Questions about Artekis.

No. It never writes to a device, OPC item, setpoint or alarm, never acknowledges or shelves an alarm, and never applies a configuration change. A proposed change is a recommendation your team applies under its own change control.

Yes, through named queries. Your team writes a select-type named query in a project Artekis is allowed to read, and Ask can call it, up to 1,000 rows at a time. Artekis never runs free-form SQL, so your IT team decides exactly what the model can see.

One you choose, through your own key: Anthropic, OpenAI, or any OpenAI-compatible endpoint, including a model you run on your own network. Every call is priced and recorded.

Copilot works on Microsoft 365 data and cannot see an Ignition gateway. Artekis runs inside the gateway and reads your tags, history, alarms, audit log and production database directly, then sends only the evidence for one question or one run to the model you choose. It answers in Perspective, where your supervisors already are, with a citation for each claim.

Ignition 8.3. The module loads on 8.3.4 and later, and 8.3.8 is the verified platform. Ignition 8.1 is not supported.

A one-time license per gateway, normally $10,000 and $7,000 for purchases through December 31, 2026, activated through Ignition’s own licensing, with an annual support plan for updates and new releases, the same model as Ignition. The price includes four hours of an Artek engineer’s time to set it up with your team. You can evaluate it in Ignition’s two-hour trial first, and it is free on Maker Edition under Maker’s non-commercial terms.

Only inside a run you configured, through your key, to the provider you chose, and every call is recorded. With a model on your own network, nothing leaves it. Show prompt displays exactly what a run would send, without sending it.

In your own database: SQL Server, MariaDB, MySQL or PostgreSQL. Artekis has no cloud component.

You pay your provider directly. On our acceptance run, a 30-day Alarm Health run cost under $0.50 and a daily Gateway Health run about two cents; a gateway producing 30 to 50 alarm candidates a day costs about $15 to $24 a month. The Cost page shows every dollar, and caps stop runs that would exceed them.

No. Start with one plant area. The editor drafts the area’s assets from your tag tree in seconds, and a coverage score shows what is worth adding next.

Your engineer marks it wrong or dismisses it, and that verdict is kept. Dismissed and known issues stay quiet for a set period, and findings below a confidence floor are hidden.

Yes. Any OpenAI-compatible endpoint works, including a server on your own network. Ask needs a model that supports tool calling.

Eight steps, shown as a checklist on the gateway’s Status page: database tables, a connection and secret, the license or trial, the module, configuration, the views pack, playbooks, and an optional incident trigger. The four hours of engineering included in the license cover doing it with your engineer.

No. The baselines are a mean and a standard deviation per measurement, per operating state and product, rebuilt from your own history on every run. The language model only writes the explanation of what the arithmetic found, and that is the run’s only model call.

Yes. Ask is a panel beside the Perspective screens they already use. They type a question about an area in plain English and read an answer with its citations. Who may ask is set by security level, and each user has a limit on questions an hour and spend a day.