SignsofAI

# ✍︎ Signs of AI Writing

[![Live demo](https://img.shields.io/badge/demo-live-brightgreen?logo=googlechrome&logoColor=white)](https://peopleworks.github.io/SignsofAI/)
[![License: MIT](https://img.shields.io/github/license/peopleworks/SignsofAI?color=blue)](LICENSE)
[![.NET 10](https://img.shields.io/badge/.NET-10-512BD4?logo=dotnet&logoColor=white)](https://dotnet.microsoft.com/)
[![Blazor WebAssembly](https://img.shields.io/badge/Blazor-WASM-512BD4?logo=blazor&logoColor=white)](https://learn.microsoft.com/aspnet/core/blazor/)
[![GitHub stars](https://img.shields.io/github/stars/peopleworks/SignsofAI?style=social)](https://github.com/peopleworks/SignsofAI/stargazers)

[![NuGet Core](https://img.shields.io/nuget/v/SignsOfAI.Core?logo=nuget&label=Core)](https://www.nuget.org/packages/SignsOfAI.Core)
[![NuGet CLI](https://img.shields.io/nuget/v/SignsOfAI.Cli?logo=nuget&label=CLI)](https://www.nuget.org/packages/SignsOfAI.Cli)
[![NuGet MCP](https://img.shields.io/nuget/v/SignsOfAI.Mcp?logo=nuget&label=MCP%20server)](https://www.nuget.org/packages/SignsOfAI.Mcp)

**[Try the live demo →](https://peopleworks.github.io/SignsofAI/)** — English & Spanish, runs 100% in your browser. No signup, and nothing leaves your device.

![Signs of AI Writing analyzing text live: the score climbs as AI tells accumulate, then every tell is highlighted with a fix](Docs/screenshots/analyze-live.gif)

<sub>Real recording of the live demo — the score updates as you type, and every highlight comes with a suggested fix.</sub>

A free, privacy-first toolkit for **academic and writing integrity**. It does two things:

1. **De-AI-ify linter** — flags the tells of AI-generated writing (overused vocabulary, rhetorical
   crutches, robotic sentence rhythm) and, for **every** finding, tells you *how to fix it*.
2. **Originality checker** — *"did they write it, or copy it?"* Compares documents against each other
   and surfaces the passages they share — verbatim copies, **reworded paraphrases** (even across
   languages), and a whole-cohort overview — as **evidence a human judges**. Not a black-box verdict.

> 🔒 **Almost everything runs 100% in your browser. Your documents never leave your device.**
> The only exception is the optional paraphrase check, which is strictly opt-in and clearly disclosed.

Built with **.NET 10** and **Blazor WebAssembly** by **Pedro Hernández (PeopleWorks)**, Microsoft MVP
for .NET — for the .NET and Microsoft developer community, *por y para la comunidad educativa*.

Repo: https://github.com/peopleworks/SignsofAI

Both **English** and **Spanish** are supported throughout (auto-detected or selectable). The Spanish
rule-pack is an original derivation of AI-writing markers for Spanish.

---

## 1. The AI-writing linter ("Analyze")

Unlike black-box detectors that only spit out a score, this is an **explainable, actionable, educational**
linter. Paste, upload (`.docx` / `.txt` / `.md`), or **just start typing** — the 0–100 score, highlights,
statistics, and per-finding fixes update **as you write**.

| Category       | Examples |
|----------------|----------|
| **Lexical**     | *delve, tapestry, multifaceted, nuanced, pivotal, underscore, showcase, testament…* (weighted by post-ChatGPT excess frequency) |
| **Rhetorical**  | Negative parallelisms (*"it's not just X, it's Y"*), cliché openers (*"in today's digital age"*), hedging (*"it's worth noting that"*), false ranges, rule-of-three |
| **Syntactic**   | Copula avoidance (*"serves as a…"*, *"a testament to…"*), inflated constructions (*"plays a crucial role"*) |
| **Statistical** | **Burstiness** — sentence-length uniformity. Machine text hovers at 0.0–0.2; human prose 0.6–0.8 |

- **Sentence-rhythm visualization** — a per-sentence bar chart that makes *burstiness* visible.
- **Per-finding recommendations** — every flagged tell carries a concrete fix and the research behind it.
- **Humanize (optional, BYOK)** — connect an AI provider and rewrite the flagged text in one click.
  Anthropic (`claude-opus-4-8`, works from the browser), OpenAI / DeepSeek, Azure OpenAI, or **Ollama**
  (local, no key). Credentials live only in your browser and are sent **directly** to the provider.
- **Before/after diff** and a **shareable result card** (a PNG summary that never includes your text).
- **Custom catalogs (BYO rules)** — paste banned words or import a rule-pack JSON; merges live.
- **Catalog page** — a searchable library of every AI-writing sign, in both languages, ranked with an
  in-browser BM25 index.

![The annotated text with every AI tell highlighted, beside the recommendation list explaining and fixing each one](Docs/screenshots/evidence.png)

<sub>This is the difference: not "87% AI", but *which* words, *why* they were flagged, and *what to write instead*.</sub>

## 2. The Originality checker ("Originality")

*"¿Lo escribió la IA, lo copiaste, o lo parafraseaste para esconderlo?"* Drop in two or more documents —
a thesis and its sources, a batch of student submissions — and see exactly what they share. The guiding
principle is honest: **we surface the evidence and highlight it; a human judges. We never accuse.** This is
**not** a whole-internet index like Turnitin.

| Phase | What it catches | How | Where it runs |
|-------|-----------------|-----|---------------|
| **A — Literal copy** | verbatim shared passages, resistant to changed capitalization/accents | accent/case-folded word *k*-shingles + greedy longest-match tiling, verified token-by-token | 🔒 **in your browser** |
| **B — Paraphrase** | *reworded* copies — same idea, different words — **even across languages** | sentence embeddings (Google **EmbeddingGemma-300M**, ONNX) + cosine similarity | 🌐 optional server (**opt-in**) |
| **C — Cohort** | who copied whom across a whole class, at a glance | batch upload + an N×N **overlap heatmap**; click a cell to inspect the pair | 🔒 **in your browser** |
| **D — Web spot-check** | whether a passage already exists online | extracts a document's most **distinctive passages** and hands you one-click exact-phrase searches (Google/Bing/DuckDuckGo) | 🔒 **in your browser** |

- **Shared-passage evidence** — matches are highlighted in both documents, side by side; the headline
  overlap number equals exactly what you see highlighted (the evidence *is* the score).
- **Phase B is the one feature that leaves the device.** It's opt-in, disclosed in the UI, and sends only
  the sentences you choose to check to the PeopleWorks server. Everything else stays on your machine.
- **Phase D** is deliberately honest: we can't index the whole web, so instead of pretending to, we surface
  the passages worth checking and prepare the searches — nothing is sent anywhere until *you* click one.
  An **optional automatic web search** can be enabled by the server operator (see *Optional server* below).

![Cohort overlap matrix showing which documents share text, with the most similar pairs ranked below](Docs/screenshots/originality.png)

<sub>A whole class at a glance: every document against every other, then the shared passages themselves — evidence, not an accusation.</sub>

## 3. The predictability meter (optional server)

An honest reframing of perplexity. A small language model (Qwen2.5-0.5B or Microsoft Phi-4-mini, int8 ONNX)
measures how *predictable / generic* a text's phrasing is. **This is not an AI-vs-human verdict** — on a
labelled corpus the two overlap badly (memorized human text scores *predictable* too). We surface
predictability honestly as one signal among many, calibrated per language. Opt-in; runs on the PeopleWorks
server. The model lazily loads and idle-unloads to keep the server light.

## 4. Use it from other apps — MCP server

Everything above is also available to **Claude Desktop and any [MCP](https://modelcontextprotocol.io)
client** through `SignsOfAI.Mcp`, a Model Context Protocol server (built on the official
[`ModelContextProtocol`](https://www.nuget.org/packages/ModelContextProtocol) SDK, stdio transport). Because
the engine lives in `SignsOfAI.Core` — pure .NET, no browser — the server just exposes it as tools:

| Tool | What it does | Where it runs |
|------|--------------|---------------|
| `analyze_ai_writing` | score + verdict + findings (with fixes) + statistics | 🔒 on-device |
| `check_originality` | overlap % and shared passages across 2+ documents | 🔒 on-device |
| `search_catalog` | search the catalog of AI-writing signs (EN/ES) | 🔒 on-device |
| `extract_distinctive_phrases` | distinctive phrases + ready-made web-search links | 🔒 on-device |
| `measure_predictability` | perplexity via the optional server | 🌐 server (**opt-in**) |
| `check_paraphrase` | reworded/translated matches via EmbeddingGemma | 🌐 server (**opt-in**) |

The first four run entirely on the machine; the last two disclose that they send text to the server
(endpoint via the `SIGNSOFAI_API_ENDPOINT` environment variable).

It ships on NuGet as [`SignsOfAI.Mcp`](https://www.nuget.org/packages/SignsOfAI.Mcp), so nothing needs
building. Point Claude Desktop at it:

```jsonc
// %APPDATA%\Claude\claude_desktop_config.json
{ "mcpServers": { "signs-of-ai": {
  "command": "dnx",
  "args": ["SignsOfAI.Mcp", "--yes"]
}}}
```

Or install it as a global tool once — `dotnet tool install --global SignsOfAI.Mcp` — and use
`"command": "signsofai-mcp"`. See `src/SignsOfAI.Mcp/README.md` for details.

**VS Code**: the package ships an MCP manifest, so its
[NuGet page](https://www.nuget.org/packages/SignsOfAI.Mcp) has an **MCP Server** tab with the config
already generated — copy it into `.vscode/mcp.json` and you're done.

## 5. Use it as an agent skill — `/signs-of-ai`

Prefer to work inside your editor? `skill/signs-of-ai` is a drop-in **Claude Code / Codex / agent skill**
that de-slops a draft — or judges whether text reads as AI-written — in **English and Spanish**. It's a
human-readable distillation of the same `rules.en.json` / `rules.es.json` taxonomy, so it edits by the
same rules