Updating base domain in Confidential Inference quick start doc

guides/confidential-inference/confidential-chat.mdx

@@ -0,0 +1,88 @@
+---
+title: "Confidential Chat"
+description: "io.net provides a web-based confidential chat interface where you can interact with AI models securely, with full privacy guarantees and verifiable attestation."
+---
+
+## Getting Started
+
+### Step 1: Select a Secure Model
+
+1. Navigate to [ai.io.net/ai/models](https://ai.io.net/ai/models)
+2. Look for models with the **SECURE AI** badge
+3. Click on a secure model to start a confidential chat session
+
+![Image](/images/image-5.png)
+
+### Step 2: Start Chatting Privately
+
+Once you select a secure model, you enter a private chat session with the following guarantees:
+
+- **Messages are never saved** - your conversation is not stored on any server
+- **No observation** - io.net staff cannot see your prompts or responses
+- **Session-only context** - only the current chat is passed to the LLM for context
+- **End-to-end verification** - every response is cryptographically signed
+
+## Privacy Guarantees
+
+| Feature           | Description                                                       |
+| ----------------- | ----------------------------------------------------------------- |
+| Zero storage      | Messages exist only in your browser and the TEE during processing |
+| No logging        | Conversation content is never written to logs                     |
+| Session isolation | Each chat session is independent and ephemeral                    |
+| Signed responses  | Every AI response includes a cryptographic signature              |
+
+## Verifying Attestation and Signatures
+
+Every message in a confidential chat can be verified. Click the **Secure AI** label under any AI response to open the verification panel.
+
+![Image](/images/image-6.png)
+
+### Attestation Report
+
+The verification panel displays the full attestation report, proving:
+
+- The response came from a genuine NVIDIA GPU running in TEE mode
+- The specific hardware configuration and firmware version
+- The container image hash (`image_digest`) running inside the secure enclave - compare with the expected digest from the [latest official release](https://github.com/ionet-official/attestation-agent/releases) to confirm the container hasn't been tampered with
+
+### Message Signatures
+
+For each AI response, you can view:
+
+| Field               | Description                                           |
+| ------------------- | ----------------------------------------------------- |
+| **Signed Text**     | The exact content that was signed                     |
+| **Signature**       | The cryptographic signature proving authenticity      |
+| **Signing Address** | The public key that signed (matches attestation)      |
+| **Algorithm**       | The signing algorithm used (e.g., ecdsa)              |
+| **Image digest**    | SHA256 hash of the container image running in the TEE |
+
+This allows you to independently verify that:
+
+1. The response was generated by the attested hardware
+2. The content was not modified after generation
+3. The signing key matches the attestation report
+
+## Best Practices
+
+### For Maximum Privacy
+
+- **Start fresh sessions** for sensitive topics
+- **Verify signatures** for critical responses
+- **Check attestation** to confirm hardware authenticity
+- **Clear your browser** after sensitive sessions
+
+### Understanding Session Context
+
+Since messages are not saved:
+
+- The AI only has context from the current session
+- New chat starts a new session with no history
+- You cannot retrieve previous confidential conversations
+
+This is by design - true privacy means no persistent storage.
+
+## What's Next
+
+- [Quick Start API](./guides/confidential-inference/quick-start) - For developers building integrations
+- [Verification Guide](./guides/confidential-inference/verification-guide) - Deep dive into verifying attestation and signatures

guides/confidential-inference/overview.mdx

@@ -0,0 +1,90 @@
+---
+title: "Overview"
+description: "io.net's Confidential Inference enables verifiable AI inference where you can cryptographically prove that your prompts were processed securely on trusted hardware, without storing any of your data."
+---
+
+## Don't Trust, Verify
+
+Traditional AI APIs require you to trust that the provider handles your data securely. With confidential compute, you can **verify** these guarantees cryptographically:
+
+- **Hardware attestation** proves your request ran on genuine, secure GPU hardware
+- **Response signatures** prove the output came from the attested machine
+- **Nonce verification** proves the attestation is fresh, not replayed
+
+## How It Works
+
+1. **Request attestation** with a unique nonce you generate
+2. **io.net routes** your request to a confidential compute-enabled GPU machine
+3. **GPU TEE** generates a hardware attestation report with a signing key
+4. [**Verify**](./guides/confidential-inference/verification-guide) the attestation report proves the machine is genuine and secure
+5. [**Run inference**](./guides/confidential-inference/quick-start) - responses are signed with the attested key
+6. **Verify signatures** to prove responses came from the attested machine
+
+## Key Components
+
+### Trusted Execution Environment (TEE)
+
+The GPU runs inside a Trusted Execution Environment that provides:
+
+- **Memory isolation** - your data is encrypted in memory and inaccessible to the host
+- **Code integrity** - only authorized code can run inside the TEE
+- **Hardware attestation** - the GPU can prove its identity and configuration
+
+### Attestation Agent (Open Source)
+
+The attestation agent running on GPU machines is fully open source. You can audit the code that generates attestation reports and signs responses:
+
+**Repository:** https://github.com/ionet-official/cc-attestation-agent-api
+
+This transparency allows you to:
+
+- Verify what code is running inside the TEE
+- Understand exactly what is being attested
+- Build confidence in the verification process
+
+### Attestation Reports
+
+When you request attestation, you receive:
+
+| Field             | Description                                                          |
+| ----------------- | -------------------------------------------------------------------- |
+| `gpu`             | NVIDIA GPU attestation report proving the GPU identity and TEE state |
+| `cpu`             | CPU attestation report (when available) for additional verification  |
+| `image_digest`    | SHA256 hash of the container image running in the TEE                |
+| `signing_address` | Public key the machine will use to sign inference responses          |
+| `nonce`           | Your nonce echoed back, proving freshness                            |
+
+### Response Signatures
+
+Every inference response includes cryptographic signatures in the response headers:
+
+| Header            | Description                                         |
+| ----------------- | --------------------------------------------------- |
+| `text`            | The content that was signed                         |
+| `signature`       | Cryptographic signature of the text                 |
+| `signing_address` | Public key that signed (matches attestation report) |
+| `signing_algo`    | Algorithm used for signing                          |
+
+## What You Can Prove
+
+| Check                                 | What It Proves                                                           |
+| ------------------------------------- | ------------------------------------------------------------------------ |
+| GPU attestation report is valid       | Response came from genuine NVIDIA GPU in TEE mode                        |
+| `image_digest` matches release        | Running container hasn't been tampered with                              |
+| `signing_address` matches attestation | Responses are signed by the attested machine                             |
+| Signature verifies                    | Response was not tampered with in transit and signed on attested machine |
+| Nonce matches your request            | Attestation is fresh, not replayed                                       |
+
+## Privacy Guarantees
+
+Confidential compute operates in **Zero Data Retention (ZDR) mode**:
+
+- Your prompts and responses are **never stored**
+- Only token counts are recorded for billing
+- No logs of conversation content exist
+
+## What's Next
+
+- [Quick Start API](./guides/confidential-inference/quick-start) - For developers building integrations
+- [Confidential Chat](./guides/confidential-inference/confidential-chat) - Use the web interface for private conversations
+- [Verification Guide](./guides/confidential-inference/verification-guide) - Deep dive into verifying attestation and signatures