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

# LLM Enrichment

> Use --ai flag to have LLM fill document placeholders. Safe, proxied, and optional.

## How it works

```bash theme={null}
complior fix --ai
```

When `--ai` is used, the document generation pipeline adds an extra step: LLM fills `[TO BE COMPLETED]` and `<!-- GUIDANCE -->` markers using passport data as context.

| Without `--ai`                         | With `--ai`                              |
| -------------------------------------- | ---------------------------------------- |
| Documents scaffolded with placeholders | LLM fills placeholders (90–95% complete) |
| Compliance flags already set           | Same flags, richer content               |
| 25–80% pre-filled from passport        | 90–95% filled                            |
| Instant                                | +10–30 seconds per document              |

## Safety

<Check>
  The LLM call is wrapped through `@complior/sdk` proxy with `prohibited`, `sanitize`, and `rate-limit` hooks active. The LLM cannot bypass compliance checks.
</Check>

**LLM does NOT modify passport JSON.** It only enriches document markdown files. Compliance flags (`fria_completed`, `policy_generated`) are set identically with or without `--ai`.

## Fallback

If LLM call fails (network error, rate limit, invalid key), the fixer returns the document from the scaffold stage — with placeholders but all compliance flags intact. No data loss, no silent failure.

## BYOK configuration

Configure your LLM provider in `.complior/config.toml`:

```toml theme={null}
[llm]
provider = "openai"          # openai, anthropic, openrouter, ollama
model = "gpt-4o"
api_key_env = "OPENAI_API_KEY"  # reads from environment variable
```