Machine Pilot AI
Now in pilot with HMPS and Big Dog

Centralise your operational knowledge — the mastermind of your plant, at your fingertips.

Machine Pilot turns the operational IP scattered across your plant — PLC code, SOPs, OEM manuals, and the know-how locked in your senior operators' heads — into one source of truth. Access all of it through the Machine Pilot terminal: ask in plain language, get answers grounded in your own documentation and cited every time. Operators get help in seconds, and the knowledge stays in the business when people move on.

All your operational IP, one terminal Cited from your own sources AU data residency
OEE
87%
▲ 6%
Running
24
of 28
Downtime
2h 15m
▼ 18%
Alerts
3
attn
P1
Palletiser 01 — Running
98%
CP
Case Packer 02 — Warning
74%
RC
Robot Cell 04 — Faulted
32%
CITED HMPS 8000 manual · §11.4 · p.34

Centralise plant knowledge

Turn decades of tribal knowledge, manuals, PLC logic, SOPs and maintenance procedures into one searchable intelligence platform — so it stays in the business when people move on.

Solve problems faster

Give every operator and technician instant, sourced answers to troubleshoot, operate and maintain equipment — cutting the escalation chain and defending the shift.

Get smarter every day

Machine Pilot grows with your plant, continuously learning from new documentation, approved improvements and operational experience — a factory that gets smarter every shift.

Trusted by
HMPS — OEM partner
Big Dog Plant — pilot customer
Australian-built · SYD data residency
See it in action

Watch it answer a real fault — with the citation to prove it.

An operator asks in plain language. Machine Pilot replies with a clear, ordered fix and the exact source it came from — never a generic guess.

The problem

Faults cost more than the part — they cost the shift.

The right information is usually somewhere on site — in a senior operator's head, in a PLC nobody touches, in a manual that was last opened five years ago. Machine Pilot centralises it and puts it in the operator's hands the moment they need it.

01 · Knowledge loss

The knowledge that walks out the door, doesn't anymore

Every senior operator who leaves takes years of plant-specific knowledge with them. Machine Pilot centralises that knowledge so it stays — turnover stops costing you uptime, and new starters don't fumble through faults their colleagues solved in minutes.

02 · Knowledge at your fingertips

All your knowledge, instantly accessible

Escalating for help takes too long — sourcing the right information from the right person, while the SOP manual was lost years ago. Now, for the first time, every source of knowledge is consolidated and presented in seconds.

03 · Clear instructions, not guesswork

Clear instructions eliminate trial and error

Without a fast, trustworthy second opinion, operators try the same five fixes in different orders — and trial and error usually makes things worse. Clear, correct instructions, grounded in your machine's own data, eliminate the guesswork. Lost production costs $15K–$80K+ per day; that's the line being defended.

A line operator using the Machine Pilot terminal at the workstation
A line operator getting a cited answer at the Machine Pilot terminal — on the floor, mid-shift.
On the floor

Built for the people who keep the line running.

Machine Pilot isn't a dashboard for head office. It's a second opinion in the hands of the operator, the technician and the maintenance lead — right where the work happens, the moment a fault stops the shift.

  • Where they already stand. On the line terminal, a tablet, or the phone in their pocket — no trip to the office, no waiting on a callback.
  • Plain language in, clear steps out. Operators ask in their own words and get guidance with HMI button names called out — no manual-diving.
  • Every answer earns trust. Sourced and cited from your own documentation, so the person on the floor can act with confidence.
How it works

Every answer grounded in your operation's own sources — in a clear order of priority.

Machine Pilot doesn't guess. Every answer is built from your operation's own knowledge, in a disciplined order: your equipment's own logic and data first, your documented procedures next, then manufacturer documentation. Where sources disagree, the conflict is surfaced — not hidden. The same discipline scales from a single-machine pilot to a multi-site enterprise deployment.

1
Your equipment's own logic and data — the closest thing to ground truth

PLC exports, SCADA tags and historian data are ingested and mapped to specific tags, rungs and routines, so answers are grounded in how your machine actually works — not a generic guess. Live integration to your control systems is available where the operation needs it.

2
Your documented procedures — the way your plant actually runs

Standard operating procedures, work instructions, cleaning and changeover routines. Versioned, retrievable, and indexed in your plant's own vocabulary.

3
Manufacturer documentation — how the equipment is designed to work

Structure-aware chunking of OEM manuals. Vision-captioned electrical drawings. Indexed by section, page, and component, so a citation always lands on the right place.

Hard safety rule — non-overridable. Machine Pilot refuses any request to bypass, defeat, jumper, or override a safety interlock, guard, e-stop, or safety-rated circuit. No prompt, no tenant config, no user role can change this. Operators get pointed to the right qualified path.
Tailored to your plant

One engine. Your configuration. Your licence.

Machine Pilot isn't a generic chatbot dropped onto your shop floor. Every deployment is configured around your specific equipment, processes and people — without rewriting the platform. You get a tailored licence; we maintain the engine underneath it. The result is enterprise-grade AI that speaks your plant's language.

Your corpus, your boundary

Your manuals, SOPs and PLC exports are loaded into a tenancy that's strictly yours. No co-mingling, no cross-customer learning, no shared embeddings.

Your plant's vocabulary

System prompt extensions teach the engine your terminology, your escalation paths, and your role-based behaviour — without weakening any of the platform's safety rules.

Your model behaviour

Response style, level of caution, language, depth of citation — configurable per tenant. The same model, tuned to fit how your operators actually want to be spoken to.

Your branding and integrations

White-label option, your SSO, your audit log routing, your dashboards. The platform plugs into the systems your team already uses.

Capabilities

Built for industrial reality, not a chat window.

The features that matter on a plant floor — citations, safety refusals, multi-source reasoning, audit trails — are first-class. Not bolted on.

Cites every claim

Inline citations to section, page, PLC tag, and routine. Operators can verify, supervisors can audit, suppliers can trust.

Safety-first refusals

Hard refusals on guard bypass, interlock defeat, or any safety-rated override — built into the base prompt, not toggleable by configuration.

Multi-source reasoning

One question can pull from PLC, SOP, manual, and drawings in a single answer — and flag where they disagree.

Multi-tenant by design

Each customer's corpus, system prompt, and model behaviour is configured per tenant. One platform, many plants — no data ever crosses.

Audit trail + analytics

Every operator turn, model decision, and source citation is logged. Supplier audit, plant management reporting, regulatory traceability — all out of the box.

Browser, tablet, or chatApp soon

Operators interact on the screen they already use — and the terminal is fully mobile-responsive today, so it works on the phone in their pocket on the floor. A dedicated mobile app is on the roadmap, with WhatsApp and Slack adapters that drop in without changing the engine.

Self-service knowledge updates

When your SOPs change or a new procedure is approved, drop the updated file into your customer portal — drag, drop, indexed. The next operator question sees the new procedure. No code change, no engineering ticket, no waiting.

Scales with your plant

From a small manual line to a fully automated multi-site plant.

The platform meets your operation where it is today and grows as your automation, data and people mature. A site with paper SOPs and tribal knowledge starts seeing value in week one; a fully PLC-instrumented multi-site group gets the same engine with deeper grounding, central oversight, and consistent answers reaching everyone — from the operator on the line to the supervisor at the production meeting to the CEO reviewing OEE.

Small & semi-automated

Paper SOPs, OEM manuals, and the tribal knowledge in your senior operators' heads. Captured, indexed, and made answerable in week one. Add PLC ingestion later as your data matures — no replatforming.

Multi-machine production lines

Several machines on one site, mixed automation, mixed vintages. PLC + SOP + manual + drawings ingested for each asset. Plant-specific prompt tuning, integrated maintenance schedules, supervisor-level analytics.

Multi-site enterprise

Many plants, central tenancy and audit, per-site configuration, SSO, and exec-level reporting. The same engine reaches operators, supervisors and executives with answers grounded in each site's own data.

Who benefits

One platform, three audiences.

Operators get answers. Maintenance gets context. Plant managers get visibility. Everyone gets the audit trail.

Operator

Resolve faults in minutes, not hours.

  • Plain-language guidance with HMI button names in bold
  • Photo upload of fault screens, vision-parsed and explained
  • Refuses requests that would compromise safety
  • Time-saved counter visible after every resolution
Maintenance

Walk in with context, not questions.

  • Full transcript + cited sources for every escalation
  • Maintenance schedule pulled from OEM intervals
  • Trending photo-eye / sensor issues flagged before they fail
  • Spare-parts list linked to the relevant page of the manual
Plant manager

OEE, downtime, and resolution metrics, daily.

  • Live dashboard: OEE %, machines running, alerts, downtime
  • Per-shift, per-machine, per-fault-code breakdowns
  • AI-recommended interventions before faults compound
  • Exportable reports for supplier and regulatory audit
~28 min
Average time saved per resolved fault vs. typical escalation path
82%
Faults resolved by AI in the Big Dog pilot, first 30 days
100%
Answers cite their sources — auditable end-to-end
0
Successful safety-bypass attempts — refused 100% of the time
Pilot data from asset 13859 (HMPS 8000 de-palletiser) at Big Dog · stats updated as the pilot extends
Pricing

Pick the tier that matches your plant.

One platform, three tiers, transparent metering. All tiers ship with citation grounding and safety refusals — they're not premium features.

Essential
$890/ month
For single-machine pilots
  • One machine, one site
  • OEM manual + SOP ingestion
  • Browser / tablet operator chat
  • Source citations on every answer
  • Standard safety refusals
  • 500 queries / month
  • Community support
Start a pilot
Enterprise
Custom
For multi-site groups and OEMs
  • Unlimited machines, multi-site
  • All Pro features
  • SSO / SAML + audit log
  • Australian data residency option
  • Dedicated technical specialist
  • Unlimited queries
  • 4-hour critical SLA
Contact sales
Security & compliance

Built with the assumption that your data matters.

Customer / OEM documents are sensitive. We treat them that way from day one — encryption, tenant isolation, hard safety rules, and Australian hosting where you need it.

Bearer-token API auth

Per-tenant API keys with tier scoping. No cookie sessions, no shared credentials, no auth surprises.

Strict tenant isolation

Every database row carries a tenant_id. Every query filters by it. Customer A never sees Customer B's documents, fault logs, or system prompt.

Non-overridable safety rules

The safety refusals are in the base system prompt. Tenant configuration can extend, never weaken. AS 4024 / ISO 13849 aware.

Immutable audit log

Every operator turn, every model decision, every cited source — logged with timestamps. Supplier and regulator-ready.

Australian data residency

Hosted on DigitalOcean Sydney (SYD1). No data leaves the country unless you explicitly extend to a multi-region deployment.

Encryption in transit & at rest

TLS 1.3 for all traffic, AES-256 at rest for conversation logs and ingested documents. Secrets managed in the DO App Platform vault.

FAQ

The questions plant managers and OEMs ask first.

How is Machine Pilot different from ChatGPT or generic AI assistants?

Generic chatbots hallucinate. Machine Pilot is wired into your specific PLC, SOPs and OEM manuals — every answer it gives is grounded in your machine's own documentation, with citations. The model is also configured to refuse any request that would compromise safety (e.g. bypassing an interlock), which generic chatbots do not enforce.

What if our PLC export isn't available yet?

The platform runs in a "manuals and SOPs" mode until the PLC export is available, and clearly tells operators when a question would benefit from PLC context that isn't yet ingested. When the L5X export arrives from your OEM, ingestion is a single job run — no code change.

What does onboarding a new site look like?

For an existing customer adding a second site: drop the new site's documents into their cloud folder, add a tenant row with site-specific configuration, run the ingestion job. Typically under one hour of work. For a brand-new customer: a kick-off call to map their documentation, then 1–2 weeks to first operator demo with their real corpus.

Does the AI ever just guess or make things up?

The system prompt is hardened to require source attribution on every factual claim. If the retrieved chunks don't cover the question, the model is instructed to say so and ask a clarifying question — not to invent fault codes, tag names, or procedures. We monitor citation accuracy as a first-class quality metric.

Can it integrate with our existing tools?

Yes. The API is the product. The browser / tablet wireframe you see in the demo is one interface; Slack, WhatsApp, and embedded-in-your-own-dashboard integrations all hit the same /ask endpoint. The roadmap covers Slack escalations in Phase 2 and WhatsApp field-tech mode in Phase 3.

Who owns the data?

You do. The conversation logs and ingested documents belong to you. We use the platform's logs to improve quality on your tenant only — never to train models that other tenants benefit from. Enterprise tier includes a contractually scoped data-use clause.

What happens when our SOPs or PLC code change?

Drop the new files into your customer portal — drag, drop, indexed. The platform re-ingests automatically and the next operator question sees the updated content. For PLC L5X changes, the same one-job ingestion pipeline catches the new tag definitions and rung logic. No engineering ticket, no code change, no waiting on us. Your plant team owns its own knowledge updates.

Stop fault-finding alone.

We're booking 10-minute discovery calls with plant managers and OEMs through May–June. Walk us through one of your machines, see Machine Pilot answer a real question from your documentation, decide if it's worth a pilot.

Machine Pilot Tell us about your plant — we'll be in touch