diff --git a/docs/architecture/HARDWARE_INVENTORY.md b/docs/architecture/HARDWARE_INVENTORY.md
index d377dea..448dc19 100644
--- a/docs/architecture/HARDWARE_INVENTORY.md
+++ b/docs/architecture/HARDWARE_INVENTORY.md
@@ -3,7 +3,7 @@
 ## Serenity (NAS / Media Ingestion)
 - **OS:** Unraid 7.2.4
 - **IP:** 10.5.1.5 | Tailscale: 100.94.87.79
-- **CPU:** Xeon X5690
+- **CPU:** Dual Xeon X5690 (6c/12t each — 24 threads total)
 - **RAM:** 102GB
 - **GPU:** None (Matrox IPMI only)
 - **UPS:** None
diff --git a/docs/planning/TODO.md b/docs/planning/TODO.md
index aa19c60..8dbabcc 100644
--- a/docs/planning/TODO.md
+++ b/docs/planning/TODO.md
@@ -9,7 +9,7 @@
 - [ ] Set up off-site backup for vital data (appdata, databases, config repo, photos)
 - [ ] Remove dead Unraid-Cloudflared-Tunnel container from Serenity
 - [ ] Serenity malcolm pool capacity planning (heavily utilized)
-- [ ] Add Pangolin resource for `ai.paccoco.com` → openwebui (port 8282)
+- [ ] Add Pangolin resource for `ai.paccoco.com` → OpenWebUI (port 8282)
 - [ ] Add Cloudflare DNS A record for `ai.paccoco.com`
 - [ ] Install fresh editor on PD
 - [ ] Set up private Gitea repo for .env file backups
@@ -18,17 +18,8 @@
 - [ ] Pull `qwen2.5:14b` on PD ollama: `sudo docker exec -it ollama ollama pull qwen2.5:14b`
 - [ ] Create OpenWebUI account and set system prompt from HOMELAB_AI_CONTEXT.md
 - [ ] Disable signups in OpenWebUI after creating account
-- [ ] Connect desktop Ollama to OpenWebUI (Admin → Settings → Connections)
-- [ ] Set `OLLAMA_HOST=0.0.0.0` on desktop and restart Ollama service
-
-## Planned Deployments (PD)
-- [ ] dispatcharr
-- [ ] gotify
-- [ ] bytestash
-- [ ] kima-hub
-- [ ] n8n
-- [ ] qdrant
-- [ ] paperless-ngx
+- [ ] Connect Rocinante Ollama to OpenWebUI (Admin → Settings → Connections)
+- [ ] Confirm `OLLAMA_HOST=0.0.0.0` set on Rocinante and Ollama service restarted
 
 ## Healthchecks
 - [ ] Add healthcheck to ix-plex-plex-1
@@ -39,5 +30,16 @@
 
 ## Documentation
 - [ ] Document meshtastic stack fully (see docs/reference/MESHTASTIC.md)
-- [ ] Fill in port/URL columns in SERVICES_DIRECTORY.md
 - [ ] Document N.O.M.A.D. containers (start_nomad.sh services)
+
+## Completed
+- [x] Deploy Gotify (Phase 1) — 2026-05-05
+- [x] Deploy AI stack — LiteLLM, OpenWebUI, Qdrant, Whisper, SearXNG (Phase 2) — 2026-05-05
+- [x] Deploy n8n (Phase 3) — 2026-05-05
+- [x] Deploy Paperless-NGX (Phase 4) — 2026-05-05
+- [x] Deploy Home Assistant + Kima Hub (Phase 5) — 2026-05-06
+- [x] Deploy Grafana + Prometheus (Phase 6) — 2026-05-06
+- [x] Move reranker from PD (8787) to Serenity (9787) — 2026-05-09
+- [x] Fill in port/URL columns in SERVICES_DIRECTORY.md — 2026-05-09
+- [x] Create ROCINANTE.md server doc — 2026-05-09
+- [x] Update all docs to reflect deployed state — 2026-05-09
diff --git a/docs/servers/PLAUSIBLEDENABILITY.md b/docs/servers/PLAUSIBLEDENABILITY.md
index f6f84d6..dc1a315 100644
--- a/docs/servers/PLAUSIBLEDENABILITY.md
+++ b/docs/servers/PLAUSIBLEDENABILITY.md
@@ -31,7 +31,8 @@ Primary Docker host running all production workloads.
 RTX 2080 Ti used by:
 - Plex (hardware transcoding)
 - immich-ml (CUDA face recognition)
-- ollama (LLM inference)
+- Whisper (CUDA speech-to-text, port 8786)
+- Ollama light-tier inference (qwen2.5:14b and smaller)
 
 Recommended models for 11GB VRAM:
 | Model | VRAM | Best for |
@@ -45,9 +46,14 @@ Recommended models for 11GB VRAM:
 - Pangolin VPS + Newt for external services
 - SSH from Windows 11
 
-## NFS Exports to Other Servers
-- `data` share → PD at `/mnt/unraid/data`
-- `immich` share → PD at `/mnt/unraid/immich`
+## NFS Mounts (from Serenity)
+- Serenity `/mnt/user/data` → `/mnt/unraid/data` (media libraries)
+- Serenity `/mnt/user/immich` → `/mnt/unraid/immich` (Immich photo library)
+
+> **Note:** NFS mounts are not automatic at boot. Run after every TrueNAS restart:
+> ```bash
+> sudo bash /mnt/tank/docker/scripts/mount-unraid-nfs.sh
+> ```
 
 ## Known Issues
 - immich-ml intermittently unhealthy — investigate GPU/CUDA health
@@ -55,6 +61,6 @@ Recommended models for 11GB VRAM:
 - No off-site backup
 
 ## Pending
-- Deploy: dispatcharr, gotify, bytestash, kima-hub, n8n, qdrant, paperless-ngx
 - Add Pangolin resource + DNS for `ai.paccoco.com`
 - Install fresh editor
+- Set up private Gitea repo for .env file backups