Waterloo Road Pump Station. An operator types a question in plain English; the assistant answers it from plant records and controlled documents, and shows its evidence. This page follows one question through the assistant, names the piece of software doing each job, and marks what already exists.
Status as observed on the live host, 21 August 2026.
Seven stages. The important thing to notice: the assistant decides what kind of question it is before it looks anything up, and that decision fixes both which sources it may use and what it is allowed to say.
A web page with a question box and an answer pane, opened in an ordinary browser on the control-room PC. Nothing to install.
A small, fast AI model reads the question and labels it as one of four kinds — or says it is unsure. It does no answering; it only labels. This is the most safety-relevant step in the whole assistant, because the label decides everything downstream.
Two rules are built in: if it is not confident, it asks the operator to rephrase rather than guessing; and if two labels are close, it takes the more cautious one — a question that is partly advice is treated as advice.
Operators say “Pump 02” or “the wet well”. The plant records call those PU-302 and WW-101. This step converts everyday names into the plant’s official ones by looking them up in a list — no AI, no guessing. When it gets a name wrong, the fix is to add the nickname to the list.
“How many high level alarms last week?”
Counts and measurements taken from the plant’s recorded history. If there are no records, the answer says so — it never estimates a figure.
“What does the level fault alarm mean?”
Explains a signal, alarm or piece of equipment from the manuals and alarm records, quoting the document it came from.
“How do I lift the interlock on Pump 02?”
Finds the approved procedure and identifies it — document number, revision, date — and quotes its prerequisites word for word. It never writes the steps itself.
“What discharge rate avoids a spill?”
Shows what has been run before, what happened when, and the documented limits — then hands the decision back to a competent person. It never gives a number as the answer.
“Is the pump alright?”
When the sorting step is not confident, the assistant stops and asks a clarifying question. No sources are searched and no answer is drafted.
The larger AI model is used here and only here: to put the gathered evidence into plain English. It cannot go looking for anything else — it only sees what its lane collected. It supplies wording, not facts.
Every draft is checked against a fixed rulebook before the operator sees it: no invented steps for safety-critical work, no recommended setpoint, nothing beyond the evidence actually found, and every claim carrying its citation. A draft that fails is rewritten once and then refused — it is never shown.
These are ordinary software checks written in code, not instructions given to the AI. That distinction is the point: an AI can be talked out of an instruction, and cannot be talked out of a check.
Beside the answer the operator sees how it was reached: which kind of question it was judged to be, what data was counted and over what period, how many records were found, and which documents were cited with their revision and date. Procedural and advisory answers carry a visible banner stating plainly what the assistant did not do.
Each question, the kind it was judged to be, the sources used, the rulebook result and how long it took are all recorded, so any answer can be reviewed afterwards and any mistake traced to the step that caused it.
The assistant has no free access to anything. These four, and nothing else.
Turns “high level alarms last week” into an exact query over the plant’s recorded history. The definitions that make an answer right — what counts as an alarm, what “last week” means, what counts as a fill — are written down in files an engineer can read and check, instead of being invented per question. It also keeps ready-made summaries so common questions never hammer the live historian.
The assistant never writes database code itself. It fills in a request form; Cube does the rest.
Searches the controlled documents by meaning rather than keyword, so “lift the interlock” finds the right procedure even when the document says “interlock override”. Two rules are permanently on: withdrawn revisions are never returned, and every result carries its document number, revision, date, page and section — a passage that cannot be cited cannot be used.
Every piece of equipment and every measurement point, with the everyday names operators actually use. Deliberately a plain list rather than something the AI works out, so it behaves the same way every time and can be corrected by editing one row.
Not a source of answers — the record of them. Every question and every step it took is stored so the assistant’s behaviour can be audited and improved from evidence rather than impressions.
Two supply lines feed those tools. Neither is finished.
Procedures, manuals, alarm rationalisation and design documents are read, split into sections, and converted into a searchable form. Three habits matter: a numbered step sequence is never cut in half; the document’s type comes from the folder it was filed in, not from a guess; and a person confirms the document number, revision and date before anything is stored. A wrong revision on a procedure is a safety problem, not a tidiness one.
The station’s control system records levels, pump runs and alarms into the plant historian. The assistant reads that history through Cube — read-only, never writing to it, and never touching the control system itself.
Each step ends in a check that must pass before the next begins — so that when an answer comes out wrong, there is one place to look, not four.
| Step | What it delivers | Status | What it needs |
|---|---|---|---|
| 1 | The store — where documents, equipment names and ready-made summaries live | Running now | Done. Live, checks passed. |
| 2 | The logbook — recording of every question, put in early on purpose so every later experiment is traceable | Running now | Done. Live. |
| 3 | The documents — the real procedures and manuals, read in and searchable | Next up | The documents themselves, and someone to confirm each one’s revision and date. Needs nothing from the historian — which is why it goes next. |
| 4 | Access to plant history — a read-only login to the historian | Blocked | The historian server, a read-only login and agreed table names. The only true blocker — start that conversation now, alongside step 3. |
| 5 | Cube — the data translator, with every definition written down | Built, not switched on | Step 4 — though it can be proven on stand-in data first. An engineer must independently confirm its first numbers before anyone trusts them. |
| 6 | The assistant itself — the sorting step, the four lanes, the answer writer and the rulebook | Built, not switched on | Steps 3 and 5, so that a wrong answer can only be the assistant’s own fault. |
| 7 | The operator’s screen — the question box, the answer, the working | Built, not switched on | Step 6, plus one network name record so control-room PCs can reach it — ask for that early, it depends on someone else and will not surface as a problem until the day it is tried. |
| 8 | The exam — 62 engineer-checked questions run end to end and scored | Written, not run | Everything above. Pass mark: 85% correct overall, 95% on the two dangerous kinds, and zero breaches of the rulebook. |
Sign-in, network routing and hosting are handled by platform services already running on the demo host. They are deliberately left off this map — they protect the assistant, but they are not part of how it answers a question.