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

# Context and knowledge

> Provide AI with company context for more accurate responses.

**Context and knowledge** is the repository of information you provide to Arya to contextualise its AI responses to your specific business.

## What it can contain

<CardGroup cols={2}>
  <Card title="Company info">Description, mission, market, main products/services.</Card>
  <Card title="Internal terminology">Glossary of industry- or company-specific terms.</Card>
  <Card title="Processes and policies">How you handle leads, customer success, escalations.</Card>
  <Card title="Templates and tone of voice">Email examples, preferred tone, recurring phrases.</Card>
  <Card title="Customer FAQs">Frequent questions + official answers.</Card>
  <Card title="Product documentation">Specs, pricing, key features.</Card>
</CardGroup>

## Why it matters

Without context, Arya responds generically. With rich context:

* Responses use your terminology
* Suggestions aligned with your processes
* Generated emails reflect your tone
* Correct pricing and product info in quotes

## How to feed it

<Tabs>
  <Tab title="Upload documents">
    Upload PDF, DOCX, TXT, Markdown. Arya indexes them (without using for global training). Max 100MB per doc, 50 total docs (1000 on Enterprise).
  </Tab>

  <Tab title="Link resources">
    Link to your site, company Notion, Confluence. Arya re-scans periodically for updates.
  </Tab>

  <Tab title="Inline editor">
    Write directly with markdown editor. Ideal for policies, glossaries, FAQs.
  </Tab>

  <Tab title="Import from workspace">
    Some workspace data (pricing, products) can be flagged as "context" for consistent use.
  </Tab>
</Tabs>

## Context segmentation

Not all context is relevant for every question. Organise by categories:

<AccordionGroup>
  <Accordion title="Commercial">
    Used when AryaChat responds on deals, quotes, pricing, objections.
  </Accordion>

  <Accordion title="Product">
    Used for product technical questions, specs, use cases.
  </Accordion>

  <Accordion title="HR">
    Internal policies, HR processes, benefits, welfare.
  </Accordion>

  <Accordion title="Legal">
    Standard contract clauses, applicable regulations, compliance.
  </Accordion>

  <Accordion title="Financial">
    Admin processes, fiscal deadlines, expense policies.
  </Accordion>
</AccordionGroup>

Arya automatically picks relevant context based on the question.

## Context quality

<Warning>
  More specific and current is better. Avoid:

  * Outdated documents (old pricing, abandoned processes)
  * Contradictory information
  * Corporate manual generality

  Prefer:

  * Concrete examples
  * Real customer dialogues
  * Actually-used templates
</Warning>

## Periodic review

Arya notifies if:

* A document has > 6 months without edits
* There are contradictions between documents
* Glossary terms no longer appear in recent records

## Privacy

<Note>
  Context documents are visible only within your workspace. Not shared with other Arya customers, nor used for global AI model training.
</Note>

## Effective context examples

<AccordionGroup>
  <Accordion title="Sales playbook">
    Document with: ICP, objection handling, pricing flexibility, success examples, industry use cases.
  </Accordion>

  <Accordion title="Customer service scripts">
    Template responses to common questions, escalation policy, tone of voice for difficult situations.
  </Accordion>

  <Accordion title="Product specs">
    Feature matrix, technical limits, public roadmap, supported integrations.
  </Accordion>

  <Accordion title="Company culture">
    Values, communication style, things NOT to say, ethics approach.
  </Accordion>
</AccordionGroup>