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

# What is ModelHub

> ModelHub is CorePillar's governed AI chat client for employees: one chat box that routes, trims and screens every message before a model sees it.

ModelHub is the AI assistant your company gives to every employee. You open [modelhub.corepillar.ai](https://modelhub.corepillar.ai), type a question, and get an answer from one of the models your administrators have connected. In the app it introduces itself as **CorePillar Assistant**.

It looks like an ordinary chat app. The difference is what happens between pressing **Send** and the model reading your message:

| Step | What happens | Where to read more |
| - | - | - |
| Privacy screening | Personal data and credentials in your message (and any attached documents) are replaced with placeholders such as `[EMAIL_4821]` before anything leaves CorePillar. | [Privacy screening](/modelhub/chat/privacy-screening) |
| Model routing | With the model picker on **Auto**, each message is scored for difficulty and sent to the cheapest connected model that can handle it. | [Models and routing](/modelhub/chat/models-and-routing) |
| Prompt tidying | With **Optimise** switched on, stock politeness and wordy phrases are removed so you pay for fewer tokens. | [Optimise](/modelhub/chat/optimise) |
| Cost and fit reporting | Every answer shows what it cost, how long it took, and whether the model was the right size for the question. | [Chat overview](/modelhub/chat/overview) |

## Who it is for

* **Employees** who need a capable AI assistant without choosing between a dozen models or worrying about pasting the wrong thing.
* **Administrators** who want every AI conversation in the company to run on approved models, on the company's own provider keys, with spend and privacy events visible per person.

ModelHub is a separate deployment of the same platform that powers AgentHub. Employees get the chat; administrators configure models and review usage in [AgentHub](https://pillarforge.corepillar.ai).

## What you can do in ModelHub

* Chat with streaming answers rendered as Markdown, with syntax-highlighted code blocks and copy buttons.
* Let **Auto** pick a model, or choose a specific connected model from the picker.
* Attach up to five text documents (`.txt`, `.md`, `.csv`, `.tsv`, `.json`, `.log`, `.pdf`, `.docx`) per message. They are scanned and masked like your typed text.
* Reopen past conversations from the sidebar.
* See your own spend, token use, model mix and privacy events on the **AI Usage** page.
* Change your profile photo, switch between light and dark mode, and switch organization or project.

## What ModelHub does not do

Being clear about limits saves you time:

* **No model setup.** You cannot add models or API keys in ModelHub. If you see "No models available yet", an administrator has to connect a model in AgentHub's [Model Manager](/agenthub/model-manager).
* **No other platform pages.** Traces, evaluations, the cost calculator and the rest of AgentHub are not reachable from ModelHub. Typing their URLs sends you back to the chat.
* **No conversation rename, delete or search.** The sidebar lists your recent conversations; there are no controls to manage them yet.
* **No regenerate or edit.** To change a question, send a new message.
* **No images or audio.** Attachments are text documents only. Scanned PDFs with no selectable text are rejected.
* **Reopened chats show placeholders.** Personal details are removed before a conversation is saved, so when you reopen it later you see `[PERSON_NAME_0042]` rather than the name. This is by design.
* **Not a general confidentiality filter.** Screening finds identifiers and credentials. It does not recognise confidential business content such as unreleased figures or strategy.

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/modelhub/quickstart">
    Sign in and send your first message.
  </Card>

  <Card title="Signing in" icon="log-in" href="/modelhub/signing-in">
    Email codes, single sign-on, and why your email needs approval.
  </Card>

  <Card title="Using the chat" icon="messages-square" href="/modelhub/chat/overview">
    Every control on the chat screen.
  </Card>

  <Card title="Your usage" icon="chart-line" href="/modelhub/usage">
    What your AI use costs and what was protected.
  </Card>

  <Card title="How routing works" icon="route" href="/modelhub/how-it-works/routing">
    The scoring behind Auto, in full.
  </Card>

  <Card title="Rolling out ModelHub" icon="users" href="/modelhub/admin/rollout">
    Administrator guide to giving employees access.
  </Card>
</CardGroup>


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