Automating calendar tasks

Jan 20

Just used Gemini Enterprise chatbot to create 32 calendar invites from a spreadsheet. Someone else creates this spreadsheet for the meetings but usually I have to manually make the calendar invites.

This time around, I thought...maybe the machine can do this for me.

and wow!

My UC Berkeley Spring Capstone meetings are now sent out. It took about 3 minutes to process 4 invites (each team) so not lightning fast but it didn't make any mistakes and made this task much easier since I supervised rather than did the work.

It worked well on one team's data at a time and then I managed to get it to process two teams in one dataset and prompt.

I used a simple prompt:
can you make a calendar invite that it titled "Team NUMBER - 270K Session" where you replace "NUMBER" with the number in the first column of the data I'm pasting. Then add all the emails from each row. Then create one invite for each of the dates in the last column of the data using the start/end time in the row. Only one calendar invite per date per number in the first column of the data. then add all the emails. Make sure it has a Google Meet video conference in the invite turned on.

The AI-Enhanced Product Manager

Featured

Searching in the content of images

"What can AI do for you?"

For example, I have hundreds of handmade drawings I created to explain PM concepts. Searching for them is super annoying. The Mac Spotlight search usually can't even find files by keywords in a filename (another fail for Apple "Intelligence").

So I vibe coded an image search. In less than 2 hours of chatting/prompting (over a couple days), I created a fully functional image search.

Automating calendar tasks

SF AI Hackathon

I hosted the Supra AI Hackathon last night in SF. Thirty (30) non-engineers gathered to bang on the keyboard and turn ideas into interactive apps in two hours.

So many interesting creations from teaching kids abstract concepts to simplifying youth softball rosters to tracking subscriptions by scanning an email inbox and more!

Getting Started with AI Coding

AI tools are not one-size-fits-all.

I’ve categorized the AI coding tools to help you get started: AI-assisted coding, “Vibe” coding (coding by chatting), No code.

The AI Turning Point

Writing code was once a sacred art to us software engineers.

Somehow I had it in my mind that machines made of code would never write code.

I even nudged my kids toward computer science.

AI “Mom Test” Interview Script Creator

Use my AI "Mom Test" interview script creator to reduce the friction of finding and interviewing customers.

Enter a few fields into a form and then the magic happens and an interview script is created and sent.

Types of AI Product Managers

AI is transforming the role of the Product Manager.

From casual experimentation to building custom models, new archetypes are emerging that reflect how deeply a PM integrates AI into their work.

This article explores AI Product Manager roles and what success looks like for each: AI Builder PM, AI Experiences PM, AI Enhanced PM, AI Curious PM

Fear AI Flattery, not its Hallucinations

AI blinds us by flattering us.

This goes deeper than pleasantries.

When we ask AI for help, we also give it our assumptions.

Our assumptions magically become facts when these words are sent back to us in the AI response.

How AI is like a Dishwasher

AI is the new dishwasher

It's come with the hype, the skills and the limitations.

Certainly, AI exceeds dishwashers on most accounts but will it provide the benefits it touts?

AI Side Effect: Human Scope Creep

I used AI to get a head start. But in the end, I created a monster.

With AI, even the simplest idea can turn into a gothic nightmare.

But we can’t totally blame the AI for this resulting scope creep.

AI Disobedience

The joy of most AIs is their surprising skill at answering most any question.

We get used to this success. So when an AI fails to do something, it’s disappointing.

AI folks call this a failure of “Instruction Following”. I call it disobedience.

How to Keep AI from Going Off the Rails

Sometimes an AI response feels written by a high schooler; other times, a seasoned Product genius.

How we can coach an AI to be more consistent in its first response?

This article will focus on creating and using a persistent set of instructions for accomplishing a specific task.

AI Ideation, Laziness, and Wrapper AIs

An idea is not enough to build an app. So we write up the details.

This initial document is the starting point … call it a “spec”, specification, requirements doc, “1 pager” … it goes by many names.

In this article, I’ll outline how AI creates an initial specification document incredibly fast from a raw idea and how to use a “wrapper AI” for niche-specific tasks.

Dictation and Conversation with an AI

With AI chatbots, we can skip the step of crafting keywords and just type what comes to mind in a stream of consciousness.

These chatbots deal with spelling mistakes, grammar mistakes and don’t require as much forethought when we interact with them.

So as I started thinking about my app I went straight to voice mode where I could ramble a bit and trust that the AI would organize my thoughts.

Jim coaches Product Management organizations in startups, growth stage companies and Fortune 100s.

He's a Silicon Valley founder with over two decades of experience including an IPO ($450 million) and a buyout ($168 million). These days, he coaches Product leaders and teams to find product-market fit and accelerate growth across a variety of industries and business models.

Jim graduated from Stanford University with a BS in Computer Science and currently lectures at University of California, Berkeley in Product Management.

The AI-Enhanced Product Manager

Jim Morris

Automating calendar tasks

The AI-Enhanced Product Manager

Searching in the content of images

Feedback is a gift