Skip to main content
The Human Bit
Ask Bit
← All playbooks

Practical playbook · comfortable · 30 minutes

Create a presentation from source material

Turn the notes, documents and data you already have into an editable first deck, while the argument and the evidence stay in your hands.

This is for you when
The thinking is all there, spread across notes and files, but the storyline and the slide order are still a mess.
What you will leave with
An editable draft deck with a storyline that holds together and source material you can trace back.

The Human Partnership

Use the capability. Keep the part that needs a person.

Presentation generation is valuable when it removes production work without outsourcing the argument. The person must still decide what the audience needs to believe, understand or do.

AI contribution

Choose a capability for a real job.

Each capability removes a different kind of effort. Its value depends on the human context beside it.

01 · capability

Multi file synthesis and storyline drafting

AI can read notes, reports, spreadsheets and a previous template, then propose a slide sequence that connects the evidence to the intended decision before designing the deck.

The person contributes
The person chooses the governing message, identifies the audience's existing knowledge and decides which tension or decision deserves the limited presentation time.
Do not assume
A coherent storyline can still be generic, politically naive or aimed at information transfer when the real job is alignment, challenge or approval.
02 · capability

Editable presentation and document creation

File creation features can produce PowerPoint, Google Slides or other editable drafts with speaker notes, tables and source material already organised for revision.

The person contributes
The person protects the organisation's template, chooses what belongs on the slide versus in speech, and rewrites anything that sounds unlike the presenter.
Do not assume
Generated files may contain layout defects, weak hierarchy, unsupported filler or formulas and charts that do not update as expected.
03 · capability

Charting, visual concepts and critique

AI can create a first chart, suggest diagrams, identify crowded slides and critique whether the evidence supports the stated takeaway.

The person contributes
The person chooses the truthful visual encoding, removes decoration that competes with the message and decides whether a chart clarifies or overstates the evidence.
Do not assume
A polished visual can imply precision, causation or certainty that the underlying data does not support.

Human expertise

The resources already inside the work.

Experience, relationships, definitions and accountability are inputs to the workflow, not a final check after AI has finished.

Strategic intent

You know the decision, behaviour or conversation the presentation must create, not merely the information it should contain.

Audience dynamics

You know what the room already believes, where resistance may appear, which context can be spoken rather than displayed and who needs to feel heard.

Narrative accountability

You decide what evidence is strong enough for the claim, what must be disclosed, and whether the deck presents uncertainty honestly rather than selling a conclusion too hard.

Shared workflow

See where the work changes hands.

The useful pattern is not one prompt followed by one check. The person and AI shape the work at different moments.

  1. 01 · person

    Set the job of the room

    Define the audience, speaking time, desired decision and the one idea that should remain after the slides are closed.

  2. 02 · ai

    Propose the argument before the deck

    File synthesis, outline generation and source mapping

    Read the approved source pack and return only a storyline, slide purpose and source map so the person can challenge the logic before file generation begins.

  3. 03 · together

    Build and challenge the first deck

    Generate an editable draft, then remove generic filler, test the strongest counterargument and revise charts, emphasis and sequence around the real audience.

  4. 04 · decision

    Choose the message and the ask

    The presenter decides which evidence leads, what is omitted, how uncertainty is framed and what the audience is explicitly being asked to decide or do.

  5. 05 · verification

    Verify the deck and rehearse the room

    Check every number and claim against its source, inspect the editable file, test links and charts, and rehearse aloud to find slides that do not support the spoken argument.

The decision stays human

Someone must be able to stand behind the result.

The presenter owns the argument, the ethical use of evidence, the final ask and the delivery. AI can accelerate synthesis and production, but it cannot read the room or take responsibility for persuading people with a misleading story.

Verification required

  • Trace every material claim, quotation and number to the exact source used.
  • Check chart scales, denominators, labels and comparisons for visual distortion or unsupported precision.
  • Open the generated file in the target presentation software and inspect layout, fonts, formulas, notes and accessibility.
  • Rehearse within the actual time and remove slides that do not help the audience understand or decide.

Failure to watch

The main failure is persuasive polish without earned meaning. A generated deck can look board ready while carrying the wrong denominator, a generic storyline or an ask that ignores the relationships and history in the room.

Skill strengthened

Strategic communication

Used well, the workflow strengthens argument design, evidence selection, visual judgement and the ability to adapt a message to a specific room without losing truth or clarity.

Worked example

Watch the judgement change the draft.

The first pass is useful. The human correction is what makes it specific, appropriate and worth using.

01 · Input

The honest starting point

Monthly metrics, project notes and the previous board-deck template for a ten-minute operating review.

02 · AI draft

A useful first pass

A seven-slide storyline: result, drivers, customer evidence, delivery risks, decisions required, next month and appendix.

03 · Human correction

Context changes the answer

The manager cuts a vanity metric, fixes a churn figure that had used the wrong denominator, and moves the decision the board actually needs to make up to slide two.

04 · Final result

The version a person can stand behind

A tight seven-slide review pack with source notes attached, one decision per section, and figures that have each been checked.

Try it on your work

Start with the real material.

Remove anything you cannot share, fill in the brackets and keep the decision and verification steps visible.

  • Do not expect a deck with a point of view unless you supply the point of view and review the result.
  • Never put a claim or a figure on a slide that you have not checked against the source, because a clean, confident-looking deck is exactly what an audience reads as trustworthy, and a wrong number travels every time it is forwarded.
  • Do not treat the first generated deck as done: build the truth layer first, a note of which claim rests on which source and which numbers are still assumptions, and it helps to have a second tool argue against the draft before it leaves your desk.

Use these files to propose a [length]-slide presentation for [audience]. The outcome I need is [decision or action]. Start by showing only the storyline, the job of each slide and the source material each slide would use. Keep source facts traceable and mark missing evidence. Wait for my approval before drafting the full presentation.

Tools that can support this

Pick the tool after the job is clear.

These are evidence backed starting points, not universal winners. Open a guide or ask Bit to help you weigh the fit.

ChatGPT

Its reviewed ChatGPT Work guidance covers longer tasks that end in an editable presentation.

inferred · moderate confidenceSee why it may fit →Kimi

Its reviewed guide includes Slides and workflows that run across large mixed file sets.

inferred · moderate confidenceSee why it may fit →Claude

Its reviewed Cowork guidance covers multi-file work that ends in editable deliverables.

inferred · moderate confidenceSee why it may fit →

Keep going

Build the next useful skill

Reviewed
Review by
Owner
The Human Bit editorial

The Human Bit Weekly

The useful changes, not every launch.

One short issue every Monday. What changed, what it means for your work, and the part that stays yours.

The Human Bit records when and how consent was given. Subscription is confirmed only after the email provider accepts the request.