> ## Documentation Index
> Fetch the complete documentation index at: https://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://docs-2.manicule.dev/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://docs-2.manicule.dev/api/mcp.
> Every agent surface: https://docs-2.manicule.dev/.well-known/llms-manifest.json

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

<!-- agent-signals: reading_time_min: 1 · est_tokens: 222 · updated: 2026-11-11 -->
Related: [Encrypted Token Vault](/security/token-vault.md), [Execution Isolation & Security](/security/sandboxing.md), [Database Migrations & ORM Setup](/databases/migrations.md)

> BhaiCode privacy standards and zero customer code training policy.

Your source code and proprietary data remain strictly confidential.

***

## Zero Code Training Policy

* **No Model Training**: BhaiCode never uses your source code, prompts, schemas, or repository metadata to train or fine-tune public foundation models.
* **Enterprise Agreements**: Upstream LLM provider agreements include zero-data-retention and zero-training commitments.
* **Local-First in Desktop**: In BhaiCode Desktop, code analysis runs locally on your machine. Context is dispatched to AI providers only when you submit an active prompt.

***

## Data Minimization

* Only files and context required for the specific task are sent in the prompt payload.
* Files listed in `.gitignore` and `.env` are automatically excluded from context.
* Ephemeral prompt contexts are flushed after response generation.