diff --git a/README.md b/README.md
index 88e811b..c5e2bc0 100644
--- a/README.md
+++ b/README.md
@@ -1,8 +1,10 @@
 # Running agents on proc-0 (for friends)
 
 You get gVisor-sandboxed coding agents running on Alex's server. Each task
-clones a git repo into a sandbox and runs an agent there (pi or Claude Code),
-using a local Qwen 3.8 27B model. No API keys needed.
+clones a git repo into a sandbox and runs a coding agent there, backed by a
+Qwen 3.8 27B model that Alex hosts. No API keys or accounts needed. The
+recommended agent is [pi](https://pi.dev); see [Using pi with
+Qwen](#5-using-pi-with-qwen). Claude Code is available too.
 
 ## 1. Join
 
@@ -64,9 +66,9 @@ metadata:
   name: sam-hello
   atespace: default
 spec:
-  # pi:          code.proc.io/ax/ax-task-runner:pi-vllm-1
+  # pi:          code.proc.io/ax/ax-task-runner:pi-vllm-3
   # Claude Code: code.proc.io/ax/ax-task-runner:claude-vllm-3
-  image: code.proc.io/ax/ax-task-runner:pi-vllm-1
+  image: code.proc.io/ax/ax-task-runner:pi-vllm-3
   workspaces:
     - name: sam-myrepo
       path: /workspace
@@ -79,7 +81,6 @@ ax resume task sam-hello         # starts it; the first start can take a minute,
                                  # so re-run if it times out
 ax ssh sam-hello -- ls /workspace  # the repo is cloned into /workspace/<repo-name>
 ax ssh sam-hello -- sh -c 'cd /workspace/your-repo && pi -p "explain the build system"'
-#   (Claude Code image: claude -p "...")
 ax suspend task sam-hello        # frees the worker; files and state are kept
 ax resume task sam-hello         # picks up where it left off
 ax delete task sam-hello         # when done
@@ -92,6 +93,85 @@ workspace.
 
 Tasks are immutable: to change one, delete it and apply again.
 
+## 5. Using pi with Qwen
+
+### The model
+
+- **Qwen 3.8 27B** (`qwen3.8-27b`), served by vLLM on proc-0's GPU. It supports
+  tool calling and reasoning ("thinking").
+- 128K-token context (131,072). Large repos still need the agent to read
+  selectively, which it does by default.
+- Shared: the server runs at most 8 requests at a time across everyone,
+  including Alex's other work, so responses slow down when it's busy.
+- From inside a sandbox it's also a plain OpenAI-compatible API at
+  `http://vllm.vllm.svc:8000/v1`, if you want to script against it directly.
+  It isn't reachable from your own machine.
+
+### pi is preconfigured
+
+The pi image (`ax-task-runner:pi-vllm-3`) points pi at that model, so there's
+nothing to log in to or set up. pi runs in the task's working directory with
+four tools: `read`, `bash`, `edit` and `write`. It can run builds and tests and
+change files in the repo.
+
+Since `ax ssh` isn't interactive, always use print mode (`-p`). Wrap commands
+in `sh -c '…'` so `cd` and pipes run inside the sandbox:
+
+```bash
+T=sam-hello R=/workspace/your-repo
+
+# one-shot question or task
+ax ssh $T -- sh -c "cd $R && pi -p 'find where config is loaded and explain it'"
+
+# keep going in the same conversation (survives suspend/resume)
+ax ssh $T -- sh -c "cd $R && pi -p -c 'now add a test for the env-var override'"
+
+# feed it input
+ax ssh $T -- sh -c "cd $R && git diff | pi -p 'review this change'"
+
+# read-only: no edits, no shell
+ax ssh $T -- sh -c "cd $R && pi -p --tools read,grep,find,ls 'audit error handling'"
+
+# a fresh conversation that isn't saved
+ax ssh $T -- sh -c "cd $R && pi -p --no-session 'list the TODOs'"
+
+# see what it changed
+ax ssh $T -- sh -c "cd $R && git status && git diff"
+```
+
+### Thinking level
+
+Qwen thinks before answering. More thinking is slower but better on hard
+problems. pi defaults to `medium`. Change it per call with `--thinking`:
+
+| `--thinking` | Use for |
+|---|---|
+| `off` | quick lookups, renames, boilerplate |
+| `low` | simple edits |
+| `medium` (default) | most work |
+| `high` | tricky bugs, design questions (Qwen's maximum; slowest) |
+
+`minimal` and `xhigh` aren't supported by this model, and pi rounds them to the
+nearest supported level.
+
+### Tips
+
+- Put project instructions in an `AGENTS.md` at your repo root. pi reads it
+  automatically (build commands, conventions, what not to touch).
+- The workspace is yours for the task's lifetime: run `npm install`, builds and
+  tests freely. Package downloads work from npm, PyPI and GitHub.
+- To get work out, have pi produce a patch (`git diff > /workspace/out.patch`)
+  and `ax ssh $T -- cat /workspace/out.patch > out.patch` it to your machine.
+  Pushing from the sandbox would need credentials, and nothing there is private.
+- Long runs are tied to your `ax ssh` connection. Break big jobs into steps
+  and use `pi -p -c` to continue between them.
+
+### Claude Code instead
+
+Set the image to `code.proc.io/ax/ax-task-runner:claude-vllm-3` and use
+`claude -p "…"` (also against Qwen). In our tests, pi was faster on the same
+model. Claude Code's `--continue` history doesn't survive a suspend; pi's does.
+
 ## Ground rules and limits
 
 - **Two tasks can run at once, server-wide.** Suspend yours when you're not
diff --git a/task.yaml b/task.yaml
index 95ce497..6bb5d43 100644
--- a/task.yaml
+++ b/task.yaml
@@ -17,9 +17,9 @@ metadata:
   name: sam-hello
   atespace: default
 spec:
-  # pi:          code.proc.io/ax/ax-task-runner:pi-vllm-1
+  # pi:          code.proc.io/ax/ax-task-runner:pi-vllm-3
   # Claude Code: code.proc.io/ax/ax-task-runner:claude-vllm-3
-  image: code.proc.io/ax/ax-task-runner:pi-vllm-1
+  image: code.proc.io/ax/ax-task-runner:pi-vllm-3
   workspaces:
     - name: sam-myrepo
       path: /workspace