> ## Documentation Index
> Fetch the complete documentation index at: https://docs.multivon.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Install pdfhell and run your first adversarial PDF benchmark in 30 seconds.

PDF Hell is an adversarial benchmark for AI document readers. Every test case is a PDF generated *from code*, so the correct answer is exactly known — no LLM judges another LLM.

## Install

```bash theme={null}
pip install pdfhell
```

The bare install pulls `multivon-eval` (the engine), `reportlab` (PDF generation), `pypdf`, and the three frontier-provider SDKs (`anthropic`, `openai`, `google-genai`). No GPU required, no provider extras to remember.

If you use [uv](https://docs.astral.sh/uv/), skip the install — `uvx pdfhell <cmd>` works zero-setup.

## Set an API key

PDF Hell sends each PDF to a vision-capable model. Bring your own key for at least one of:

```bash theme={null}
export ANTHROPIC_API_KEY=sk-ant-...
export OPENAI_API_KEY=sk-proj-...
export GOOGLE_API_KEY=AIza...
```

## Run the smoke suite (3 cases, \~10 seconds)

```bash theme={null}
pdfhell run --model google:gemini-2.5-flash --suite smoke
```

You should see something like:

```
PDF Hell smoke suite — n=3
model: google:gemini-2.5-flash
pass: 3/3  (100.0%)
refused: 0.0%

per-trap pass rate:
  footnote_override               pass=100%  fell-for-trap=0%
  hidden_ocr_mismatch             pass=100%  fell-for-trap=0%
  split_table_across_pages        pass=100%  fell-for-trap=0%
```

The smoke suite is one case per trap family. The full mini suite is 30 cases (10 per family) — same command, `--suite mini`.

## Try a specific trap

Generate one PDF and inspect it visually:

```bash theme={null}
pdfhell make --trap hidden_ocr_mismatch --seed 42
open ./cases/hidden_ocr_mismatch-0042.pdf
```

Open the PDF — you'll see what looks like a normal invoice. The trap is invisible: a second copy of the total amount is written into the PDF's text content stream using PDF render mode 3 (placed in the text stream but never rasterised). A vision model reads the visible amount; a text-extraction pipeline reads the hidden one.

Every case JSON (`cases/<case_id>.json`) carries the expected answer, the forbidden answer (the value the trap was specifically designed to elicit), and a description of the failure mode.

## What's next

* See the **[Trap families](/pdfhell/trap-families)** reference to understand what each trap tests.
* Wire pdfhell into your CI with the **[CI integration](/pdfhell/ci-integration)** guide.
* Full **[CLI reference](/pdfhell/cli-reference)**.
* The **[FAQ](/pdfhell/faq)** covers methodology questions (test leakage, prompt sensitivity, statistical power).