diff --git a/README.md b/README.md
index 18e81db9..cd0023cb 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,7 @@
 
 <p align="center">
   <a href="https://www.npmjs.com/package/perstack"><img src="https://img.shields.io/npm/v/perstack" alt="npm version"></a>
+  <a href="https://hub.docker.com/r/perstack/perstack"><img src="https://img.shields.io/docker/v/perstack/perstack?label=docker" alt="Docker image version"></a>
   <a href="https://www.npmjs.com/package/perstack"><img src="https://img.shields.io/npm/dm/perstack" alt="npm downloads"></a>
   <a href="https://github.com/perstack-ai/perstack/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue" alt="License"></a>
 </p>
@@ -14,16 +15,24 @@
 
 Agentic software in production hits two walls. Build from scratch, and most of the code is plumbing — not prompts. Throw a frontier model at a monolithic agent, and it works but doesn't scale commercially.
 
-Perstack takes a third approach: purpose-specific micro-agents on value-tier models. Narrow tasks don't need Opus-level reasoning. Haiku is enough. And single-purpose prompts are easy to write.
+Perstack takes a third approach: purpose-specific micro-agents on value-tier models, running in sandboxed containers. Narrow tasks don't need Opus-level reasoning. Haiku is enough. And single-purpose prompts are easy to write.
 
-`create-expert` generates agent definitions in a `perstack.toml` file. `perstack` executes them on an event-sourced runtime.
+Every agent runs inside its own Docker container with an isolated filesystem and network. The host system is never exposed. This makes Perstack safe to run in production — agents can execute shell commands and write files without risk to the host.
+
+`create-expert` generates agent definitions in a `perstack.toml` file. `perstack` executes them on an event-sourced runtime inside a sandboxed container.
 
 ```bash
 npx create-expert "Form a team named ai-gaming to build a Bun-based CLI indie game playable on Bash for AI."
-npx perstack start ai-gaming --model "haiku-4-5" "Make a Wizardry-like dungeon crawler."
+
+docker run --rm -e ANTHROPIC_API_KEY \
+  -v ./perstack.toml:/workspace/perstack.toml:ro \
+  -v ./workspace:/workspace/output \
+  perstack/perstack start ai-gaming --model "haiku-4-5" "Make a Wizardry-like dungeon crawler."
 ```
 
-A game built with these commands: [demo-dungeon-crawler](https://github.com/perstack-ai/demo-dungeon-crawler). Play it via `npx perstack-demo-dungeon-crawler start`. Built entirely on Claude 4.5 Haiku.
+The official [`perstack/perstack`](https://hub.docker.com/r/perstack/perstack) image ships pre-compiled standalone binaries — no Node.js or npm needed. File writes, shell commands, and all agent activity are confined to the container.
+
+A game built with these commands: [demo-dungeon-crawler](https://github.com/perstack-ai/demo-dungeon-crawler). Built entirely on Claude 4.5 Haiku.
 
 ## How it works
 
@@ -48,7 +57,37 @@ description = "Tests the game and reports bugs"
 instruction = "Play-test the game, find bugs, and verify fixes."
 ```
 
-`perstack start` executes the agents and streams activity in real time. `perstack run` does the same headless with JSON output, for integration into your own applications.
+Run with Docker — the config is mounted read-only, and output stays inside the container:
+
+```bash
+docker run --rm -e ANTHROPIC_API_KEY \
+  -v ./perstack.toml:/workspace/perstack.toml:ro \
+  -v ./output:/workspace/output \
+  perstack/perstack run ai-gaming "Make a Wizardry-like dungeon crawler."
+```
+
+`perstack start` streams activity in real time. `perstack run` does the same headless with JSON output, for integration into your own applications.
+
+## Sandboxed by default
+
+Agents have access to shell execution, file I/O, and MCP tools. Running them directly on the host is a security risk. Docker containers solve this:
+
+- **Filesystem isolation** — agents read and write inside the container. Mount only what you need with `-v`.
+- **Network control** — restrict outbound access with `--network=none` or custom Docker networks.
+- **Resource limits** — cap CPU and memory with `--cpus` and `--memory`.
+- **Disposable environments** — `--rm` ensures nothing persists after execution.
+
+```bash
+# Maximum isolation: no network, resource-limited, read-only config
+docker run --rm \
+  --network=none \
+  --cpus=1 --memory=2g \
+  -e ANTHROPIC_API_KEY \
+  -v ./perstack.toml:/workspace/perstack.toml:ro \
+  perstack/perstack run my-expert "Analyze this codebase."
+```
+
+For production deployments, see [Isolation by Design](https://perstack.ai/docs/operating-experts/isolation-by-design/).
 
 ## Runtime
 
@@ -73,14 +112,24 @@ Custom MCP servers can be added per agent in `perstack.toml`.
 ## Deployment
 
 ```dockerfile
-FROM node:22-slim
-WORKDIR /app
-COPY perstack.toml perstack.lock .
-RUN npm install -g perstack && perstack install
-ENTRYPOINT ["perstack", "run", "--config", "/app/perstack.toml", "ai-gaming"]
+FROM perstack/perstack:latest
+COPY perstack.toml .
+RUN perstack install
+ENTRYPOINT ["perstack", "run", "my-expert"]
+```
+
+```bash
+docker build -t my-expert .
+docker run --rm -e ANTHROPIC_API_KEY my-expert "query"
+```
+
+The image is multi-arch (`linux/amd64`, `linux/arm64`) and weighs ~74MB. Pin to a specific version for reproducible builds:
+
+```dockerfile
+FROM perstack/perstack:0.0.94
 ```
 
-The runtime can also be imported directly as a TypeScript library, so it works in Cloudflare Workers, Vercel, or any Node.js environment:
+The runtime can also be imported directly as a TypeScript library for serverless environments (Cloudflare Workers, Vercel, etc.):
 
 ```typescript
 import { run } from "@perstack/runtime"
@@ -89,7 +138,7 @@ const checkpoint = await run({
   setting: {
     model: "claude-sonnet-4-5",
     providerConfig: { providerName: "anthropic", apiKey: env.ANTHROPIC_API_KEY },
-    expertKey: "ai-gaming",
+    expertKey: "my-expert",
     input: { text: query },
   },
 })