docs: simplify navigation and tutorial catalog

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

Author: drew

README.md

@@ -196,7 +196,7 @@ Docker-backed GPU sandboxes auto-select CDI when available and otherwise fall ba
 OpenShell can run an agent that works in a Linux container. Build a versioned
 image with the agent and its dependencies, publish it where the gateway can
 pull it, then attach the providers and policy that the workflow requires. See
-[Run an Agent](https://docs.nvidia.com/openshell/latest/about/run-an-agent) for
+[Run Your First Agent](https://docs.nvidia.com/openshell/latest/about/run-an-agent) for
 the complete workflow.
 
 ## Key Commands

docs/about/installation.mdx

@@ -192,7 +192,7 @@ for preflight details and manual schema-v1 migration steps.
 
 ## Next Steps
 
-- To launch an agent, refer to [Run an Agent](/about/run-an-agent).
+- To launch an agent, refer to [Run Your First Agent](/about/run-an-agent).
 - To create your first sandbox, refer to the [Quickstart](/get-started/quickstart).
 - To run the gateway as a container without the installer, refer to [Running the Gateway as a Container](/reference/container-gateway).
 - To register, select, and inspect gateways, refer to [Gateways](/sandboxes/manage-gateways).

docs/about/run-an-agent.mdx

@@ -1,8 +1,8 @@
 ---
 # SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
-title: "Run an Agent"
-sidebar-title: "Run an Agent"
+title: "Run Your First Agent"
+sidebar-title: "Run Your First Agent"
 description: "Prepare a sandbox image, provider profile, and policy for an AI agent or another autonomous workload."
 keywords: "Generative AI, Cybersecurity, AI Agents, Sandboxing, Provider Profiles, Policies, Custom Images"
 position: 4

docs/get-started/quickstart.mdx

@@ -56,7 +56,7 @@ For a remote gateway, push the image to a registry the gateway can access:
 docker push registry.example.com/team/claude-code:1.0
 ```
 
-Refer to [Run an Agent](/about/run-an-agent) for image requirements and the
+Refer to [Run Your First Agent](/about/run-an-agent) for image requirements and the
 bring-your-own-agent workflow.
 
 ## Import a Provider Profile
@@ -109,7 +109,7 @@ process.
 ## Next Steps
 
 - To build images for other agents and tools, refer to
-  [Run an Agent](/about/run-an-agent).
+  [Run Your First Agent](/about/run-an-agent).
 - To manage sandbox resources, files, templates, and connectivity, refer to
   [Sandboxes](/sandboxes/manage-sandboxes).
 - To review or change allowed access, refer to

docs/get-started/tutorials/docker-compose.mdx

@@ -27,19 +27,4 @@ Launch Claude Code in a sandbox, diagnose a policy denial, and iterate on a cust
 Configure a Microsoft Graph provider profile with gateway-managed OAuth2 refresh-token rotation.
 </Card>
 
-<Card title="Inference with Ollama" href="/get-started/tutorials/inference-ollama">
-
-Connect a user-owned sandbox workload to an Ollama service on the gateway host.
-</Card>
-
-<Card title="Local Inference with LM Studio" href="/get-started/tutorials/local-inference-lmstudio">
-
-Attach an endpoint-bearing profile and call a local LM Studio server directly.
-</Card>
-
-<Card title="Docker Compose Setup" href="/get-started/tutorials/docker-compose">
-
-Run the OpenShell gateway as a Docker Compose service and create agent sandboxes including OpenClaw.
-</Card>
-
 </Cards>