Articulate. The deck Method Exemplars The data Templates
Articulate · Better PowerPoint

Make a world-class deck with AI.

A working resource for producing presentations that actually land — the repeatable process that takes a deck from a 6 to a 9, the standards the best decks are judged against, 100+ templates you can hand off and edit, and a real confidential board deck rebuilt end-to-end as the proof. Point us at a deck; we apply all of it.

Explore the method → Browse 100+ templates See the proof deck
The proof — a worked example

A real board deck, rebuilt end-to-end

To show the method working, a confidential 13-slide strategy deck was re-cut to eleven action-titled slides — real photography, every figure sourced, the model and money in clean data-viz. The original asked the board to back a continental rollout; the rebuild asks for one small, reversible pilot, and proves every step. This is the bar the resource is built to clear.

The redesigned deck

Structured on SCQA (Situation → Complication → Question → Answer) with action titles — every headline states the argument, so the deck reads as a single sentence top-to-bottom. Topic-specific palette: clinical navy with an African-warm terracotta accent.

Cover slide
1 · Cover. Owning the diagnostic backbone of a continent.
Situation slide
2 · Situation. The diagnosis never comes — 47% / 81% / 94% malaria / TB burden.
Market slide
3 · Opportunity. A $1.4bn market with no one in charge.
Needs vs supply matrix
4 · Quantified. The whitespace — 71 countries, need vs. supply (World Bank data).
Investment map
5 · Landscape. Where the diagnostic capital is going — and the gap.
Kupanda model slide
6 · The answer. One unit, not fifty-four bespoke builds.
Two deployment models slide
7 · Proven, then scaled. One engine, two ways to deploy.
Alliance slide
8 · Why us. Three partners, three risks removed.
Structure and precedent slide
9 · How it lasts. Kenya proved it (KSh 38bn); Lesotho warns ($67m = 51% of budget).
Geographic strategy slide
10 · Where to start. Tanzania, then Kenya and Zambia.
The ask slide
11 · The ask. Greenlight one pilot: Tanzania, twelve months.

Download the editable .pptx → Eleven slides, real documentary photography, two data slides built from live World Bank data, every figure sourced; three headline options sit in each slide's speaker notes.

Before / after

Original (13 slides)Rebuild (11 slides)
~7 of 13 slides AI-generated in NotebookLM — narrative scaffolding presented as strategyEvery slide purpose-built; the genuine Kupanda model and two-model structure kept, the filler cut
Topic-titled slides ("The Vision", "Four Levels of Impact")Action titles — the headline is the argument
Key claims asserted, unsourced ("15 nations = 80% of market")Claims sourced or cut; Kenya MES & Lesotho QMMH added as real, costed precedents
Empty stat slides, no imageryDense sourced factoids + real documentary photography on the human slides
Ask: back a continental rolloutAsk: one reversible 12-month pilot with a single Go/No-Go

The 6 → 9 method

A 9/10 deck is never one prompt. It is a pipeline — research, critique, redesign, critique — with a tool at each stage. This is how LLMs and tools actually get there:

1
Structure before pixels. Lock the storyline (Pyramid Principle / SCQA) and write every action title first. If the headlines don't tell the story alone, the deck fails.
2
Source every claim. Each number gets a citation or gets cut. The single biggest 6→9 lever — an original deck asserts; a 9 proves.
3
Adversarial review. Attack each slide's weakest claim before it ships. LLM-as-critic is where most of the quality comes from.
4
One design system. A single grid, ≤2 fonts, a three-colour palette, consistent chart style (Zelazny: pick the chart from the message).
5
Data-viz, not clip-art. Every concept becomes a schematic or chart — never a stock graphic standing in for an idea.
6
Imagery with intent. Real photography for stakes (people, context); clean schematics for substance (model, money). Never decoration.
7
Look at the output. Render every slide and inspect it at real size against the brief. "Looks good" only counts after looking.
8
Version and iterate. Snapshot every pass so you can compare and roll back. The loop — not a better model — is the unlock.

20 board-grade exemplars

The canon isn't a pile of templates — it's a handful of sources that generate good slides, plus the real decks that prove the point. Links go to the best public home for each.

CANON · STRUCTURE

Minto — The Pyramid Principle

Governing thought on top, MECE support below. The grammar of every consulting deck.

barbaraminto.com →
CANON · CHARTS

Zelazny — Say It With Charts

Pick the chart from the message: comparison→bar, trend→line, composition→stacked, correlation→scatter.

The reference →
CANON · STORYLINE

SCQA + the ghost deck

Sketch every slide as a one-line title before building a pixel. Forces the argument to hold before design.

Worked examples →
CANON · ACTION TITLES

The "so-what" headline

The title states the insight, not the topic. Read the headlines alone and you've read the deck.

See it applied →
REAL DECK

Airbnb — seed deck (2009)

The deck that shaped all pitch decks: one idea per slide, ruthless brevity, problem→solution→market.

View the deck →
REAL DECK

Uber — pitch deck (2008)

Dense market logic made legible; a masterclass in sequencing the case for a category that didn't exist.

In the collection →
REAL DECK

Sequoia — pitch deck template

The canonical 10-slide skeleton VCs expect. The default structure to bend, not break.

sequoiacap.com →
REAL DECK

Dropbox — seed deck

A simple product, a clear wedge, a believable path to scale. Clarity beats polish.

In the library →
REAL DECK

Buffer — transparent raise deck

Honest metrics, plain design — proof that substance and trust outrank visual fireworks.

In the collection →
REAL DECK

LinkedIn — Series B deck

Reid Hoffman's annotated deck: every slide with the reasoning behind it. A teaching artifact.

reidhoffman.org →
REAL DECK

Front — Series A deck

Mathilde Collin's published deck: narrative tension, crisp metrics, a confident ask.

In the library →
REAL DECK

Tesla / SpaceX investor narratives

Mission-first framing that makes capital-intensive bets feel inevitable, not risky.

In the library →
STRATEGY · PUBLIC

McKinsey Global Institute reports

Exhibit-led pages: one chart, one takeaway, sourced footers. The reference for data-density done cleanly.

mckinsey.com/mgi →
STRATEGY · PUBLIC

BCG Henderson Institute

Concept diagrams that carry an argument — the schematic as the slide, not a decoration on it.

bcg.com/publications →
STRATEGY · PUBLIC

Bain — corporate strategy decks

Tight executive summaries; the "answer-first" page that respects a board's time.

bain.com/insights →
STRATEGY · PUBLIC

Stripe annual letters

Prose-and-chart hybrids that prove you don't need bullet soup to land a complex point.

stripe.com →
GALLERY

Slidebean — 35+ startup decks

Annotated, downloadable real decks from funded companies. The best single library to study.

slidebean.com →
GALLERY

Figma — 34 pitch deck examples

Modern, design-led examples with the why behind each layout decision.

figma.com →
GALLERY

Visme — 18 funded decks

Real decks that closed rounds, grouped by what each did well.

visme.co →
TECHNIQUE

Duarte — Resonate / slide:ology

Story structure for presentations: tension and resolution, not a list of facts.

duarte.com →

The data that lifts it

What turned this from a 6 into a 9 was evidence the original didn't carry:

Access gap
47% / 81%
of the global / low-income population has little to no access to diagnostics.
Lancet Commission on Diagnostics, 2021
Market size
$1.38 → $1.91bn
Africa IVD market, 2025–2034, at 3.7% CAGR — small, fragmented, no integrated operator.
Africa IVD Market Report, 2025–34
Precedent that works
KSh 38bn
Kenya's Managed Equipment Services: 98 hospitals across 47 counties on a 7-year lease (2015) — the structure we adopt.
World Bank · Parliament of Kenya
Precedent that warns
$67m/yr · 51%
Lesotho's IFC-flagship QMMH PPP cost $67m a year — 51% of the national health budget — and was terminated early. The failure mode we design out.
Oxfam · PMC

Still internal-only, and flagged as such: per-unit economics, the real country concentration behind "15 nations", and whether any development-finance term sheet exists. A deck can't reach a true 9 on those until the principal supplies them.

Read this first

A note on confidentiality

The source material was marked strictly internal — highly confidential. This page is set to noindex and is unlisted, but it is still reachable by anyone with the link. Treat the URL as sensitive — and say the word to password-gate it or swap the live content for a sanitised dummy.