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

# Research and sources

> Ground a slide in live web research, one named page, or your own uploaded documents, then check what comes back.

Pretty has two routes to the web and one to your own material, and it treats each differently.

## The two web routes

<Columns cols={2}>
  <Card title="Researching" icon="globe">
    Live web research across many sources. Returns dense factual prose plus a structured list of
    sources, each with a title, a URL and a last-updated date.

    Use it when you do not know which pages hold the answer: market sizing, competitive
    landscape, trends, recent financials.
  </Card>

  <Card title="Reading page" icon="link">
    One URL that you name. Pretty fetches it, converts it to text, and pulls out the parts
    relevant to your question.

    Use it when the answer is on a page you already have: a pricing page, an agenda, a press
    release, a spec sheet.
  </Card>
</Columns>

You do not pick between them by name. Paste a URL and you get **Reading page**. Ask an open
question about the world and you get **Researching**.

### Asking for research

```text theme={null}
Research the European B2B expense management market. I need current
market size, the three or four largest players with their positioning,
and what has changed in the last eighteen months. Then build two slides:
a market map and a "what changed" timeline.
```

### Asking for one page

```text theme={null}
https://example.com/pricing

Read this and build a slide comparing their three plans against ours -
price, seat limits, and the two or three features that actually
differentiate each tier.
```

<Tip>
  Ask a page a sharp question, not a topic. "The full session-by-session agenda with times and
  speakers" gets you the agenda. "Info about the conference" gets you vague text.
</Tip>

<Note>
  Content a page renders with JavaScript after loading is not visible to the fetch. If a page
  comes back thin or empty, that is usually why. Try a different URL or attach a PDF export.
</Note>

## Sources end up on the slide

When Pretty drafts slide content from web research, it is required to add a small **Sources:**
footer label listing the domains it drew on. Attribution on research-derived slides is a rule it
follows, not a case-by-case decision.

If you do not want the footer on a particular slide, say so, and move the attribution somewhere
you do want it.

```text theme={null}
Drop the Sources footer from slides 3 and 4 and put a single sources
list on a new appendix slide at the end, one line per source with the
full URL.
```

## Grounding in your own documents instead

Often the web is the wrong source and your own material is the right one. Attach it and say so.

Drag files onto the pane (it shows **Drop to reference in chat**) or use **Upload files**.
Several at once is fine, and so is a `.zip`.

```text theme={null}
Attached are the four customer interview transcripts from last month.
Build a three-slide summary: the themes that came up in more than one
interview, the objections we heard, and the direct quotes worth showing.

Only use what is in these transcripts. Do not research anything on the
web, and do not add industry context from your own knowledge.
```

Without that last paragraph, Pretty may reach for the web to fill gaps. Say explicitly when you
want a closed-world answer.

| Attachment          | What Pretty gets                                                 |
| ------------------- | ---------------------------------------------------------------- |
| Text, CSV, Markdown | Numbered lines                                                   |
| DOCX                | Extracted text                                                   |
| PDF                 | The document itself, viewable (text layer only, no OCR on scans) |
| PNG, JPG, GIF, WebP | The image itself, viewable                                       |
| XLSX                | The workbook, readable sheet by sheet                            |

<Warning>
  Typing or pasting a file path does not attach anything. Pretty cannot reach your filesystem.
  The upload is the only route in.
</Warning>

## Asking for citations, and checking them

Pretty will attribute what it drew from research, but it will not footnote every line unless you
ask. When precision matters, ask for it:

```text theme={null}
For every number on this slide, put the source and the date next to it in
small grey type. If you cannot find a dated source for a figure, leave the
figure off rather than estimating it.
```

Then check two things before the deck leaves your hands:

* **Open the sources.** The research result carries real URLs and last-updated dates. A source
  from four years ago behind a claim about "current" market share is a problem the model will not
  flag for you.
* **Match every number to a source.** If a figure has no source next to it and did not come from
  your own attached file, treat it as unverified until you find where it came from.

<Tip>
  Ask Pretty to be explicit about gaps: *"If the research does not support a claim, write
  'not found' on the slide rather than filling it in."* An obvious hole is easier to fix than a
  confident guess.
</Tip>

## Research turns take longer

A **Researching** row runs many searches and reads many pages before it returns anything, so a
turn that includes research is noticeably slower than one that just builds a slide. Nothing is
stuck. If you want to move faster, do the research in one turn, check what came back, then ask for
the slides in the next.