> ## Documentation Index
> Fetch the complete documentation index at: https://012e27a-docs-2.manicule.dev/llms.txt
> Use this file to discover all available pages before exploring further.
> For every page in one file, fetch https://012e27a-docs-2.manicule.dev/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://012e27a-docs-2.manicule.dev/api/mcp.
> Every agent surface: https://012e27a-docs-2.manicule.dev/.well-known/llms-manifest.json

# Data Privacy & Zero Code Training (/security/privacy)

<!-- agent-signals: reading_time_min: 1 · est_tokens: 269 · updated: 2026-11-12 -->
Related: [Security & Privacy](/security/overview.md), [Encrypted Token Vault](/security/token-vault.md), [Execution Isolation & Security](/security/sandboxing.md)

> BhaiCode privacy standards and the zero customer code training policy.

Your source code and proprietary data stay confidential.

## Zero code training

* **No model training**: BhaiCode never uses your source code, prompts, schemas, or repository
  metadata to train or fine-tune foundation models.
* **Enterprise agreements**: upstream provider agreements include zero-data-retention and
  zero-training commitments.
* **Local-first on desktop**: code analysis runs on your machine. Context is sent to an AI
  provider only when you submit an active prompt.

## Data minimisation

<CardGroup cols="3">
<Card title="Task-scoped context" icon="filter">Only the files and context a task needs are included in a prompt.</Card>

<Card title="Secrets excluded" icon="eye-off">Files in `.gitignore` and `.env` are excluded from context.</Card>

<Card title="Ephemeral prompts" icon="trash-2">Prompt context is flushed after the response is generated.</Card>
</CardGroup>

[Contact the team](mailto:hello@bhaico.de) for the latest security summary or to discuss
enterprise terms.