diff --git a/src/content/docs/agents/capabilities/slash-commands.mdx b/src/content/docs/agents/capabilities/slash-commands.mdx
index d20521f9..328d7d3b 100644
--- a/src/content/docs/agents/capabilities/slash-commands.mdx
+++ b/src/content/docs/agents/capabilities/slash-commands.mdx
@@ -18,7 +18,7 @@ As you type, the menu filters results in real time, making it easy to find and r
 
 Warp currently supports the following built-in Slash Commands:
 
-<table><thead><tr><th width="211.64453125">Slash Command</th><th>Description</th></tr></thead><tbody><tr><td><code>/add-mcp</code></td><td>Add a new <a href="/agents/capabilities/mcp/">MCP server</a>.</td></tr><tr><td><code>/add-prompt</code></td><td>Add a new <a href="/knowledge-and-collaboration/warp-drive/prompts/">Agent Prompt</a> in Warp Drive.</td></tr><tr><td><code>/add-rule</code></td><td>Add a new <a href="/agents/capabilities/rules/">Global Rule</a> for the Agent.</td></tr><tr><td><code>/agent</code></td><td>Start a new <a href="/agents/local-agents/interacting-with-agents/">agent conversation</a>. Optionally include a prompt to send immediately.</td></tr><tr><td><code>/changelog</code></td><td>Open the latest Warp <a href="/changelog/">changelog</a>.</td></tr><tr><td><code>/cloud-agent</code></td><td>Start a new <a href="/platform/">cloud agent conversation</a>. <code>{'*'}</code></td></tr><tr><td><code>/compact</code></td><td>Free up context by summarizing conversation history.</td></tr><tr><td><code>/compact-and</code></td><td>Compact the current conversation and then send a follow-up prompt.</td></tr><tr><td><code>/conversations</code></td><td>Open <a href="/agents/local-agents/interacting-with-agents/">conversation history</a>.</td></tr><tr><td><code>/cost</code></td><td>Toggle credit usage details in the current conversation.</td></tr><tr><td><code>/create-environment</code></td><td>Create a <a href="/platform/environments/">Warp Environment</a> (Docker image + repos) via guided setup. <code>{'*'}</code></td></tr><tr><td><code>/create-new-project</code></td><td>Have the Agent walk you through creating a new coding project. <code>{'*'}</code></td></tr><tr><td><code>/environment</code></td><td>Switch the <a href="/platform/environments/">environment</a> for the current cloud agent conversation.</td></tr><tr><td><code>/export-to-clipboard</code></td><td>Export the current conversation to clipboard in markdown format.</td></tr><tr><td><code>/export-to-file</code></td><td>Export the current conversation to a markdown file.</td></tr><tr><td><code>/feedback</code></td><td>Open the static feedback experience. See <a href="/support-and-community/troubleshooting-and-support/sending-us-feedback/#using-feedback-in-warp">Using <code>/feedback</code> in Warp</a> for details.</td></tr><tr><td><code>/fork</code></td><td><a href="/agents/local-agents/interacting-with-agents/conversation-forking/">Forks the current conversation</a> into a new thread with the full context and history of the original. <br /><br />You can optionally include a prompt that will be sent immediately in the forked conversation.</td></tr><tr><td><code>/fork-and-compact</code></td><td><a href="/agents/local-agents/interacting-with-agents/conversation-forking/">Forks the current conversation</a> and automatically compacts the forked version.<br /><br />Useful when you want a fresh, summarized starting point that preserves relevant context while trimming the rest.</td></tr><tr><td><code>/fork-from</code></td><td>Open a searchable menu to <a href="/agents/local-agents/interacting-with-agents/conversation-forking/">fork the conversation</a> from a specific query. Select a query to create a fork that includes everything up to that point.</td></tr><tr><td><code>/harness</code></td><td>Switch the <a href="/platform/harnesses/">harness</a> for the current cloud agent conversation.</td></tr><tr><td><code>/host</code></td><td>Switch the execution host for the current cloud agent conversation.</td></tr><tr><td><code>/index</code></td><td>Index the current codebase using <a href="/agents/capabilities/codebase-context/">Codebase Context</a>.</td></tr><tr><td><code>/init</code></td><td>Index the current codebase and generate an <a href="/agents/capabilities/rules/">AGENTS.md file</a>. <code>{'*'}</code></td></tr><tr><td><code>/model</code></td><td>Switch the base agent model for the current conversation.</td></tr><tr><td><code>/new</code></td><td>Start a new <a href="/agents/local-agents/interacting-with-agents/">agent conversation</a> (alias for <code>/agent</code>).</td></tr><tr><td><code>/open-code-review</code></td><td>Open the <a href="/code/code-review/">code review</a> pane.</td></tr><tr><td><code>/open-file</code></td><td>Open a file for editing in Warp's <a href="/code/code-editor/">code editor</a>.</td></tr><tr><td><code>/open-mcp-servers</code></td><td>View the status of your <a href="/agents/capabilities/mcp/">MCP servers</a>.</td></tr><tr><td><code>/open-project-rules</code></td><td>Open the <a href="/agents/capabilities/rules/#project-rules">Project Rules</a> file (<code>AGENTS</code>).</td></tr><tr><td><code>/open-repo</code></td><td>Switch to another indexed repository.</td></tr><tr><td><code>/open-rules</code></td><td>View all of your global and project <a href="/agents/capabilities/rules/">rules</a>.</td></tr><tr><td><code>/open-settings-file</code></td><td>Open the Warp <a href="/terminal/settings/">settings file</a> (<code>settings.toml</code>) in Warp's code editor.</td></tr><tr><td><code>/open-skill</code></td><td>Open an interactive menu to browse and edit project or global <a href="/agents/capabilities/skills/">skills</a>.</td></tr><tr><td><code>/orchestrate</code></td><td>Break a task into subtasks and run them in parallel with multiple agents. <code>{'*'}</code></td></tr><tr><td><code>/plan</code></td><td>Prompt the Agent to do some research and create a <a href="/agents/capabilities/planning/">plan</a> for a task.</td></tr><tr><td><code>/profile</code></td><td>Switch the active <a href="/agents/capabilities/agent-profiles-permissions/">execution profile</a>.</td></tr><tr><td><code>/prompts</code></td><td>Search saved <a href="/knowledge-and-collaboration/warp-drive/prompts/">prompts</a>.</td></tr><tr><td><code>/queue</code></td><td>Queue a prompt to send after the agent finishes responding. See <a href="/agents/local-agents/interacting-with-agents/prompt-queueing/">Prompt Queueing</a>.</td></tr><tr><td><code>/rename-conversation</code></td><td>Rename the current conversation.</td></tr><tr><td><code>/rename-tab</code></td><td>Rename the current tab. Include the new tab name as an argument (for example, <code>/rename-tab deploy</code>).</td></tr><tr><td><code>/rewind</code></td><td>Rewind to a previous point in the conversation.</td></tr><tr><td><code>/skills</code></td><td>Invoke a <a href="/agents/capabilities/skills/">skill</a> from a searchable menu.</td></tr><tr><td><code>/usage</code></td><td>Open <a href="/support-and-community/plans-and-billing/">billing and usage</a> settings.</td></tr></tbody></table>
+<table><thead><tr><th width="211.64453125">Slash Command</th><th>Description</th></tr></thead><tbody><tr><td><code>/add-mcp</code></td><td>Add a new <a href="/agents/capabilities/mcp/">MCP server</a>.</td></tr><tr><td><code>/add-prompt</code></td><td>Add a new <a href="/knowledge-and-collaboration/warp-drive/prompts/">Agent Prompt</a> in Warp Drive.</td></tr><tr><td><code>/add-rule</code></td><td>Add a new <a href="/agents/capabilities/rules/">Global Rule</a> for the Agent.</td></tr><tr><td><code>/agent</code></td><td>Start a new <a href="/agents/local-agents/interacting-with-agents/">agent conversation</a>. Optionally include a prompt to send immediately.</td></tr><tr><td><code>/changelog</code></td><td>Open the latest Warp <a href="/changelog/">changelog</a>.</td></tr><tr><td><code>/cloud-agent</code></td><td>Start a new <a href="/platform/">cloud agent conversation</a>. <code>{'*'}</code></td></tr><tr><td><code>/compact</code></td><td>Free up context by summarizing conversation history.</td></tr><tr><td><code>/compact-and</code></td><td>Compact the current conversation and then send a follow-up prompt.</td></tr><tr><td><code>/conversations</code></td><td>Open <a href="/agents/local-agents/interacting-with-agents/">conversation history</a>.</td></tr><tr><td><code>/cost</code></td><td>Toggle credit usage details in the current conversation.</td></tr><tr><td><code>/create-environment</code></td><td>Create a <a href="/platform/environments/">Warp Environment</a> (Docker image + repos) via guided setup. <code>{'*'}</code></td></tr><tr><td><code>/create-new-project</code></td><td>Have the Agent walk you through creating a new coding project. <code>{'*'}</code></td></tr><tr><td><code>/environment</code></td><td>Switch the <a href="/platform/environments/">environment</a> for the current cloud agent conversation.</td></tr><tr><td><code>/export-to-clipboard</code></td><td>Export the current conversation to clipboard in markdown format.</td></tr><tr><td><code>/export-to-file</code></td><td>Export the current conversation to a markdown file.</td></tr><tr><td><code>/feedback</code></td><td>Open the static feedback experience. See <a href="/support-and-community/troubleshooting-and-support/sending-us-feedback/#using-feedback-in-warp">Using <code>/feedback</code> in Warp</a> for details.</td></tr><tr><td><code>/fork</code></td><td><a href="/agents/local-agents/interacting-with-agents/conversation-forking/">Forks the current conversation</a> into a new thread with the full context and history of the original. <br /><br />You can optionally include a prompt that will be sent immediately in the forked conversation.</td></tr><tr><td><code>/fork-and-compact</code></td><td><a href="/agents/local-agents/interacting-with-agents/conversation-forking/">Forks the current conversation</a> and automatically compacts the forked version.<br /><br />Useful when you want a fresh, summarized starting point that preserves relevant context while trimming the rest.</td></tr><tr><td><code>/fork-from</code></td><td>Open a searchable menu to <a href="/agents/local-agents/interacting-with-agents/conversation-forking/">fork the conversation</a> from a specific query. Select a query to create a fork that includes everything up to that point.</td></tr><tr><td><code>/harness</code></td><td>Switch the <a href="/platform/harnesses/">harness</a> for the current cloud agent conversation.</td></tr><tr><td><code>/host</code></td><td>Switch the execution host for the current cloud agent conversation.</td></tr><tr><td><code>/index</code></td><td>Index the current codebase using <a href="/agents/capabilities/codebase-context/">Codebase Context</a>.</td></tr><tr><td><code>/init</code></td><td>Index the current codebase and generate an <a href="/agents/capabilities/rules/">AGENTS.md file</a>. <code>{'*'}</code></td></tr><tr><td><code>/model</code></td><td>Switch the base agent model for the current conversation.</td></tr><tr><td><code>/new</code></td><td>Start a new <a href="/agents/local-agents/interacting-with-agents/">agent conversation</a> (alias for <code>/agent</code>).</td></tr><tr><td><code>/open-code-review</code></td><td>Open the <a href="/code/code-review/">code review</a> pane.</td></tr><tr><td><code>/open-file</code></td><td>Open a file for editing in Warp's <a href="/code/code-editor/">code editor</a>.</td></tr><tr><td><code>/open-mcp-servers</code></td><td>View the status of your <a href="/agents/capabilities/mcp/">MCP servers</a>.</td></tr><tr><td><code>/open-project-rules</code></td><td>Open the <a href="/agents/capabilities/rules/#project-rules">Project Rules</a> file (<code>AGENTS</code>).</td></tr><tr><td><code>/open-repo</code></td><td>Switch to another indexed repository.</td></tr><tr><td><code>/open-rules</code></td><td>View all of your global and project <a href="/agents/capabilities/rules/">rules</a>.</td></tr><tr><td><code>/open-settings-file</code></td><td>Open the Warp <a href="/terminal/settings/">settings file</a> (<code>settings.toml</code>) in Warp's code editor.</td></tr><tr><td><code>/open-skill</code></td><td>Open an interactive menu to browse and edit project or global <a href="/agents/capabilities/skills/">skills</a>.</td></tr><tr><td><code>/orchestrate</code></td><td>Break a task into subtasks and run them in parallel with multiple agents. See <a href="/platform/orchestration/">Multi-agent orchestration</a>. <code>{'*'}</code></td></tr><tr><td><code>/plan</code></td><td>Prompt the Agent to do some research and create a <a href="/agents/capabilities/planning/">plan</a> for a task.</td></tr><tr><td><code>/profile</code></td><td>Switch the active <a href="/agents/capabilities/agent-profiles-permissions/">execution profile</a>.</td></tr><tr><td><code>/prompts</code></td><td>Search saved <a href="/knowledge-and-collaboration/warp-drive/prompts/">prompts</a>.</td></tr><tr><td><code>/queue</code></td><td>Queue a prompt to send after the agent finishes responding. See <a href="/agents/local-agents/interacting-with-agents/prompt-queueing/">Prompt Queueing</a>.</td></tr><tr><td><code>/rename-conversation</code></td><td>Rename the current conversation.</td></tr><tr><td><code>/rename-tab</code></td><td>Rename the current tab. Include the new tab name as an argument (for example, <code>/rename-tab deploy</code>).</td></tr><tr><td><code>/rewind</code></td><td>Rewind to a previous point in the conversation.</td></tr><tr><td><code>/skills</code></td><td>Invoke a <a href="/agents/capabilities/skills/">skill</a> from a searchable menu.</td></tr><tr><td><code>/usage</code></td><td>Open <a href="/support-and-community/plans-and-billing/">billing and usage</a> settings.</td></tr></tbody></table>
 
 :::caution
 Slash commands marked with a `*` consume credits to complete the task.
diff --git a/src/content/docs/platform/agents.mdx b/src/content/docs/platform/agents.mdx
index b438cdee..9e0bedde 100644
--- a/src/content/docs/platform/agents.mdx
+++ b/src/content/docs/platform/agents.mdx
@@ -65,6 +65,7 @@ When a team is over its plan limit (for example, after downgrading), the extra a
 
 * [Triggers](/platform/triggers/) - How schedules, integrations, and API calls invoke cloud agents.
 * [Environments](/platform/environments/) - The runtime context (Docker image, repos, setup commands) a cloud agent uses.
+* [Multi-agent orchestration](/platform/orchestration/) - Coordinate a parent cloud agent and its children across local and cloud runs.
 * [API keys](/reference/cli/api-keys/) - Create personal and agent API keys.
 * [Oz API & SDK](/reference/api-and-sdk/) - Programmatic access to the cloud agent endpoints.
 * [Federated identity tokens](/reference/cli/federate/) - Issue OIDC tokens from inside a run.
diff --git a/src/content/docs/platform/faqs.mdx b/src/content/docs/platform/faqs.mdx
index 2231ad84..5eeacb8d 100644
--- a/src/content/docs/platform/faqs.mdx
+++ b/src/content/docs/platform/faqs.mdx
@@ -118,7 +118,7 @@ To learn more about how secrets work in practice, see [Cloud Agent Secrets](/pla
 
 The cloud agents platform is intentionally flexible. As the developer, you decide how agents should branch, coordinate, and resolve conflicts.
 
-Interactive agents can plan work and spawn subagents to parallelize tasks. Cloud agents provide the building blocks for running and coordinating multiple concurrent agents, rather than enforcing a fixed workflow.
+Interactive agents can plan work and spawn subagents to parallelize tasks. Cloud agents provide the building blocks for [running and coordinating multiple concurrent agents](/platform/orchestration/), rather than enforcing a fixed workflow.
 
 ### Why focus on orchestration primitives instead of immediately adopting new agent standards?
 
diff --git a/src/content/docs/platform/quickstart.mdx b/src/content/docs/platform/quickstart.mdx
index a293b458..6a264a51 100644
--- a/src/content/docs/platform/quickstart.mdx
+++ b/src/content/docs/platform/quickstart.mdx
@@ -16,7 +16,7 @@ This guide walks you through running your first cloud agent with an environment
 
 **Common use cases for cloud agents:**
 
-* Launch parallel cloud coding agents to multithread complex development tasks
+* Launch [parallel cloud coding agents](/platform/orchestration/) to multithread complex development tasks
 * Automate repetitive development tasks (e.g., feature-flag cleanup, documentation updates, fixing server crashes)
 * Build apps on top of agents, like bug triage and incident response systems
 
@@ -111,6 +111,7 @@ Now that you've run your first cloud agent, try these next steps:
 
 * [**Schedule recurring work**](/platform/triggers/scheduled-agents-quickstart/) - Create a scheduled agent for maintenance tasks like dependency checks, cleanup, or triage.
 * [**Trigger agents from Slack or Linear**](/platform/integrations/quickstart/) - Connect Oz to team tools so mentions and issue updates can launch cloud agent runs.
+* [**Orchestrate multiple agents**](/platform/orchestration/multi-agent-runs/) - Fan work out across parent and child agents for large refactors, PR review swarms, and parallel package migrations.
 * [**Turn successful prompts into reusable skills**](/platform/skills-as-agents/) - Save repeatable agent workflows and run them again from the CLI, web app, API, or a schedule.
 * [**Build programmatic automations**](/reference/api-and-sdk/quickstart/) - Start cloud agent runs from your own systems with the Oz API or SDKs.
 
diff --git a/src/content/docs/platform/software-factory.mdx b/src/content/docs/platform/software-factory.mdx
index 7f1a0fc6..596244c3 100644
--- a/src/content/docs/platform/software-factory.mdx
+++ b/src/content/docs/platform/software-factory.mdx
@@ -44,7 +44,7 @@ The inner loop runs when a new issue is filed:
 3. A human reviews and approves the specs.
 4. When the implementation label is applied, the implementation agent opens a PR that includes the spec files alongside the code.
 
-Oz orchestrates each agent as a cloud run. Every run has its own environment (repository checkout, secrets, toolchain), its own permissions, and a session link your team can use to inspect what the agent did, steer it mid-run, or hand work back to a local session.
+Oz orchestrates each agent as a cloud run. Every run has its own environment (repository checkout, secrets, toolchain), its own permissions, and a session link your team can use to inspect what the agent did, steer it mid-run, or hand work back to a local session. For parent/child fan-out and review swarms across those roles, see [Multi-agent orchestration](/platform/orchestration/).
 
 The outer loop runs on a schedule, not in response to events.
 
@@ -71,6 +71,7 @@ Start with one agent role. Most teams start with a triage agent, which is the si
 * [Set up your software factory](/guides/agent-workflows/set-up-a-software-factory) — Connect the four roles into a working loop.
 * [Run a software factory in the cloud](/guides/agent-workflows/run-a-software-factory-in-the-cloud) — Move the loop off your laptop with Oz.
 * [Build a self-improving agent](/guides/agent-workflows/build-a-self-improving-agent) — Add the outer improvement loop.
+* [Multi-agent orchestration](/platform/orchestration/) — Coordinate specialized agent roles as parent and child runs.
 * [Skills](/agents/capabilities/skills) — How skill files work in Warp and Oz.
 * [Cloud agents overview](/platform) — Setting up cloud agents on Oz.
 * [Deployment patterns](/platform/deployment-patterns) — Common architectures for cloud agent deployment.