logging, reconciliation code, measured sink sizing across 100,000 records, and per-feature cost attribution from an indie operator’s point of view.
Replying to 11 Languages of Google Play Reviews With Gemini Without Sounding Like a Bot
After two major Android updates, I had to clear a backlog of unanswered Google Play reviews in Japanese, English, Traditional Chinese, Korean, Thai, Italian, Russian, Persian, Ukrainian, and Polish. This is the operations design I settled on for using Gemini as a translation and vocabulary partner without losing the human temperature.
Building Automatic Wallpaper Category Classification with Gemini Vision
An indie developer shares how they implemented automatic wallpaper image classification with the Gemini Vision API — including accuracy results, real pitfalls, structured-output tips, and a cost comparison with GPT-4o Vision.
Testing Gemini Vision for Wallpaper Auto-Classification — Real Accuracy Numbers and Pitfalls
A hands-on record of automating wallpaper image classification with Gemini Vision — moving from 67% to 87% accuracy, and using a confidence threshold to cut human review down to 15% of the batch.