95.8%
Citation rate
The self-hosted support intelligence engine for engineering-led manufacturers — trained on your products, running on your infrastructure, with every answer traceable to source.
For an engineering-led manufacturer, customer support bleeds money in four directions at once, and none of it shows on a single P&L line.
£40k–£100k of senior engineering time given away every year — untracked, unbilled, invisible.
Your best people answer tickets instead of building product — and the knowledge walks out the day they leave.
The moment support data hits a cloud AI platform, you may already be in breach of an NDA or export obligation.
The same part fails across eight systems over six months — and nobody connects it until it's a warranty crisis.
Cortex captures every case, resolves the routine work automatically, enforces your commercial policy, and turns recurring failures into product intelligence — learning a little more about your equipment with every case it touches. Self-hosted by default. Trained on your data. Yours forever.
Cases arrive from any of eight channels into one record, then are scored on contract, severity, warranty and repeat-failure signals and assigned automatically.
Cortex proposes validated resolutions, enforces commercial policy, drafts the reply, and raises a quote when free support is exceeded — handling the 80% already solved.
Recurring failures become R&D intelligence; every closed case feeds the knowledge base, so accuracy compounds with every ticket.
An 90-second walkthrough of the case lifecycle, the conversion email, and the learning loop.
The commercial policy engine tracks support time against your free-hours allowance, detects the moment a case becomes billable, and generates a three-option conversion offer — automatically, on-brand. Support stops leaking money and starts generating it.
Recurring failures are clustered across unit, part and component, then raised as structured Product Improvement Recommendations for engineering — with the at-risk installed-base list attached. Reactive support becomes proactive engineering.
Knowledge is indexed by your bill of materials, not flat document storage. A case about one product pulls the right answer at product, sub-assembly and component level — specific to the exact configuration in front of the customer.
Every recommendation cites its source; if it can't, it flags inference rather than asserting fact. Every parameter is yours to set — and the AI model is swappable, so there's no lock-in at the AI layer.
A conversational assistant over your whole operation. Ask it how to do something and it walks you through it — that's your onboarding, no manual required. Ask who owns a customer's open cases, or this month's satisfaction score, and it answers from your live data, showing each person only what they're allowed to see. Sharp, permission-aware, and with a dry sense of humour.
A native mobile app puts the whole operation in your engineer's pocket: update a case from a plant floor, capture a voice field report that transcribes itself, and read your cases even with no signal at all. On your own infrastructure, over a secure tunnel — because the work doesn't always happen at a desk.
No rip-and-replace. Cortex pulls your customers and installed base from your CRM — Salesforce, HubSpot, Zoho, Microsoft Dynamics, SAP — takes tickets in from Jira and Zendesk, and ingests documents straight from SharePoint or a network file share. Sign-on rides your own identity provider. It reads from your systems and never needs write-access into them — which is exactly what your security team wants to hear.
Cortex learns from two streams — your company knowledge and your team's corrections. Every closed ticket becomes training data; every expert's instinct becomes structured, reusable capability before it walks out the door. Where every other platform plateaus, Cortex compounds.
Cortex publishes its accuracy against a locked, open benchmark — a 120-case hand-authored corpus across ten real manufacturing failure clusters, a held-out split, and bootstrap confidence intervals, measured on the same hardware we ship. The full methodology is available on request.
| Metric | Result | What it means |
|---|---|---|
| Citation rate | 95.8% | Grounded in a real, clickable source document |
| Fabrication rate | 5.0% | How rarely it asserts what it can't ground |
| Recall @ 5 | 83.3% | Right answer in the top five when it exists |
Enterprise software with a formal security architecture — 4,000+ automated tests on every code change and a production-approved security risk score.
| Framework | How Cortex aligns |
|---|---|
| GDPR | Data on your infrastructure; one-click erasure with full cascade. |
| ISO 27001 | Aligned to ISO 27001 controls across the stack. |
| DEFCON 658 · CSMv4 | Appliance fully air-gapped — no telemetry, all local. |
| Cyber Essentials · EU AI Act | Transparent AI, human override, source citation throughout. |
The same software and guarantees on all three tiers, with full data portability between them.
Cortex is priced against what it returns, not what it costs. A typical client recovers more in unbilled support in the first year than the platform, implementation and maintenance combined.
Unbilled support typically recovered per year.
Lower 5-year cost of ownership vs enterprise alternatives.
To implement — not the 6–18 months of enterprise platforms.
Set your team size and support operation. Your projected return updates as you go — enter a work email to reveal your indicative investment and our commitment.
A valid work email is required to reveal your pricing. We'll send you a copy and follow up to talk it through — nothing else.
Please enter a valid email address.
We make it work. If Cortex doesn't deliver against the plan we agree, we don't hand back cash and walk away — we keep going: extended support, further training and continued optimisation, until it does.
Your figures are on their way — let's walk through them. A short call to confirm the tailored figure for your deployment and put the commitment in writing.
Book a call →Cloud helpdesks have no hardware lifecycle and are ruled out where data can't leave the building. Enterprise field-service platforms are priced for £500m-plus companies. Cortex is built for the engineering manufacturer who needs working support intelligence, owns the result, and refuses to send their product data anywhere.
The 8-page overview — what Cortex does, the proof, deployment and security.
Download PDF →Watch the case lifecycle, the conversion email and the learning loop.
Watch the demo →For your compliance team — architecture, controls and the compliance map.
Request access →The full, reproducible measurement spec behind the published numbers.
Request the spec →It stays on your hardware. Full stop. No telemetry, no external AI APIs, no cloud dependencies. You own the appliance, the data, and the knowledge base it builds.
Every suggestion is reviewed by a human before it reaches a customer — Cortex drafts, your engineers approve. And every correction feeds back: fabrication rate is down to 5.0%, and 95.8% of recommendations cite a real source. Getting it wrong becomes training data.
That's your advantage, not your problem. Cortex is model-agnostic — you pull a better model, load it from the admin UI, benchmark it against your own corpus, and switch. No code changes, no upgrade fee, no lock-in at the AI layer.
If two or more engineers lose time to things that aren't R&D, you're the right size. Smaller teams benefit more, because tribal knowledge is a bigger risk.
Two to eight weeks depending on data migration. You're not buying a blank canvas — Cortex ships with a proven support workflow already configured.
It learns your products during onboarding — from your manuals, historical tickets and a knowledge session with your engineers. The value is the knowledge base it builds about your equipment, and it keeps learning every day.
You'll know within those twenty minutes whether Cortex solves a problem you have.
On Microsoft Teams. Bring a real support case and we'll run it through Cortex live.
Book your call →Accelerate. Optimise. Outperform.