Architecture
How Capped AI deploys an isolated inference environment inside your AWS VPC.
Every component in the inference path runs on a physical appliance inside your plant perimeter. No operator data leaves the site. Capped AI connects to your DCS historian in read-only mode via OPC-UA. The appliance cannot write to or actuate the DCS — architectural guarantee, not policy.
System architecture
┌─────────────────────────────────────────────────────────┐
│ Plant Perimeter │
│ │
│ ┌──────────────┐ OPC-UA ┌─────────────────────┐ │
│ │ DCS / DeltaV │ (read-only) │ Capped AI Appliance │ │
│ │ Honeywell │──────────────▶│ 1U · 2× H100 80GB │ │
│ │ PI Historian│ │ Qwen 2.5 72B │ │
│ └──────────────┘ │ Whisper-large-v3 │ │
│ │ pgvector retrieval │ │
│ ┌──────────────┐ └──────────┬──────────┘ │
│ │ Operator │ Voice/text │ │
│ │ Tablet │──────────────────────────┘ │
│ └──────────────┘ │
└──────────────────────────────┬──────────────────────────┘
│ Outbound only
│ Aggregate metrics, no customer data
▼
┌──────────────────────┐
│ Capped AI Ops Cloud │
│ Health metrics only │
│ Model updates only │
└──────────────────────┘Key architectural properties
| Property | How it works |
|---|---|
| No cloud egress of customer data | All AI inference runs on the local H100 appliance. Handover text, alarm logs, and DCS readings never leave the plant perimeter. |
| OPC-UA read-only | Capped AI connects to your historian via a read-only OPC-UA subscription. The appliance has no write path to the DCS — verified at the firewall and at the OPC-UA session level. |
| Open-weights LLM on-site | Qwen 2.5 72B runs in vLLM on the H100 appliance. Llama 3.3 70B is available as a fallback. No dependency on external AI APIs. |
| WORM audit log | Every completed and signed handover is written to a tamper-evident, append-only log on the appliance. Cannot be deleted without physical access and a dual-person integrity process. |
| Voice to text on-site | Whisper-large-v3 runs locally for Arabic and English speech recognition. No audio data is sent off-site. |
| pgvector retrieval | Historical handovers are indexed in pgvector for semantic search. The Search module queries this index; the data stays on the appliance. |
DCS integrations — reference architectures
Select your DCS vendor below. Each section includes the network topology, data-flow table, and a configuration checklist for your plant IT team.
Capped AI connects to Honeywell Experion PKS and Uniformance PHD via the built-in OPC-UA server available from Experion R500 onward. No third-party middleware is required — the appliance opens a read-only OPC-UA subscription directly to the Experion server on port 4840.
Data flow
| Data type | Historian source | Typical latency |
|---|---|---|
| Process values (analog / discrete) | Experion PKS real-time DB | 50–150 ms |
| Alarm / Event log | Experion Alarm Manager | 50–150 ms |
| Sequence of Events (SoE) | Experion Event Journal | 50–150 ms |
| Operator journal entries | Experion Station notes | On-demand |
| Historical trend data | Uniformance PHD (up to 5 yr) | 100–300 ms |
Configuration checklist
- Experion R500+ (PKS 510 / 520 / 530) with the built-in OPC-UA server enabled
- OPC-UA endpoint URL:
opc.tcp://<dcs-server>:4840(or custom port configured in Experion) - Security policy:
Basic256Sha256; message mode:SignAndEncrypt - Generate Capped AI read-only OPC-UA client certificate (2048-bit RSA, 2-year expiry) — provided by Capped AI field engineer
- Add Capped AI client cert to Experion's Trusted Certificates store in the Experion Server Configuration Console
- Grant NodeId read access to:
AlarmConditionType(alarm summary), historical trend nodes, and Operator Journal — no write-capable NodeIds - Firewall rule: allow
TCP 4840from Capped AI appliance IP to Experion OPC-UA server IP (one-way, inbound to DCS only) - Verify no write-capable NodeIds appear in the Capped AI session's subscription list after connection
Integration FAQ
TCP 4840 — OPC-UA, outbound from Capped AI appliance to DCS historian (inbound to DCS only; no reverse write path). TCP 443 — HTTPS, outbound from Capped AI appliance to ops.capped.ai for the encrypted aggregate metrics heartbeat (no customer data; can be disabled for fully air-gapped mode). TCP 443 — HTTPS, inbound from operator tablets to Capped AI appliance. No other ports are opened or accepted.Appliance hardware specification
| Component | Specification |
|---|---|
| Form factor | 1U rack-mount server |
| CPU | Intel Xeon Gold 6438N (32-core, 2.0 GHz) |
| GPU | 2× NVIDIA H100 80GB NVLink (SXM5) |
| RAM | 256 GB DDR5 ECC |
| Storage | 8 TB NVMe RAID-1 (handover data) + 2 TB OS SSD |
| Network | 2× 10GbE (OPC-UA + management), 1× IPMI |
| Power | 220V / 15A, redundant PSU |
| Operating system | Ubuntu 22.04 LTS (hardened, no public internet access) |
| Inference | vLLM serving Qwen 2.5 72B + Whisper-large-v3 |
| Database | PostgreSQL 16 + pgvector extension |