Tōge Education Hub · Module

The Killer Talk

Give a talk people remember — and walk out wanting to act.

A working method for the talk that lands: narrative-first, figure-driven, and AI-assisted. This module teaches the method and demonstrates what Tōge does — it measures presentation intuition the same way it measures clinical intuition, by comparing your judgment to expert consensus.

3Questions before slide one
5Stages of the arc
5Levels of review
Start the method → Jump to AI Co-Pilot
The Science of Intuition — measure expert intuition, teach it at scale.
The Method

The slides are the last thing you build.

A killer talk is not a slide-building exercise — it's a strategic communication event. The audience leaves with one idea they can act on. Everything in this module works backward from that: decide the message, shape the story, then — only then — open PowerPoint. The same skill Tōge measures in surgeons (expert intuition, externalized and compared) is the skill you are building here.

Teaching

Externalize the expert's mental model

The Three Questions, the narrative arc, and the visual rules are the tacit moves a seasoned speaker makes without naming them. Made explicit, they become a method any speaker can practice.

Measurement

Score the talk before the room does

The 5-Level Review turns "did it work?" into a structured check across narrative, content, design, motion, and assets — the same move IOH makes when it converts opinion into a measured hierarchy.

The learning signal

Where your instinct diverges from the rule

Every interactive below shows where a natural instinct (more text, more slides, decorative motion) diverges from what experienced presenters actually do. The gap is the lesson.

Step 1 · Before PowerPoint

Answer three questions first.

If you can't answer these three, the talk isn't ready to build — no matter how good the slides look. Fill them in. The build button stays locked until all three are real.

Q1 Who is in the room?
Audience determines everything: depth, tone, jargon, what to teach vs. assume, and the call-to-action.
Q2 What is the ONE thing they should remember?
A single take-home message, stated in one sentence. If it takes two sentences, the talk isn't ready.
Q3 Why should they care?
The opening hook connects the science to something the audience already cares about — a patient, a problem, a gap.
0 / 3 answered
Step 2 · Shape the story

Build the arc, not the outline.

A killer talk follows a story arc, not a manuscript. Click each stage to see what it does — and what it sounds like.

01

Hook

02

Tension

03

Journey

04

Reveal

05

Resolution

✕ THE MANUSCRIPT (don't present this)
Introduction →
Methods →
Results →
Discussion →
Conclusion

Correct for a paper, deadly for a talk. The audience has to hold everything in memory and assemble meaning at the end.

✓ THE ARC (present this)
Hook →
Tension →
Journey →
Reveal →
Resolution

The audience solves the problem alongside you. By the reveal, the finding feels earned — not dumped.

Step 3 · The slides

Slides are visual aids, not teleprompters.

The cardinal rule: if it can be said aloud, it does not go on the slide. The speaker provides the narrative; the slide provides the evidence. Toggle the slide below to see the fix.

Titles that argue

Not "Results." Instead: "Plasmin accelerates fracture healing at day 14." The title states the finding; the figure proves it.

Only four kinds of text

Declarative titles, axis/figure labels, key numbers (p, n, effect size), and one take-home sentence. Nothing else earns a place.

White space is confidence

Uncluttered slides feel sure of themselves. Cramped slides feel anxious. Leave room for the audience's eyes to rest.

Step 4 · Motion

Every animation must earn its place.

The test for any motion: does this help the audience understand something they couldn't understand without it? If not, cut it.

MOTION THAT TEACHES
  • Morph — shows one state evolving into another (pre-op → post-op, time-point → time-point)
  • Sequential builds — reveal data one point at a time to guide the narrative
  • 3D rotation — show spatial relationships across planes
  • Zoom — move from overview to detail, macro to micro
MOTION THAT DISTRACTS
  • Fly-in effects for bullet points
  • Spinning transitions between unrelated slides
  • Bouncing or swinging text
  • Any motion that draws attention to itself instead of the content

Morph is the power tool.

Morph creates visual continuity between slides — but only when the objects share names across consecutive slides. Mismatched names fall back to a generic crossfade, defeating the purpose. The naming convention keeps morph targets sorted at the top of the Selection Pane:

// name matched objects identically on both slides
!!MorphTarget_femur_pre   →   !!MorphTarget_femur_post
// the !! prefix sorts targets to the top of PowerPoint's Selection Pane

The cinematic timing model

Morph-heavy talks move far faster than the textbook "2 minutes per slide." A calibrated reference point: 374 slides ran in 40 minutes — roughly 6–7 seconds per slide, because each slide is a single visual beat, not a paragraph to read. The next section turns this into a calculator.

Step 5 · Respect the clock

Will it actually fit?

Finishing early beats rushing. Set your slide count and your slot; the calculator uses the cinematic calibration (374 slides ≈ 40 min) or the standard 2-min/slide model, and tells you whether you'll make it.

Cinematic: ~6.4s/slide — each slide is one visual beat. Calibrated from 374 slides = 40 min.

Estimated runtime
12:48
7 min to spare
Step 6 · The 5-Level Review

Score it before the room does.

Every talk gets reviewed at five levels before it's ready. Always start at Level 1 — a talk can look gorgeous (Level 3) and still tell the wrong story (Level 1). Check what's true; watch your readiness move.

Talk readiness
0%
Start at Level 1 — does the talk WORK?
Step 7 · AI Co-Pilot

Let AI build the scaffolding — you keep the judgment.

AI is fastest at the parts that are mechanical: drafting a deck skeleton from your narrative, polishing layout, and generating clean figures. It is worst at the part that matters most — deciding the one idea. Use these copy-paste recipes after you've answered the Three Questions, never before. Each prompt has placeholders in [brackets] — fill them in.

1 · Narrative 2 · AI draft & design 3 · Your review (5 levels) 4 · Deliver

Understand first, design second. AI never skips step 1.

Claude · text

Turn a narrative into a slide-by-slide skeleton

Use after the Three Questions. Output is a build list, not a deck — one visual idea per slide, titles that argue, speaker notes carrying the words.
You are helping me build a conference talk. Here is my plan: - AUDIENCE: [who is in the room] - ONE TAKE-HOME: [the single sentence they should remember] - WHY THEY CARE (the hook): [the patient / problem / gap] - TIME SLOT: [minutes] Build a slide-by-slide skeleton that follows a STORY arc (Hook → Tension → Journey → Reveal → Resolution), NOT a manuscript (no Intro/Methods/Results/Discussion sections). Rules for each slide: 1. A declarative title that states an argument, not a label (e.g. "Plasmin accelerates healing at day 14", never "Results"). 2. ONE visual idea per slide (a figure, a number, a diagram) — describe what it shows. 3. Put the spoken words in speaker notes, NOT on the slide. Slides hold only: title, labels, key numbers, one take-home sentence. 4. Flag where a morph transition or a build would teach something (state evolving, data revealed in steps). Return a numbered list of slides. Keep it to a realistic count for the time slot.
Then iterate: "Slide 7 has too much text — what's the single number that makes the point?"
Claude Design · visual

Polish the layout with a live visual editor

Once the skeleton is right, move to a visual tool (e.g. Claude Design) to lay it out, refine spacing and type, and export to PPTX / PDF. This closes the feedback loop that a text tool can't.
Design a [N]-slide deck from the skeleton below. Style: - 16:9, dark navy background (#0f2b46), one accent color (gold #d4a053), generous white space. - Large declarative titles; minimal body text; one figure or number per slide. - No bullet-point walls, no clip art, no busy backgrounds. - Consistent type scale; titles ~40pt, labels ~18pt. - Leave a clearly marked image placeholder on slides that need a figure. Here is the skeleton: [paste the slide list from the previous step] Export-ready for PowerPoint. Keep speaker notes intact.
Per the Claude Design workflow: build the narrative first, design second — the tool refines look, never the message.
Gemini / Nano Banana Pro · image

Generate clean, figure-driven illustrations

For mechanism drawings, anatomy, and concept figures — the kind of clean vector-style art a killer talk leans on. Generate text-free images so your slide titles do the talking.
Create a clean, professional scientific illustration for a presentation slide. SUBJECT: [e.g. a long bone fracture healing, showing callus formation at the fracture site] STYLE: minimal vector-style medical illustration, flat clean shapes, limited palette (navy, gold accent, soft neutrals), white or transparent background. COMPOSITION: single clear focal subject, centered, generous negative space, no clutter. CRITICAL: NO text, NO labels, NO captions, NO watermark in the image — the slide adds those separately. ASPECT: 16:9, high resolution. MOOD: confident, editorial, suitable for a dark slide background.
Ask for variations ("3 versions, varying the angle"), then drop the cleanest onto the placeholder from the design step. Add labels in PowerPoint so they stay editable and crisp.
Claude · text

Pressure-test the talk before you give it

A fast Level-1 review partner: paste your skeleton and let AI play a skeptical audience member.
Act as a skeptical but fair member of my audience: [audience]. Here is my talk skeleton: [paste] 1. In one sentence, what will I most likely remember 24 hours later? (If it's not my intended take-home, tell me where it got lost.) 2. Where does the arc sag — which slides are orphans that exist because the data exists, not because the story needs them? 3. What is the single toughest question this audience will ask, and where should I pre-empt it? 4. Is the opening a real hook, or a throat-clear? Suggest a sharper first 30 seconds. Be direct. I'd rather fix it now than on stage.
This mirrors the Tōge idea exactly: your draft is the intuition; the AI is the evidence-based counterpoint. The gap between them is the lesson.
The "so what"

One page. Tape it above your desk.

A killer talk ends by telling the audience what to DO. So does this module. Here is the whole method as a pre-talk checklist — download it and run it before every talk.

  • Who is in the room? — depth, tone, and call-to-action all follow from this.
  • One take-home sentence — if I can't say it in one breath, the talk isn't ready.
  • A real hook — a patient, a problem, a gap the audience already cares about.
  • Story arc, not manuscript — Hook → Tension → Journey → Reveal → Resolution.
  • Slides are visual aids — if it can be said aloud, it's not on the slide.
  • Titles argue — every title states a finding, not a label.
  • Motion earns its place — morph and builds teach; fly-ins and spins distract.
  • It fits the clock — checked against the slot, with time to spare.
  • Reviewed at 5 levels — Strategic → Content → Design → Motion → Assets.
  • Ends with "so what" — the audience knows exactly what to do next.
Back to top

"The slides are the last thing you build. The narrative comes first."

— The Tōge presentation method