The Size Column Said 'F6' and 'About A4' — I Let Gemini Read It, and Let a Table Do the Math
An artist's spreadsheet mixed 'F6', '41×31.8cm', and 'about A4' in one size column. Here is the small tool I built: Gemini reads each cell, a lookup table converts to centimeters, and the artwork image decides the orientation. Working code, step by step.
I Stopped Asking Gemini 'Is This Right?' and Started Hiding My Answer Instead
Ask Gemini to confirm a label you already chose and it tends to agree. Here is why I compared three ways of asking, chose blind re-classification, how my answer still leaked in, and the routing code that sends only disagreements to a human.
Matching name variants in a print catalog: normalize first, then ask Gemini for candidates
When the same artist appears under three spellings, asking Gemini whether two names are the same person quietly merges different generations. Here is the two-layer alternative — deterministic normalization first, model-generated candidates second — with working code and a cost estimate.
Your Spreadsheet Breaks Before Gemini Ever Sees It
Merged cells and two-row headers quietly strip rows of their keys during extraction, long before the model reads anything. Here is what gets lost, measured, plus the Python that flattens the table and catches the total row.
Gemini quietly drops %1$s from translations, and no reviewer catches it
Format specifiers go missing, turn full-width, or get duplicated when Gemini translates app strings. Here are the four failure modes I keep seeing in production, how to stop them at generation time, and a short check that catches the rest.
A minimal pre-send guard for Gemini-drafted app review replies
Store replies are risky after you hit send, not before. Here is a short Python guard that blocks unkeepable promises, leaked contact details, and register slips, plus the two false positives it produced on the first run.
The Day I Stopped Tracking gemini-flash-latest: Batch Design That Survives Silent Model Swaps
A silent model swap pushed my batch rejection rate from 2.1% to 9.8% overnight. The pinning-plus-canary design I moved to, with the harness and numbers.
Building an App Store Rejection Workflow with the Gemini API — From Structured Notices to Resolution Center Replies
How I use the Gemini API to parse App Store rejection notices into structured JSON, cross-check guidelines, draft Resolution Center replies, and run pre-submission checks as an indie developer.
When responseSchema enum returns unexpected values — debugging Gemini API
Why Gemini API sometimes returns values outside the enum you defined in responseSchema, and the three-layer workaround I use in production for my wallpaper app classification pipeline.
Build a CSV Insight App with Gemini API and Streamlit — A Production-Ready Dashboard with Auto-Insights and Visualization
A production-grade implementation guide for a Streamlit + Gemini API data analysis app. Upload a CSV, get auto-insights and visualizations in seconds. Covers schema inference, structured output, and real-world rate-limit handling.
Defending Gemini API Responses with Schema Validation — Never Let Unexpected Formats Reach Production
Gemini's structured output is convenient, but in production the day always comes when an unexpected format slips through. This piece walks through layered Zod/Pydantic validation, repair prompts, and graceful degradation — the defense lines I run on my own apps.
A near-miss label won't fix itself on retry — a normalization layer for closed-vocabulary classification
When responseSchema enum returns an out-of-set label, retrying tends to return the same near-miss. From a wallpaper app's 30-category batch, here is the distribution of how labels miss, plus a normalization layer built on an alias table and gemini-embedding-2 nearest-neighbor, with measured results.