docs(get-started): add Brev web UI quickstart guide (#2563)

docs(get-started): add Brev web UI quickstart guide

## Summary
Adds a new getting started guide for running NemoClaw using the Brev 
web UI. The existing deploy-to-remote-gpu guide covers the deprecated 
CLI-based nemoclaw deploy flow. This guide covers the new one-click 
web experience on brev.nvidia.com that requires zero local installation.
Tested end-to-end on April 27, 2026.

## Related Issue
None

## Changes
- Added docs/get-started/brev-web-ui-quickstart.md
- Covers full web UI flow from brev.nvidia.com including agent setup
- Includes troubleshooting section based on real first-run experience
- Documents OpenClaw dashboard sections for first-time users

## Type of Change
- [ ] Code change (feature, bug fix, or refactor)
- [ ] Code change with doc updates
- [x] Doc only (prose changes, no code sample modifications)
- [ ] Doc only (includes code sample changes)

## Verification
- [ ] `npx prek run --all-files` passes
- [ ] `npm test` passes
- [ ] Tests added or updated for new or changed behavior
- [x] No secrets, API keys, or credentials committed
- [x] Docs updated for user-facing behavior changes
- [x] `make docs` builds without warnings (doc changes only)
- [x] Doc pages follow the style guide (doc changes only)
- [x] New doc pages include SPDX header and frontmatter (new pages only)

## AI Disclosure
- [x] AI-assisted - tool: Claude (claude.ai)

---
Signed-off-by: Kunchala Hema Sai Venkat Chandra Kumar
<kumarchanduk@gmail.com>

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Documentation**
* Published a Brev Web UI quickstart for NemoClaw: guides obtaining an
NVIDIA API key, deploying a sandboxed agent via the Brev GPUs banner,
completing the three-stage web UI setup and automated provisioning,
confirming launch and opening the OpenClaw dashboard, walkthrough of
dashboard sections, example first-chat prompts and USER.md template,
cost-control tips, troubleshooting guidance, and suggested next steps.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Kunchala Hema Sai Venkat Chandra Kumar <kumarchanduk@gmail.com>
Co-authored-by: Miyoung Choi <miyoungc@nvidia.com>

Author: hemachandra666

docs/get-started/brev-web-ui-quickstart.md

@@ -0,0 +1,163 @@
+---
+title:
+  page: "Get Started with NemoClaw on Brev (Web UI)"
+  nav: "Brev Web UI"
+description:
+  main: "Run a sandboxed NemoClaw agent in minutes using the Brev web interface with no CLI installation or local setup required."
+  agent: "Guides users through deploying NemoClaw using the Brev web UI. Use when a user wants to try NemoClaw without installing the CLI, or asks how to get started on Brev."
+keywords: ["nemoclaw brev web ui", "nemoclaw getting started", "brev quickstart", "nvidia nemotron agent"]
+topics: ["generative_ai", "ai_agents"]
+tags: ["brev", "openclaw", "getting-started", "web-ui", "nemoclaw"]
+content:
+  type: get_started
+  difficulty: technical_beginner
+  audience: ["developer", "engineer"]
+status: published
+---
+
+<!--
+  SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+# Get Started with NemoClaw on Brev (Web UI)
+
+Run a sandboxed NemoClaw agent in minutes using the Brev web interface.
+No CLI installation, no local setup, and no GPU required on your machine.
+
+:::{note}
+This guide covers the Brev web UI flow, which is the fastest way to try NemoClaw.
+If you prefer the CLI-based remote deployment, see [Deploy to a Remote GPU Instance](../deployment/deploy-to-remote-gpu.md).
+:::
+
+## Prerequisites
+
+- An NVIDIA Brev account at [brev.nvidia.com](https://brev.nvidia.com)
+- An NVIDIA API key from [build.nvidia.com](https://build.nvidia.com)
+
+No local software installation is needed.
+
+## Get Your NVIDIA API Key
+
+1. Go to [build.nvidia.com](https://build.nvidia.com).
+2. Sign in or create a free account.
+3. Click your profile icon in the top right.
+4. Select **API Keys**.
+5. Click **Generate API Key**.
+6. Copy the key -- it starts with `nvapi-`.
+
+Keep this key ready for the next step.
+
+## Deploy NemoClaw on Brev
+
+1. Go to [brev.nvidia.com](https://brev.nvidia.com) and sign in.
+2. On the **GPUs** page, look for the banner: **"Your agents are waiting. Meet NemoClaw"**.
+3. Click **Try NemoClaw**.
+4. The NemoClaw setup page shows the following:
+   - Instance type: CPU (4 CPUs, 16 GiB RAM)
+   - Cloud Provider: GCP
+   - Cost: $0.18/hr
+5. Click **Deploy NemoClaw**.
+
+## Configure Your Agent
+
+NemoClaw walks you through three configuration steps.
+
+### Connect to AI
+
+- **NVIDIA Cloud** is selected by default (recommended).
+- This uses Nemotron-3-Super-120B hosted by NVIDIA.
+- Paste your `nvapi-` API key in the field.
+- Click **Create Agent**.
+
+:::{note}
+Other providers are available: OpenAI, Anthropic, Google Gemini, and Local Ollama.
+Click **Show Other Providers** to see all options.
+:::
+
+### Setup
+
+NemoClaw automatically performs the following:
+
+- Provisions a secure Linux VM on GCP.
+- Installs Docker and the OpenShell runtime.
+- Sets up the sandboxed agent environment.
+- Configures inference routing to NVIDIA Cloud.
+
+This takes approximately 2-3 minutes.
+
+### Launch
+
+When setup completes, the following confirmation appears:
+
+```text
+AGENT CREATED SUCCESSFULLY
+Your agent is running in a secure sandbox and ready to use.
+
+Agent: agent
+Model: nemotron-3-super-120b
+Provider: NVIDIA Cloud
+```
+
+Click **Chat With Agent** to open the OpenClaw gateway dashboard.
+
+## Have Your First Conversation
+
+In the Chat box, type the following:
+
+```text
+Hello! What can you do for me? What skills do you have available?
+```
+
+The agent reads its workspace files and introduces itself.
+By default it has three skills available:
+
+- **Weather** -- Get current weather and forecasts.
+- **Healthcheck** -- Security audit and hardening.
+- **Skill-Creator** -- Create new custom skills.
+
+## Tell the Agent Who You Are
+
+The agent starts with an empty `USER.md` file -- it knows nothing about you.
+Update it so the agent personalizes its responses.
+
+In the chat, type the following:
+
+```text
+Please update my USER.md file with the following:
+Name: [your name]
+Timezone: [your timezone, e.g. EST]
+Notes: [what you are working on]
+```
+
+The agent writes this to your workspace so it remembers you across sessions.
+
+## Stop Your Instance When Done
+
+To avoid unnecessary charges, stop your instance when you are finished experimenting.
+
+1. Go back to [brev.nvidia.com](https://brev.nvidia.com).
+2. Click **GPUs** in the nav bar.
+3. Find your NemoClaw instance.
+4. Click **Stop**.
+
+At $0.18/hr, a 3-hour session costs approximately $0.54.
+
+## What to Try Next
+
+Now that your agent is running, explore these capabilities.
+
+**Connect a messaging channel.**
+Go to **Channels** in the dashboard to connect your agent to Telegram, Slack, or Discord so it can message you proactively.
+
+**Use a different AI model.**
+The agent supports switching inference providers at runtime.
+See [Switch Inference Providers](../inference/switch-inference-providers.md) for instructions.
+
+## Next Steps
+
+- [Prerequisites](prerequisites.md) -- System requirements before getting started.
+- [Quickstart](quickstart.md) -- CLI-based local setup.
+- [Deploy to a Remote GPU Instance](../deployment/deploy-to-remote-gpu.md) -- CLI-based Brev deployment.
+- [Troubleshooting](../reference/troubleshooting.md) -- Common issues and fixes.
+- [Monitor Sandbox Activity](../monitoring/monitor-sandbox-activity.md)

docs/index.md

@@ -344,6 +344,7 @@ Customize the Network Policy <network-policy/customize-network-policy>
 :hidden:
 
 Deploy to a Remote GPU Instance <deployment/deploy-to-remote-gpu>
+Brev Web UI <get-started/brev-web-ui-quickstart>
 Install OpenClaw Plugins <deployment/install-openclaw-plugins>
 Sandbox Hardening <deployment/sandbox-hardening>
 ```