The product

The Trinito AI Gateway

An on-premise appliance that lets your team use ChatGPT, Claude, and Gemini safely. Sometimes called an AI Firewall or AI Sanitiser — the job is the same: confidential information never leaves your office unredacted.

Book a 20-minute demo Download technical overview (PDF)
Redaction pipeline

Five stages. Layered defence.

Each stage has a job. Together they catch what regex alone cannot.

  1. Regex pass

    UK-specific patterns — postcodes, NI numbers, VAT numbers, IBANs, sort codes, Luhn-validated cards, email, phone. Fast and precise.

  2. Named entity recognition

    A local spaCy model finds person names, organisations, places, and money references that no regex can reliably catch.

  3. Custom rule pack

    Your client list, project codenames, internal product names, supplier names. Loaded per organisation by your admin.

  4. Optional LLM cross-check

    A small local model gets a second look at the prompt; configurable per organisation, off by default for latency, on by default in regulated tiers.

  5. Deduplication and approval

    Findings are merged, the user sees the sanitised version, and one click sends it.

Before
Draft an offer letter for Sarah Patel for the 3-bed flat at 14 Cromwell Road, SW7 4XL. Her solicitor is at Henderson & Co.
After
Draft an offer letter for [PERSON_1] for the 3-bed flat at [ADDRESS_1], [POSTCODE_1]. Her solicitor is at [ORG_1].

On the way back, placeholders are restored so the letter reads naturally.

LLM router

Use any model. Control who uses what.

The Gateway can route to:

  • Local models on the appliance Qwen 2.5, Llama, and others — included with the appliance.
  • Trinito-managed cloud We bill; you get a monthly token allowance — resold Ollama Cloud plus selected direct providers.
  • Your own keys BYO OpenAI, Anthropic, and Google. Your credentials, your invoice.

The admin chooses per-model whether the model is on, who can use it, and which credentials apply. New models can be added by the admin from a curated catalogue.

Audit log

Every prompt. Every redaction. On the appliance.

Every prompt, every redaction, every send is recorded in an append-only audit log on the appliance. The log is hash-chained at the database level — tampering breaks the chain. Compliance can export the last 90 days as a signed CSV.

Hardware specs

Three appliances. Capability scales with tier.

Specs-first overview. See pricing for list prices.

Trinito Compact Trinito Standard Trinito Sovereign
CPU / NPU 8-core CPU with integrated 50 TOPS NPU 8-core CPU with integrated 50 TOPS NPU 12-core CPU with integrated 80 TOPS NPU
Unified memory 32 GB 64 GB 96–128 GB
Storage 1 TB NVMe 3 TB NVMe 4 TB NVMe
Inference throughput ~28 tok/s on Qwen 2.5 7B ~45 tok/s on Qwen 2.5 7B ~80 tok/s on Qwen 2.5 7B
Noise level Near-silent (fanless) Near-silent (fanless) Near-silent
Power draw ~28 W typical ~32 W typical ~90 W typical
Dimensions 192 × 192 × 48 mm 192 × 192 × 48 mm 262 × 197 × 80 mm
Warranty 3 years 3 years + priority support 3 years
Browser extension

Works where your team already goes.

Install the Trinito extension in Chrome or Edge. When staff visit chat.openai.com, claude.ai, or gemini.google.com, the extension routes their prompts through the office Gateway. No retraining required. Falls back to blocked if the Gateway is unreachable, with a clear explanation.

Prompt Shield enabled is what the extension shows in the toolbar.

Integrations

Shipping in v1. Planned next.

Shipping in v1

REST + streaming API

Drop-in alternative to the OpenAI API shape — prompts redacted on the appliance before they leave your network.

Planned

Microsoft Teams bot

Mention the bot in a channel; responses return rehydrated. Audit-logged on the appliance.

Planned

Slack bot

Same model as Teams. Per-channel policy and per-user authentication via SSO.

Deployment

What installation looks like.

  • Plugs into your office network
  • First-boot configuration via local web UI
  • Active Directory / Entra ID single sign-on
  • MFA out of the box
  • Remote management via Trinito's secure tunnel (opt-in, signed WireGuard, off by default for air-gapped customers)
Comparison

Four options, one that actually works.

The homepage table, expanded for buyers who need the detail.

Do nothing Block AI tools SaaS DLP Trinito AI Gateway
Staff use AI Yes Only on phones Yes Yes
Data stays in your office No Yes No — via vendor Yes
Audit trail None Partial Vendor-hosted On-appliance, hash-chained
Works with ChatGPT / Claude / Gemini Yes No Some All three, plus more
Capex, not per-seat — — Per-seat One box, monthly LLM
Custom rules you control — — Vendor-controlled Per-organisation rule pack
Air-gapped deployment — — No Sovereign tier
UK-built — — Mostly US Yes

See it on your network.

Book a 20-minute demo. We walk through the pipeline, router, and audit log on your terms.

Book a 20-minute demo Download the technical overview (PDF)