diff --git a/docs/_config.yml b/docs/_config.yml
new file mode 100644
index 0000000..c43cc2e
--- /dev/null
+++ b/docs/_config.yml
@@ -0,0 +1,5 @@
+title: SentinelGuard
+description: Security-first LLM gateway and guardrails framework for AI applications
+theme: jekyll-theme-primer
+plugins:
+ - jekyll-seo-tag
diff --git a/docs/index.md b/docs/index.md
index 0920377..34b79b0 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,129 +1,178 @@
-# SentinelGuard
-
-
-
-
-
Security-first LLM gateway and guardrails framework
-
-## Put one protected gateway in front of your AI traffic
-
-SentinelGuard helps teams secure LLM applications, AI IDEs, agents, and model
-provider traffic with prompt scanning, output scanning, PII and secret
-protection, model routing, failover, usage controls, audit events, and a stable
-management API.
-
-
-[Start in 5 minutes](getting-started.md){ .sg-button .sg-button-primary }
-[Run the gateway](gateway.md){ .sg-button .sg-button-secondary }
-[View on GitHub](https://github.com/aitechnav/Sentinel_Guard){ .sg-button .sg-button-secondary target="_blank" }
-
-
-
-OpenAI-compatible gateway
-PII and secret controls
-Prometheus metrics
-Docker and Kubernetes ready
-
-
-
-
-
-
Install and start the gateway
-
-```bash
-pip install "sentinelguard[gateway,monitoring]"
+---
+title: SentinelGuard
+description: Security-first LLM gateway and guardrails framework for AI applications
+---
+
+
+
+
+
+
+
Security-first LLM gateway and guardrails framework
+
Put one protected gateway in front of your AI traffic
+
+ SentinelGuard helps teams secure LLM applications, AI IDEs, agents, and
+ model provider traffic with prompt scanning, output scanning, PII and
+ secret protection, model routing, failover, usage controls, audit
+ events, and a stable management API.
+
-### Secure the LLM boundary
-Scan prompts before they reach a model and scan responses before they return to
-users. Block attacks, redact PII, and stop secrets from leaving the application.
-
-
-
-### Route across providers
-Use friendly model names, route traffic across OpenAI-compatible providers,
-fail over when one provider is unavailable, and keep private routes available
-for sensitive traffic.
-
-
-
-### Operate with evidence
-Use virtual keys, usage accounting, provider health, privacy-safe audit events,
-Prometheus metrics, and the stable `/gateway/v1` API for dashboards and alerts.
-
-
-
-## Built For Modern AI Applications
-
-
-
-
-### Package mode
-
-Use SentinelGuard directly in Python code when you want guardrails inside one
-application.
-
-```python
-from sentinelguard import SentinelGuard
+ --port 8080
+
Point apps and IDEs to http://localhost:8080/v1
+
+
+
+
+
+ 36
+ security scanners
+
+
+ v1
+ stable gateway API
+
+
+ 2 modes
+ library and proxy
+
+
+ local
+ model-backed detection
+
+
+
+
+
+
Why teams use SentinelGuard
+
Runtime protection for the LLM boundary
+
+
+
+
Secure prompts and responses
+
+ Scan prompts before they reach a model and scan responses before they
+ return to users. Block attacks, redact PII, and stop secrets from
+ leaving the application.
+
+
+
+
Route across providers
+
+ Use friendly model names, route traffic across OpenAI-compatible
+ providers, fail over when one provider is unavailable, and keep
+ private routes available for sensitive traffic.
+
+
+
+
Operate with evidence
+
+ Use virtual keys, usage accounting, provider health, privacy-safe
+ audit events, Prometheus metrics, and the stable
+ /gateway/v1 API for dashboards and alerts.
+
+
+
+
+
+
+
+
Built for modern AI applications
+
Use it in code or as a shared gateway
+
+
+
+
Package mode
+
Use SentinelGuard directly in Python code when you want guardrails inside one application.
+
from sentinelguard import SentinelGuard
guard = SentinelGuard()
result = guard.scan_prompt("Ignore previous instructions")
-print(result.is_valid, result.failed_scanners)
-```
-
+print(result.is_valid, result.failed_scanners)
+
+
+
Gateway mode
+
Run SentinelGuard as a proxy so multiple applications, users, and AI tools share one security boundary.
-
-### Gateway mode
-
-Run SentinelGuard as a proxy so multiple applications, users, and AI tools can
-share the same security boundary.
-
-```text
-App or IDE -> SentinelGuard /v1 -> LLM provider
-```
-
-Stable management API:
-
-```text
-/gateway/v1/contract
-/gateway/v1/health
-/gateway/v1/routes
-```
-
-