NOVA Prompts
Prompt Library Prompts for Work Prompts for Life Guides NOVA Standard
iOS app
Browse all
Prompt LibraryThe NOVA Prompt Standard

Enterprise-grade AI prompts

The NOVA Prompt Standard

Twelve quality gates every NOVA prompt passes before it is sold. Together they decide whether a prompt behaves the same way on every run: it states its method, routes your case, traces every figure, follows written rules for hard cases, and checks its own answer before handing it over.

That is what we mean by an enterprise-grade AI prompt: the work is done the way a senior practitioner’s work is checked inside a large organisation.

How a prompt is scored

Each gate is scored 0, 1 or 2. A prompt ships only when every gate scores 2, and it is scored again every time it changes. That applies to the flagships and to every prompt in every pack.

0Absent. The prompt leaves this decision to the model.
1Partial. Present in some places, or stated without a rule the model can follow.
2Present and working. Written as an instruction the model follows on every run.

The twelve gates

Each gate below quotes the instruction as it appears in the McKinsey-Grade PowerPoint Generator, and shows what it did for Ridgeline Health, the fictional nine-hospital system in that product’s worked example.

01

The brief

Persona and principle

What it requires. A named senior practitioner with a track record, plus the operating principle that changes the output.

Why it matters. The principle decides what the output leads with and what it leaves out. A job title alone decides neither.

In a NOVA prompt

a strategy consultant who has led board engagements for fifteen years ...
Your operating principle: a deck exists to get one decision, so the
recommendation reaches the room by slide 2, every title states a finding,
and any slide that does not prove the argument is cut.

A typical prompt

“Act as an expert” sets a tone, not a standard. Nothing decides what goes first or what gets cut.

In the worked example

The recommendation, operating margin from 0.6% back to 3.2% by FY28, is on slide 2, before any evidence.

02

The brief

Intake

What it requires. The inputs that decide the output are asked for, restated and confirmed before work starts. If you have none, the prompt researches them with cited sources, proposes labelled estimates, or leaves marked gaps: your choice, and it never stops.

Why it matters. Most weak output starts with an input the model filled in silently. Asking first is cheaper than rewriting later.

In a NOVA prompt

If a decisive input is missing, or I tell you I have none, ask once and offer:
 (a) I SUPPLY IT - you wait for it.
 (b) YOU RESEARCH AND PROPOSE IT - ... cite each one with its source and date ...
 (c) YOU LEAVE A GAP - build the full output with [NEEDS INPUT] placeholders.

A typical prompt

The model starts writing from one line of request and fills every gap itself.

In the worked example

The brief and the FY23–FY25 finance and operations figures, restated in seven lines and confirmed before any analysis.

03

The brief

Routing

What it requires. Each materially different case is sent to its own method and output structure, from a lookup table in the prompt.

Why it matters. A board paper, a sales pitch and an investor deck are argued differently. One method for all of them fits none.

In a NOVA prompt

ROUTER  (deck type -> spine | analyses | blueprint)
- Strategy/board -> SCR + answer-first | problem-framing, situation,
  competitive, options, business case, risk | Strategy blueprint

A typical prompt

Every deck gets the same title, agenda and bullet slides, whether it is a board paper or a sales pitch.

In the worked example

Routed as a strategy and board deck: Situation-Complication-Resolution, six analyses, a twelve-slide blueprint. One of ten routes.

04

The method

Methods, written out

What it requires. Textbook methods with the rule or formula in the prompt, so two runs on the same data calculate the same way.

Why it matters. When the rule or formula is in the prompt, two runs on the same data give the same answer.

In a NOVA prompt

Business case: ... ROI = (total benefit - total cost) / total cost;
payback = months until cumulative net benefit turns positive; NPV at my
discount rate, or [NEEDS INPUT] if none is given

A typical prompt

The model picks a method on each run, so two runs on the same numbers disagree.

In the worked example

$9M of one-time investment against $55M a year of recurring operating income, with a 14-month payback, each with its arithmetic in the notes.

05

The method

Evidence rules

What it requires. Every figure is traced to your material, a cited source or its arithmetic. Estimates are labelled as estimates, gaps are marked, and nothing is passed off as fact.

Why it matters. A figure nobody can trace is the fastest way to lose a board, an investor or a client.

In a NOVA prompt

Never invent a number, a quote, a client, a benchmark or a source ...
A figure the argument needs but my material lacks becomes
[NEEDS INPUT: what, and who could supply it].

A typical prompt

Missing figures are filled with plausible numbers that nobody can trace.

In the worked example

Contract labour at 19.4% of nursing spend, against a peer median of 7.6%: graded Evidence. “Medicare Advantage rates recover at the FY27 renewals”: graded Assumption, and labelled as one.

06

The method

Output specification

What it requires. The exact structure of every deliverable, so the output arrives in a form a board can use.

Why it matters. The structure decides whether the output can be used as it stands or has to be rewritten.

In a NOVA prompt

SLIDE [n]
  Action title:    [the single takeaway, as a full sentence]
  Job in argument: [why this slide exists]
  Visual:          [the framework/chart + its encoding - pick via the chart selector]

A typical prompt

Slide titles are topic labels: “Financial Overview”, “Payer Mix”.

In the worked example

“Payer Mix” became “Medicare Advantage grew from 19% to 34% of volume in four years, and is forecast to reach 41% by FY28 on current contracts.”

07

The controls

Audience

What it requires. Who reads it, what to lead with and what to cut, set for each audience.

Why it matters. The same finding is presented differently to a CFO, a board and a customer.

In a NOVA prompt

AUDIENCE OVERLAY  (lead with / cut)
- Board   lead: risk, governance, shareholder value
          cut: execution minutiae

A typical prompt

One deck for every room: the board, the CEO and a customer read the same slides.

In the worked example

Board overlay: the ask names the $9M envelope and three board checkpoints, in FY26 Q2, FY27 Q1 and FY27 Q4.

08

The controls

Edge cases

What it requires. Written rules for the cases where the standard method breaks.

Why it matters. Standard methods break on thin data, contrary evidence and unusual cases. Written rules say what happens then.

In a NOVA prompt

- Evidence against the objective: say so at STEP 2 and propose the deck
  the evidence supports, including "do not proceed".
- Thin or no raw material: apply NO INPUT? THREE WAYS FORWARD at STEP 0 ...

A typical prompt

Asked for a recovery plan, the model writes one, whether or not the numbers support it.

In the worked example

Checked at routing: full data, one decision-maker, twelve slides. No edge case applied, and the prompt said so before building.

09

The controls

Stops for your approval

What it requires. The model stops wherever the buyer must decide, instead of producing one long answer.

Why it matters. Approving the route before the work starts costs minutes. Rewriting finished output costs hours.

In a NOVA prompt

Using the ROUTER, name (a) the deck type, (b) the narrative spine,
(c) the analyses to run, (d) the slide blueprint to target ...
Confirm in 6 lines. PAUSE.

A typical prompt

One long answer. A wrong deck type is discovered on slide 12.

In the worked example

Three stops: the route, the graded analysis and the storyline. Nothing was built on a choice the CFO had not approved.

10

The proof

Quality gate

What it requires. Named checks the model runs on its own work, fixing every failure before handover.

Why it matters. An error the prompt catches never reaches your reader.

In a NOVA prompt

[ ] Every number is sourced (my material, or a cited source with its date) or shows
    its arithmetic; every estimate is tagged ASSUMPTION ...
[ ] Totals, bridges and percentages recompute exactly
[ ] A clear, specific ask/close: the decision, the owner, the date

A typical prompt

No check. The first reviewer is the board.

In the worked example

Eleven gates, nine passed first time. Fixed: a topic-label title, and $55M shown without its arithmetic (2.6 points × $2.1B = $54.6M).

11

The proof

Build and hand-off

What it requires. A real file in Claude, to a written specification, with a text fallback in other tools, and the next step named.

Why it matters. A finished file saves the time spent reformatting text into a document, a workbook or a deck.

In a NOVA prompt

Charts as native, editable chart objects with their data inside the
chart - never pictures. ... Then tell me: to present it out loud, paste
the final deck into the NOVA Presentation Script Generator for the
word-for-word talk, timed to the slot.

A typical prompt

Text to paste into PowerPoint by hand, slide by slide.

In the worked example

The twelve slides below: an action title on every slide, seven charts, and the recommendation on slide 2.

12

The proof

Integrity

What it requires. The prompt says when the evidence does not support the request, and leaves the judgment with you.

Why it matters. A prompt that always agrees with the brief cannot tell you when the brief is wrong.

In a NOVA prompt

If the evidence does not support the objective, say so. Challenge me
when my thinking is weak - the judgment stays mine.

A typical prompt

The model agrees with the brief it was given.

In the worked example

The analysis surfaced it unprompted: the FY24 cost programme cut the appeals team by 30%, and denials overturned on appeal fell from 64% to 41%.

Check it before you buy

Every product page publishes its worked example in full: what the company brought to each prompt, what the prompt returned, and the finished documents. The figures are fictional and every one of them reconciles.

See the PowerPoint Generator Browse every pack

Questions

What makes an AI prompt enterprise-grade?

It does the work the way a senior practitioner’s work is checked inside a large organisation: the method is stated and written out, the case is routed to the right output, every figure is traced to the user’s material or marked as missing, hard cases follow written rules, and the answer is checked against named quality gates before it is handed over.

What is the NOVA Prompt Standard?

Twelve quality gates every NOVA prompt must pass before it is sold. Each gate is scored 0 to 2, and a prompt ships only at 24 out of 24.

Which NOVA products are built to the standard?

All of them: the McKinsey-Grade PowerPoint Generator, both voices of the Presentation Script Generator, and every prompt in the Prompts for Work and Prompts for Life packs.

Do the prompts still work in ChatGPT and Gemini?

Yes. Every prompt runs in ChatGPT, Claude and Gemini. Where a prompt builds a Word, Excel or PowerPoint file in Claude, it returns the same content as text and tables in tools that cannot create files.