Kelly Huang

Author: kelly huang

  • How I Created 20 Pages of PowerPoint Notes in Under 60 Minutes

    In conclusion:

    1. Create an empty online meeting. Start meeting, start transcription.
    2. Present. Before advance to the next slide, say “next page”.
    3. End the meeting and download the transcript. Check the spelling of terminologies.
    4. Use the prompt to clean up the transcript.
    5. Check copy, paste to the slide notes.

    The prompt for step 4.

    You are a professional presentation coach specializing in converting meeting transcripts into polished PowerPoint speaker notes.

# TASK
Convert the provided meeting transcript into speaker notes for a PowerPoint presentation. The transcript contains verbal slide separators that define slide boundaries.

# CONFIGURATION PARAMETERS
- Speaker Notes Format: mixed (conversational intro + bullet points)
- Context Addition: all (technical expansion, transitions, why it matters)
- Length Target: moderate (~1 minute per slide, 150-200 words)
- Target Audience: dealers_integrators
- Slide Separator Phrase: "next page"

# TRANSCRIPT INPUT
[paste your transcript here]

    There are few assumptions this is based on:

    1. It’s easier to say it than to write.
      This is the purpose of empty meeting transcription.
    2. AI has more knowledge than I do.
      This is the purpose of the prompt, use it to clean and refine the context.
    3. I own the slide outline, not AI.
      This is the reason to say “next page”.
    How-I-Created-20-Pages-of-PowerPoint-Notes-in-Under-60-MinutesDownload

  • Goals, system, theme

    Words I constantly saw on YouTube title during the New Year: goals, habits, system, and theme.

    This post is to interpret their differences.

    Goals

    The milestone we look to achieve, such as loosing 5kg, running sub-60 10K, summer vacation to Thailand.

    The key to execution is to be as clear as possible. Instead of “Summer vacation to Thailand”, write “One week of vacation in Bangkok, Thailand”.

    System or habit

    The execution, the steps to move toward the goals.

    • Loosing 5kg: calculating the calorie, sign up for the gym.
    • One week of vacation in Bangkok: ask LLM to estimate the budget and plan, save $3,000 each month, buy plane ticket once it reaches $10,000.

    The key to execution is to automate and remove the distraction.

    • If it has to do with money, put it on the to-do list on every paycheck day or setup transfer automatically.
    • Create check points
      • If it has to do with money, then give the milestone a clear amount.
      • If it is an ongoing timeline, then setup reminder every 30 or 90-days.

    Theme

    The focus, to make sure the goal or goals create synergy and not do too much.

    Try to get promoted at work and taking 3 family trips probably won’t work well together.

  • Overdoing and anxiety

    Every time I press the Post button on LinkedIn, my stomach cramps.

    • This is stupid.
    • I’m a joke
    • It’s embarrassing

    It takes days for the stress to fade. Maybe I have not trained enough bias muscle resistance.

    At any kind of work, from business to exercise, there are good days and bad days. Then there are good weeks and bad weeks.

    The trap I set for myself is to modifying the intensity without a plan. Original plan was one post every 2 week. I had a few good writing days during the first 2 posts so I changed it to weekly without a good intention.

    The problem is trying to match the intensity in bad days and weeks. It stretches the time too thin.

    Adjustment: go back to the system

    The system I created is to write from 1pm to 1:30pm daily, on a to-do app.

    If I’m on a good day, then I can work one more pomodoro count.

    But the baseline is to follow system, don’t let emotion deviate the execution.

    Create 30 is the time block for writing, it will occasionally delay, but the basic duration is always 30 minutes.

  • Sunk cost of over-research

    The more research time I invest, the harder it became to let go of the idea. Letting go would erase the time and effort I have spent. Therefore,

    • I would argue with LLM.
    • I would add more factors, product comparison, criteria to LLM.
    • I would ignore it’s result.

    Gear often matter very little in the making of a story, at least at the very start. This is often a sign that I’m stalling, while I should be working.

  • Keep Going by Austin Kleon

    7

    The only creative journey I seem to go on is the ten-foot commute from the back door of my house to the studio in my garage.

    10

    Creative life is not linear. It’s not a straight line from point A to point B. It’s more like a loop, or a spiral, in which you keep coming back to a new starting point after every project.

    11

    Daily practice – a repeatable way of working that insulates them from success, failure, and the chaos of the outside world.

    32

    When the sun goes down and you back on the day, go easy on yourself.

    66

    Job titles…will make you feel like you need to work in a way that befits the title, not the way that fits the actual work.

    90

    If you share work online…increase the time between your sharing and receiving feedback.

    95

    If you’re bummed out and hating your work, pick somebody special in your life and make something for them.

    97

    “What I’m really concerned about is reaching one person.” — Jorge Luis Borges

    104

    Everything you need to make extraordinary art can be found in your everyday life.

    127

    The world doesn’t necessarily need more great artists. It needs more decent human beings.

    154

    WHEN IN DOUBT, TIDY UP.

    Note that it says “when in doubt”, not “always.” Tidying up is for when I’m stalled out or stuck.

    166

    Art is also made out of what is ugly or repulsive to us.

  • Over-research

    The story: I bought an Insta360 Ace Pro 2 and I fell for the marketing. It’s laughable because I work in the video industry as product marketing.

    It was a decision between DJI Action 5 Pro and Insta360 Ace Pro 2. The facts I over researched and end up persuaded myself:

    1. It has a better editing software.
      Fact: iMovie is easier.
    2. Windguard provides better sound clarity.
      Fact: still captures the surrounding sound.
    3. Better nighttime image quality.
      Fact: there’s just so much you can do with slow shutter speed in low light.
    4. Has a Leica co-branding, I could replace my Ricoh GR II.
      Fact: just a little bit.

    The quick thought on the other hand:

    1. DJI just released Action 6 Pro and Action 5 Pro is on discount.
    2. Claude recommended DJI Action 5 Pro.
    3. Perplexity recommended DJI Action 5 Pro.

  • Image inversion with Gemini 3 Nano Banana Pro

    Here’s a thought I had:

    If Gemini 3 Nano Banana Pro is the best at generating images, can I use it to reverse engineer images? Then use that to create a different style of image?

    I was working on a face recognition terminal and this key visual from Hikvision caught my eye.

    There’s no way I could design this. It would take hours of research to know how to describe it.

    Here’s the prompt I gave Gemini.

    If this was generated by a prompt, what are the possible prompt and key elements that describes it?

    See the full Gemini prompt

    And this way the final image a generated from Gemini’s recipe. It’s mirrored so I have the option to use either side.

  • Software and hardware companies

    This is a biased point of view. It is biased because most of the companies I worked for are hardware oriented or started with hardware. They are also large corporations.

    An observation that I derived with a friend was it’s more likely for software company to succeed in hardware versus hardware company in software. Great rise of hardware companies transforming to solution selling companies, for higher margin, and most have failed.

    Here’s the answer, man versus the machine

    Our reasoning

    • User centric vs product centric. Software development involves more UX consideration, that habit system creates relatable hardware. It’s not easy for a hardware company to adopt this from ground up.
    • Margin structure. Software companies have lower cost and more consistent cashflow from ARR. This would provide steadier runway and the mindset to add premium to cost and price. Hardware companies have less margin to burn through, the cashflow is limited to stock and distribution.
    • Time. It’s faster for hardware companies to gain revenue traction: manufacture and sell in channel. Software requires time to generate, convert, and sustain users. Hardware company owner needs to be patient.
    • Revenue acceleration slope. Selling hardware brings large revenue and small margin. Software, at an early stage, has small revenue and needs time to pile up. Owner needs to be patient.

    Reply from Claude, Opus 4.5.

  • Dirty work of NDB pipeline

    During the lunch meet, we shared our experience working in a new business unit in a large corporation. The common trait we found was the lack of pipeline and prove of business. Most activities circles around product development.

    That’s not new, but what’s the takeaway?

    If I was given the opportunity, how do I enable business development?

  • Two folder layering of SharePoint document sets

    SharePoint document set has a limitation: two document sets can’t layer naturally and metadata is encouraged.

    This enforced a hard coded rule: top layer folder -> one layer document sets plus metadata columns -> files.

    From a product dev point, this is a tough feature limitation to make, considering the audience of Office and Windows are accustomed to multiple folder layers.

    In the implementation phase, I learned to be extra curious for both motive and detail in order to keep the boundary.

    • How do you plan to manage keep duplicate files up to date?
    • If the folders are deleted periodically, then what happens when users want to find old documents?

    I know about the metadata and web apps that users are less likely to, I am responsible to help them get around.