> ## 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.

# Chats & Tickets

> Email threads, Slack channels and support tickets.

Email threads, Slack channels and support tickets. Four recipes, one per ScaleDown model.

## Compress

<Card title="Shrink a long thread down to what matters before an LLM drafts a reply or runs an action." icon="compress" href="https://scaledown.ai/cookbooks/messages-compress">
  Sits in front of your LLM. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Long email and Slack threads carry a lot of greetings, sign-offs, and quoted history; most of it is dead weight on the next call. |
| **How it goes** | Thread in → Compress strips the boilerplate, keeps the ask → the LLM works on the trimmed context. |
| **Payoff** | Fewer tokens into the drafting or answering call. |

## Summarize

<Card title="Catch me up on this thread in one or two lines." icon="align-left" href="https://scaledown.ai/cookbooks/messages-summarize">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | People do not want to read a long thread top to bottom; they want the state of it. |
| **How it goes** | Thread in → Summarize produces the digest → surface it in the inbox, channel, or handoff. |
| **Payoff** | Thread digests without a frontier call each time. |

## Extract

<Card title="Pull the action items, dates, and owners out of a message or thread." icon="magnifying-glass" href="https://scaledown.ai/cookbooks/messages-extract">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | The asks are buried in prose; Extract turns them into fields a system can act on. |
| **How it goes** | Message in → tell Extract what to look for → it returns tasks, dates, owners → push to the tracker. |
| **Payoff** | Structured to-dos straight from the thread. |

## Classify

<Card title="Sort and route each message by topic, priority, or sentiment." icon="tags" href="https://scaledown.ai/cookbooks/messages-classify">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Triage runs on every support message; volume makes per-message frontier cost add up fast. |
| **How it goes** | Message in → Classify assigns the label → route to the right queue, owner, or alert. |
| **Payoff** | Cheap, fast labeling at inbox volume. |


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