All Articles
After exporting a Gemini answer to Docs, check who can open it before you hit Share
Google's help page for "Export to Docs" covers creating the document, not its sharing state. Here are the three places to look right after exporting, what happens when you move the file into a shared folder, and an Apps Script audit for when exports pile up.
Fine on Desktop, Blank on Safari: Four Things to Gather Before You Ask an AI to Diagnose It
After a shuffle, my lazy-loaded images never loaded again, but only in Safari on iPhone. Here is what to collect by hand before asking Gemini or any other model to diagnose a bug that does not reproduce on desktop, plus a request template you can paste.
Keeping Money and Health Questions Out of Your History: Gemini Temporary Chat and the Settings to Check
Before you ask Gemini about household spending or a health worry, here is the order I use to check Temporary Chat and the Activity setting, so you can decide what gets kept and what doesn't.
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.
Some inputs ignore media_resolution entirely. Count the tokens on your own key first
In Gemini 3, media_resolution behaves differently per input type. Here is why audio never moves, where the official docs disagree with each other, and how to recount input tokens on your own API key.
The color label Gemini returned for the same wallpaper changed — and the model was not the reason
I counted color-label agreement across five ways of exporting the same wallpaper. Stripping the ICC profile was the worst of them. Here is how I pin the color space down before asking, and how I check the answers against a number I compute myself.
When BLOCK_NONE Changes Nothing: Telling Adjustable Gemini Blocks from the Ones You Can't Move
Some safety blocks go away when you loosen a threshold. Others never will. Here is how to read the response and decide which kind you are looking at before you touch a single setting.
Two Kinds of Video Questions: Why I Send "Find It" and "Prove It Isn't There" Down Separate Paths
Agentic video understanding lets the model decide which parts of a video to watch. That works beautifully for finding things, and it quietly breaks when you need to prove something never appears. Here is how I split my questions, and the coverage check I now run first.
Define What Counts as a Duplicate Before Adding Embedding Search to Your Image Pipeline
My dedup check flagged two prints with identical composition but different colors as one image. Here is how I split duplicate detection into three layers, measured where perceptual hashing ends, and decided what embedding search is actually for.
Rebuilding the CTR Denominator After AI Search Fans Out Your Queries
My top five queries by impressions all had zero clicks, and four of them were not phrases a person would type. Here is how I rebuilt the denominator and where I let Gemini make the call.
A Provenance Gate That Never Asks Gemini to Name the Country
How I rebuilt the pre-publish provenance check for a ukiyo-e wallpaper app, moving from asking the model to name a country to asking it only to list the marks physically present on the paper. Includes the working code, the decision table that lives on my side, and why an abstain path had to come before accuracy.
The Memory Wasn't Lost — It Was Written to a Different Profile
A Memory Bank profile is identified by the pair of schema and scope. When call sites build that scope slightly differently, extra profiles appear with no error at all. Here are the measured numbers for how badly it fragments, and how three candidate fixes actually performed.