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

# Web Pages

> Scraped pages and enriched records for GTM and signal products.

Scraped pages and enriched records for GTM and signal products. Four recipes, one per ScaleDown model.

## Compress

<Card title="Strip HTML boilerplate and repetition out of a scraped page before any downstream call." icon="compress" href="https://scaledown.ai/cookbooks/web-compress">
  Sits in front of your LLM. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Raw web content is mostly navigation, markup, and restatement across sources: high redundancy, high Compress leverage. |
| **How it goes** | Scraped page in → Compress strips boilerplate → the downstream model works on the signal. |
| **Payoff** | Large token reduction on noisy pages before the expensive step. |

## Summarize

<Card title="Turn an enriched record or scraped page into a short, human-readable summary." icon="align-left" href="https://scaledown.ai/cookbooks/web-summarize">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | The output a user reads should be a tight profile, not a wall of scraped text. |
| **How it goes** | Page or record in → Summarize produces the profile → surface it in the product. |
| **Payoff** | Readable summaries at crawl volume. |

## Extract

<Card title="Pull structured facts off a page: company, role, signal, contact details." icon="magnifying-glass" href="https://scaledown.ai/cookbooks/web-extract">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Enrichment is continuous extraction over raw web content; this is the core loop for GTM and signal products. |
| **How it goes** | Page in → tell Extract the fields → it returns structured facts → into the record. |
| **Payoff** | Structured enrichment off unstructured pages. |

## Classify

<Card title="Relevance-score and tag scraped records, so only the useful ones move on." icon="tags" href="https://scaledown.ai/cookbooks/web-classify">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Most scraped records are junk; you want a cheap, fast filter before spending on extraction. |
| **How it goes** | Record in → Classify scores relevance and assigns tags → route or drop. |
| **Payoff** | Fast filtering keeps junk out of the expensive pipeline. |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.