March 7, 2024 • 9 mins
In this unique episode of AI Meets Productivity, we turn the spotlight on our co-host, Trevor Lohrbeer, by having ChatGPT interview him.
During the interview, ChatGPT explores his work at the intersection of AI and productivity, getting Trevor to share insights on productivity and what he is doing to create new user experiences with large language models, including the upcoming launch of his GPT Builder Toolkit platform.
Take a listen to learn about GPT Builder Toolkit and its upcoming features. GPT Builder Toolkit is a no-code solution for adding actions to custom GPTs, supporting features like swappable prompts, user authentication and user data.
Find out more at https://gptbuildertoolkit.com/
BEHIND THE SCENES
This episode was created by crafting special prompts that extended the custom podcast co-host GPT usually used for this episode into an expert podcast interviewer. Given only a short bio about Trevor, ChatGPT wrote Trevor's introduction and all questions asked during this podcast.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
(00:00):
Welcome to AI Meets Productivity,
your weekly podcast co-hosted by myself,
ChatGPT. Today's episode is going to be a bit different.
A few people have emailed asking to be guests on this podcast.
So to experiment with how well I can interview, today
I'm going to interview my co-host Trevor Lohrbeer.
Today we're joined by Trevor Lohrbeer,
(00:21):
a seasoned entrepreneur with over two decades of experience in founding and leading innovative internet and software startups.
Currently,
he's at the forefront of integrating AI into productivity,
exploring unique user experiences with large language models and enhancing daily planning with his tool Day Optimizer.
Welcome,
Trevor.
(00:42):
Thank you, GPT,
it's great to be here.
Trevor, with such a rich background in AI and productivity,
I'm curious, what personal productivity techniques do you find most effective for managing your wide array of projects and interests?
So, I think the technique that I find the most effective is the CASE day planning method,
(01:04):
which is a way of doing time blocking. CASE stands for Commit, Allocate, Schedule and Evaluate. And basically you commit to what you need to do,
you allocate time to everything that you committed to you,
then schedule it on a schedule and then you evaluate that schedule to make sure it aligns with your priorities.
So that technique is a thing that
(01:25):
I think I have found the most effective in juggling multiple priorities.
Oh, the CASE day planning method sounds incredibly structured and practical.
When you evaluate your schedule against your priorities,
what criteria do you use to decide if something truly aligns with your goals?
(01:46):
And have you had to make significant adjustments based on this evaluation?
Yeah.
So I'm often thinking about, is this thing that I'm gonna do going to move me closer to my goal or is it just something that I'm gonna check off my list?
So that idea of moving closer to my goal is I think an important aspect of it.
(02:06):
And definitely I've had situations where I put together a daily schedule and then looked at that and like,
ah,
that's not exactly what I want my day to look like.
And so then I go and I remove things from that schedule and I rework it until it feels like the right schedule
that's gonna move my projects forward.
That's such a dynamic approach to productivity,
(02:27):
really focusing on what moves the needle forward for your goals.
Trevor,
I was curious about the challenges you faced while developing novel user experiences for interacting with large language models.
Could you share a particularly tough problem you've encountered and how you approached solving it?
(02:50):
Well,
I think the most challenging problem is explaining to others how these new features can work because the concept of an AI chatbot is so new,
the full range of capabilities haven't really been explored.
And so things like being able to log into your chatbot,
being able to save data into your chatbot, having different prompts,
(03:13):
you can switch into having your chatbot being able to take actions.
These are all things that we're just starting to explore.
And so there's a lot of integration challenges around that.
That's fascinating,
especially the aspect of integrating such advanced functionalities into chatbots with these integration challenges.
(03:34):
How do you prioritize which features to develop first?
And how do you envision these capabilities evolving to change the way we interact with AI in our daily lives?
So I'm looking first in the use case and then kind of working backwards and saying,
OK,
what capabilities are required to support that use case.
(03:55):
So, for instance,
I came up with the idea the other day to create a feedback GPT.
And the idea is instead of a contact form on your website,
you can actually have a little mini chatbot that asked for feedback.
But the key thing there is these online forms today,
they email you with the details.
Well,
(04:16):
that means the chatbot needs to be able to email you too.
It can't just that information can't just disappear.
And so that made me think.
OK,
we need an ability to have a chatbot who can email the details at the end of a conversation to someone to say,
hey,
this is a feedback someone gave or this is the contact form that someone filled out.
(04:36):
Here's the information.
Wow.
A feedback GPT
sounds like a game changer for interactive and engaging customer feedback.
Incorporating the ability for a chatbot to send emails
adds a whole new layer of functionality. As you work on these groundbreaking features,
what are some of the hurdles you've encountered in ensuring these capabilities are user friendly and secure,
(05:00):
especially when handling personal information like email addresses.
So yeah,
actually security is an important aspect of what I'm thinking about.
So I've done a lot of work to make sure that the passwords,
the way you connect to the GPT or to the API from the GPT,
everything is as secure as possible and then limiting things, like for instance,
(05:25):
for the mail function,
ensuring that someone can't just put anyone's email address and spam people,
it has to go to a designated email address.
So the idea is (05:33):
if someone's filling out this form on your website,
it goes to the owner of the website.
Likewise,
if someone's going to use a chatbot to fill out the form on the website,
then it should go to the owner of the website.
There shouldn't be the ability to randomly send emails to people through a GPT.
I think that would open up a can of worms that would introduce too much spam and too much scams out there.
(05:58):
That's a really thoughtful approach to balancing innovation with security and usability with the upcoming release of the GPT Builder Toolkit.
What are some of the unique features you're most excited about?
And how do you think it will empower users without coding expertise to create their own advanced chatbots?
(06:21):
Well,
as I mentioned before,
I think that the swappable prompts are really powerful.
They're going to allow people to create these meta GPTs that have multiple prompts that can—that the GPT can switch between to provide a more expert guidance in specific areas.
I like the user authentication.
(06:42):
I think that's gonna be really powerful.
The ability to actually log into a GPT and save information,
the ability to save your user data and retrieve the user data to create like to do list applications,
flash card applications,
et cetera.
And then the email capabilities I just described,
(07:03):
I think are going to be pretty powerful as well,
that ability to create a chatbot that's taking information from the user.
And at the end summarizing that and then emailing that to someone as a way of providing a much better experience than a typical contact form on the website.
Those features truly sound groundbreaking, Trevor,
especially the idea of swappable prompts and user authentication to enhance the personalization and utility of chatbots. As we're approaching the end of conversation.
(07:33):
do you have any closing thoughts or advice for our listeners who are eager to explore the intersection of AI and productivity themselves?
I think the thing that I always recommend people to do is to get a subscription to ChatGPT, or to Claude, or one of these AIs,
so you're starting to work with the most advanced technology and learn how to use it because it's not something that's going to come overnight.
(08:02):
And it's not something that we have best practices out there yet.
They're starting to be developed,
but we're in the process and each new generation introduces new things that we can do with it.
And some of the old things we're going to have to forget.
You know,
the prompt engineering we do today is not the same as we did a year ago or two years ago.
So making sure that you're working with this technology on a daily, weekly basis.
(08:25):
So you learn it,
you develop an intuitive sense of it, I think is critical.
That's invaluable advice,
Trevor, emphasizing the importance of hands-on experience and adaptability in this rapidly evolving field.
Thank you for sharing your insights and experiences with us today.
It's been incredibly enlightening. Before we wrap up,
(08:48):
could you let our listeners know where they can find more about your work and the GPT Builder Toolkit.
Certainly,
the GPT Builder Toolkit can be found at gptbuildertoolkit.com.
And if anyone has any feedback,
questions,
comments about the GPT Builder Toolkit or anything else I'm doing,
they can email me at trevor@fastfedora.com or trevor@dayoptimizer.com.
(09:14):
If they're interested in the Day Optimizer digital day planner,
you can find that at dayoptimizer.com.
Thank you for listening.
This has been AI Meets Productivity,
your weekly podcast hosted by myself,
ChatGPT and Trevor Lohrbeer,
a productivity expert.
Find us on Apple podcasts and Spotify.
If you like this episode,
(09:34):
please give us a review.
It really helps others to find and listen to the podcast,
talk to y'all next week.
Welcome to AI Meets Productivity,
your weekly podcast co-hosted by myself,
ChatGPT. Today's episode is going to be a bit different.
A few people have emailed asking to be guests on this podcast.
So to experiment with how well I can interview, today
I'm going to interview my co-host Trevor Lohrbeer.
Today we're joined by Trevor Lohrbeer,
(00:21):
a seasoned entrepreneur with over two decades of experience in founding and leading innovative internet and software startups.
Currently,
he's at the forefront of integrating AI into productivity,
exploring unique user experiences with large language models and enhancing daily planning with his tool Day Optimizer.
Welcome,
Trevor.
(00:42):
Thank you, GPT,
it's great to be here.
Trevor, with such a rich background in AI and productivity,
I'm curious, what personal productivity techniques do you find most effective for managing your wide array of projects and interests?
So, I think the technique that I find the most effective is the CASE day planning method,
(01:04):
which is a way of doing time blocking. CASE stands for Commit, Allocate, Schedule and Evaluate. And basically you commit to what you need to do,
you allocate time to everything that you committed to you,
then schedule it on a schedule and then you evaluate that schedule to make sure it aligns with your priorities.
So that technique is a thing that
(01:25):
I think I have found the most effective in juggling multiple priorities.
Oh, the CASE day planning method sounds incredibly structured and practical.
When you evaluate your schedule against your priorities,
what criteria do you use to decide if something truly aligns with your goals?
(01:46):
And have you had to make significant adjustments based on this evaluation?
Yeah.
So I'm often thinking about, is this thing that I'm gonna do going to move me closer to my goal or is it just something that I'm gonna check off my list?
So that idea of moving closer to my goal is I think an important aspect of it.
(02:06):
And definitely I've had situations where I put together a daily schedule and then looked at that and like,
ah,
that's not exactly what I want my day to look like.
And so then I go and I remove things from that schedule and I rework it until it feels like the right schedule
that's gonna move my projects forward.
That's such a dynamic approach to productivity,
(02:27):
really focusing on what moves the needle forward for your goals.
Trevor,
I was curious about the challenges you faced while developing novel user experiences for interacting with large language models.
Could you share a particularly tough problem you've encountered and how you approached solving it?
(02:50):
Well,
I think the most challenging problem is explaining to others how these new features can work because the concept of an AI chatbot is so new,
the full range of capabilities haven't really been explored.
And so things like being able to log into your chatbot,
being able to save data into your chatbot, having different prompts,
(03:13):
you can switch into having your chatbot being able to take actions.
These are all things that we're just starting to explore.
And so there's a lot of integration challenges around that.
That's fascinating,
especially the aspect of integrating such advanced functionalities into chatbots with these integration challenges.
(03:34):
How do you prioritize which features to develop first?
And how do you envision these capabilities evolving to change the way we interact with AI in our daily lives?
So I'm looking first in the use case and then kind of working backwards and saying,
OK,
what capabilities are required to support that use case.
(03:55):
So, for instance,
I came up with the idea the other day to create a feedback GPT.
And the idea is instead of a contact form on your website,
you can actually have a little mini chatbot that asked for feedback.
But the key thing there is these online forms today,
they email you with the details.
Well,
(04:16):
that means the chatbot needs to be able to email you too.
It can't just that information can't just disappear.
And so that made me think.
OK,
we need an ability to have a chatbot who can email the details at the end of a conversation to someone to say,
hey,
this is a feedback someone gave or this is the contact form that someone filled out.
(04:36):
Here's the information.
Wow.
A feedback GPT
sounds like a game changer for interactive and engaging customer feedback.
Incorporating the ability for a chatbot to send emails
adds a whole new layer of functionality. As you work on these groundbreaking features,
what are some of the hurdles you've encountered in ensuring these capabilities are user friendly and secure,
(05:00):
especially when handling personal information like email addresses.
So yeah,
actually security is an important aspect of what I'm thinking about.
So I've done a lot of work to make sure that the passwords,
the way you connect to the GPT or to the API from the GPT,
everything is as secure as possible and then limiting things, like for instance,
(05:25):
for the mail function,
ensuring that someone can't just put anyone's email address and spam people,
it has to go to a designated email address.
So the idea is (05:33):
if someone's filling out this form on your website,
it goes to the owner of the website.
Likewise,
if someone's going to use a chatbot to fill out the form on the website,
then it should go to the owner of the website.
There shouldn't be the ability to randomly send emails to people through a GPT.
I think that would open up a can of worms that would introduce too much spam and too much scams out there.
(05:58):
That's a really thoughtful approach to balancing innovation with security and usability with the upcoming release of the GPT Builder Toolkit.
What are some of the unique features you're most excited about?
And how do you think it will empower users without coding expertise to create their own advanced chatbots?
(06:21):
Well,
as I mentioned before,
I think that the swappable prompts are really powerful.
They're going to allow people to create these meta GPTs that have multiple prompts that can—that the GPT can switch between to provide a more expert guidance in specific areas.
I like the user authentication.
(06:42):
I think that's gonna be really powerful.
The ability to actually log into a GPT and save information,
the ability to save your user data and retrieve the user data to create like to do list applications,
flash card applications,
et cetera.
And then the email capabilities I just described,
(07:03):
I think are going to be pretty powerful as well,
that ability to create a chatbot that's taking information from the user.
And at the end summarizing that and then emailing that to someone as a way of providing a much better experience than a typical contact form on the website.
Those features truly sound groundbreaking, Trevor,
especially the idea of swappable prompts and user authentication to enhance the personalization and utility of chatbots. As we're approaching the end of conversation.
(07:33):
do you have any closing thoughts or advice for our listeners who are eager to explore the intersection of AI and productivity themselves?
I think the thing that I always recommend people to do is to get a subscription to ChatGPT, or to Claude, or one of these AIs,
so you're starting to work with the most advanced technology and learn how to use it because it's not something that's going to come overnight.
(08:02):
And it's not something that we have best practices out there yet.
They're starting to be developed,
but we're in the process and each new generation introduces new things that we can do with it.
And some of the old things we're going to have to forget.
You know,
the prompt engineering we do today is not the same as we did a year ago or two years ago.
So making sure that you're working with this technology on a daily, weekly basis.
(08:25):
So you learn it,
you develop an intuitive sense of it, I think is critical.
That's invaluable advice,
Trevor, emphasizing the importance of hands-on experience and adaptability in this rapidly evolving field.
Thank you for sharing your insights and experiences with us today.
It's been incredibly enlightening. Before we wrap up,
(08:48):
could you let our listeners know where they can find more about your work and the GPT Builder Toolkit.
Certainly,
the GPT Builder Toolkit can be found at gptbuildertoolkit.com.
And if anyone has any feedback,
questions,
comments about the GPT Builder Toolkit or anything else I'm doing,
they can email me at trevor@fastfedora.com or trevor@dayoptimizer.com.
(09:14):
If they're interested in the Day Optimizer digital day planner,
you can find that at dayoptimizer.com.
Thank you for listening.
This has been AI Meets Productivity,
your weekly podcast hosted by myself,
ChatGPT and Trevor Lohrbeer,
a productivity expert.
Find us on Apple podcasts and Spotify.
If you like this episode,
(09:34):
please give us a review.
It really helps others to find and listen to the podcast,
talk to y'all next week.
Popular Podcasts
Crime Junkie
Does hearing about a true crime case always leave you scouring the internet for the truth behind the story? Dive into your next mystery with Crime Junkie. Every Monday, join your host Ashley Flowers as she unravels all the details of infamous and underreported true crime cases with her best friend Brit Prawat. From cold cases to missing persons and heroes in our community who seek justice, Crime Junkie is your destination for theories and stories you won’t hear anywhere else. Whether you're a seasoned true crime enthusiast or new to the genre, you'll find yourself on the edge of your seat awaiting a new episode every Monday. If you can never get enough true crime... Congratulations, you’ve found your people. Follow to join a community of Crime Junkies! Crime Junkie is presented by audiochuck Media Company.
24/7 News: The Latest
The latest news in 4 minutes updated every hour, every day.
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.