Build a slide deck
Slides & Talks
Set the topic, audience, slide count and structure, and get a deck you can export as PPTX.
Fill the blanks and it copies as you filled it
[Paste your source material — upload a file if it's long] Build a deck on . - The occasion: - Who's listening: - Twelve slides or fewer - Sound like a working researcher, not a marketer. No overselling - Order: title / problem and background / the main points / data and evidence (a chart or table) / conclusion and next steps. Add or drop as needed - For my voice: [paste two or three paragraphs I wrote before — delete this line if you have none] - Keep the first and last slides short, I'll rewrite those - Make it exportable as PPTX
0 of 3 blanks filled · anything left blank copies with its brackets
Giving it a couple of paragraphs you actually wrote is what keeps the deck from sounding like a brochure.
What this prompt does
Compared with asking the same thing without the length and format lines.estimate
Estimated output tokens
700
Asked loosely
320
This prompt
Energy (Wh)
1.215
Asked loosely
1.215
This prompt
Token counts are estimated from character counts, not measured. Energy uses the per-band figures measured by Jegham et al. 2025 as published.
A shorter answer, but the same energy band. The measurements are per band, and this much does not cross one.
Reported backfire — Specifying output lengthSpecifying a length longer than needed backfires (a 34% increase in 11% of scenarios)
Where these figures come from
We read the prompt to see whether it carries that instruction. The percentages below are published figures for the rule itself, not a measurement of what this prompt saves.
Assigning a role
44%mean reduction · 95% CI 29–59%
Podder et al. 2026 BP#4 · 19 use cases / 61 prompts
by modelGPT-4o 34%Command R+ 50%Mistral-7B 49%
Specifying output length
38.7%mean reduction · 95% CI 29.7–47.7%
Podder et al. 2026 BP#5 · 18 use cases / 57 prompts
by modelGPT-4o 35%Command R+ 49%Mistral-7B 32%
Reduced in every scenario. No backfire reported