Felo Slides on Grok BotGrok Bot

A Bot can deliver the deck. The outline is what you still have to agree with.

Grok Bot has its own working computer, so producing the file is not the problem. Felo Slides gives you the argument first, as an outline built from the research the Bot already gathered, so the deck you approve is the one you asked for.

Built for Grok BotOutline before exportRuns from the thread
Get an API keySee the platform guide
The request that saves the methodSave the process as a skill called "Monthly briefing deck". Outline first, one line per slide, and wait for my approval before exporting.
Grok Bot logo
This skill runs on

Grok Bot

Durable AI teammates by SpaceXAI

Read the Grok Bot guide

A Grok Bot owns a job, a conversation and a schedule, and a skill is the method it runs. Felo skills are the research half of that loop, saved once and reused by every routine.

Core units
Bot · skill · routine
Skills come from
A saved run, or Settings → Plugins → Yours
Runs on
iPhone, Android, and desktop
Add it on Grok Bot

Learn it from one deck you actually approve

The useful method here is not "make slides" — it is your house shape: outline first, approval, then export. Run it once with that shape and save it.

  1. Run

    Give one Bot a real job

    Give one Bot the briefing job and run the research inside it, so the deck has something real to summarise rather than a topic.

  2. Save

    Ask it to record the method

    Ask for the outline, argue with it, approve it, then export. Save the process afterwards and say explicitly that the outline comes before the export.

  3. Enable

    Turn the skill on where it is needed

    Enable the skill for the Bots that present work, and keep it off the ones that only answer questions. A deck is a deliverable, not a reply.

  4. Schedule

    Attach a routine, then read the first run

    Attach a monthly routine for recurring briefings. Keep the headings stable so the audience reads the figures that changed rather than the redesigned slides.

What you get back

An outline you can approve before a file exists

The point of asking for the outline first is that it is cheap to change. Once the Bot has exported a deck, every correction costs a regeneration, and the reviewers have already seen a version you did not intend.

  1. 01

    Why we are looking at this now

    The trigger, stated once, so the deck is not read as a routine status update.

  2. 02

    What the research found

    The three findings that changed the picture, each with the source and date in the notes.

  3. 03

    What we expected and did not see

    The hypothesis the data refused, which is usually the most useful slide in the deck.

  4. 04

    What it costs

    The numbers, in the format the audience budgets in, with the measurement window named.

  5. 05

    What we recommend

    One option, the cost of being wrong, and how the decision would be reversed.

  6. 06

    What we need from you

    The decision, the owner, the date — and what happens if the answer is no.

Keep the source list in the speaker notes when the deck is exported. The audience reads the number; the presenter is the one who gets asked where it came from.

The routine

Research, outline, approve, export

Four steps and one gate. The gate is the part that makes a Bot-generated deck safe to present.

Runs when

A recurring briefing that somebody has to present, or a one-off deck built from research the Bot has already done.

  1. 01

    Let the research happen first

    A deck built from a topic is a template with words in it. Build it from the findings instead, with the sources still attached.

  2. 02

    Ask for the outline and read it properly

    Six headings, one line each. This is the last moment when changing the argument costs nothing and embarrasses nobody.

  3. 03

    Approve explicitly

    Say which slides go and which do not. An approval that consists of silence is how a deck ends up presenting a recommendation you never made.

  4. 04

    Export with the sources in the notes

    The Bot has the computer and the file handling; the notes are what let the presenter survive the first hard question.

Leaves behindA deck that follows the argument you approved, with the sources carried into the speaker notes.

Where it goes

Three destinations, decided before the export

The Bot can save and share files; what it should not do is guess where a deck belongs.

The thread

Outline

Review it in conversation, where changing your mind is a message rather than a regeneration.

Files

Exported deck

The Bot's own computer writes the file. Naming the folder up front saves hunting for it later.

The meeting

Presented slides

Export last, after the argument settles, and keep the approval boundary on anything that leaves the account.

Check it worked

Three checks before the deck is presented

A generated deck is confident by default, so the checks are about where each claim came from.

1

The outline you approved is the deck you got

Compare the two. Drift between them is the most common failure, and it is invisible unless you look.

2

Every figure has a date

A number without one is a number from an unknown quarter. The research behind the deck should still show its dates.

3

The recommendation is yours

Read the last two slides and check that they say what you decided, not what the method defaulted to.

FAQ

What Grok Bot users ask about Felo Slides

Can a routine produce a deck every month unattended?
It can, and it works best when the headings are fixed and only the figures change. A deck that is redesigned every month makes the audience read the layout instead of the change.
Should the Bot export without asking?
For a first run, no. The outline is where your judgement enters, and a Bot that skips it will confidently present a recommendation you did not make.
Does the deck stay inside Grok Bot?
The file is produced by the Bot's computer. Anything that leaves the account should sit behind the approval boundary you set in the description.
How long should the deck be?
Shorter than the first draft. Six headings that follow the argument beat fifteen that follow a template, and the outline stage is where that is cheap to fix.
More on Grok Bot

Every Felo skill for Grok Bot

Five skills written for Grok Bot. They follow the same pattern on this platform, so you can combine them in one session without re-explaining your setup.

Beyond ready-made skills

One API key. A full agent toolkit.

Start with a skill, then compose the exact models, live data, knowledge, and output tools your Grok Bot workflow needs — the same key every Felo skill already uses.

Models

Use cost-efficient LLM access when your agent needs custom reasoning or generation.

  • LLM API
  • Chat completions
  • Model access
Explore LLM API →

Live information

Give agents current web and social signals instead of relying on stale context.

  • Web Search
  • X Search
  • Web Fetch
Explore live data tools →

Knowledge and output

Ground work in reusable knowledge, then turn it into shareable deliverables.

  • LiveDoc
  • PPT generation
  • Mindmaps
Explore knowledge tools →

Creative tools

Extend the workflow from research to visual and office-ready results.

  • Image generation
  • Page tools
  • Office outputs
Explore platform tools →