ScribeLens

Gemini and AI writing detector for everyday drafts

ScribeLens checks text for AI writing patterns, including work drafted with Gemini inside everyday tools like Gmail and Google Docs. It marks the specific sentences that carry those patterns and names the reason for each one.

Where Gemini shows up in everyday writing

Gemini is often not something people sit down to open in its own tab the way they might open a dedicated chat window. It shows up embedded inside tools people already write in — a Gmail draft, a suggestion inside Google Docs, a quick answer pulled up on a phone — which means a lot of Gemini-assisted writing gets accepted and turned in without the writer ever thinking of it as “using AI.”

That embedded, casual path changes what a submission actually looks like. Someone who accepts a few suggestions inside a longer essay or email isn't turning in a document generated end-to-end by an assistant — they're turning in their own draft with AI-assisted passages mixed in, which is exactly the kind of partial, uneven case a single score handles badly and sentence-level evidence handles well.

The same check works wherever Gemini was used

ScribeLens reads the writing itself: sentence rhythm, word choice, and structure. A passage shows the same patterns whether it came from a Gemini chat window or from a one-line suggestion accepted inside Docs.

That matters here, because so much Gemini use happens inside other tools. The result shows which passages carry AI-like patterns and why. It does not name the product behind them.

Reading a result on assisted, everyday writing

Writing that blends a person's own sentences with a few accepted AI suggestions produces a different pattern than a document drafted end-to-end by an assistant: flags concentrated in specific sentences or paragraphs, rather than spread evenly across the whole piece. That's a more informative signal on this kind of writing than a bare score, and it's exactly what sentence-level evidence is built to show.

Educators reading a Docs-drafted assignment, teams reviewing Workspace-assisted internal writing, and anyone who accepted a few suggestions and wants to see how their own draft reads before sending or submitting it are all looking at the same kind of case: a blend, not a binary. A single number collapses that blend into one figure; reason keywords attached to each flagged sentence do not.

Frequently asked questions

If I used “Help me write” in Google Docs, will that show AI patterns?

Often, yes. A passage drafted with “Help me write” and accepted as it stands tends to carry the writing patterns ScribeLens looks for: even sentence rhythm, predictable word choice, formulaic structure. Check your draft before you submit it, see which sentences are flagged and why, and follow your course's rules on AI assistance.

Can a detector tell Gemini apart from other AI tools?

No. Gemini and other assistants write with similar patterns at the sentence level, so a result tells you whether a passage shows AI-like patterns, not which product produced it.

Does Google Docs version history help if my writing gets flagged?

Yes, as process evidence. Version history shows how a document was built up over time — drafts, edits, revisions — which is a useful companion to a ScribeLens report, not a replacement for it. The report shows what the current text looks like at the sentence level; version history shows how it got there. Bringing both to a conversation is stronger than either alone.

Will detection keep up as Gemini updates?

Yes. ScribeLens looks for patterns that assistants share, and the detector is retrained as writing tools change. Every report names the detector version that scored it; the live one, Detector v4.0, was retrained in October 2026.

I only used Gemini for a quick homework answer, not the whole assignment — will that still get flagged?

Possibly, and that's exactly the case sentence-level evidence is built for. If AI-assisted passages sit inside an otherwise human-written document, flags should concentrate around those specific sentences rather than appear evenly across the whole piece. Read the sentence-level view first, not just the overall verdict, to see where a signal is actually coming from.

Is it worth checking a short Gmail draft or reply?

Short passages give pattern analysis less to work with than a full essay or report, so treat a result on a very brief reply as a lighter signal. For anything you're planning to submit or send in a context where it matters, checking the longer draft or document it's part of produces a more reliable read.

Check Docs, Gmail, and other Gemini-assisted writing

Paste a draft — including passages drafted with Gemini inside Gmail or Google Docs — and see the sentence-level evidence behind the result. Without an account a scan covers 2,000 words; a free account scans the whole document.