Quick Win: The AI workflow that can replace your morning scroll

What if every morning you woke up to the biggest breakthroughs in your industry - already summarised and ranked before your first sip of coffee? 

In this Quick Win episode, I speak with Morgan Brown, Vice President of Product and Growth at Dropbox, about how he uses AI to simplify his workday - from automating his inbox to designing a daily AI briefing that scans and summarises the entire landscape of research papers, newsletters, tweets, and podcasts. Starting with one simple prompt, Morgan built a system that cuts through noise and delivers only what really matters. 

Morgan and I discuss: 

• How Morgan uses AI to automate routine tasks like email triage and information curation. 

• The process he followed to build a personalised daily AI news digest. 

• Why his approach started not with coding, but with one simple question: What do I keep checking every day? 

• How he refined his system through prompts, iteration, and feedback loops — just like editing a great piece of writing. 
• The mindset shift from consuming more information to filtering for signal over noise. 

KEY QUOTES 

“I realised there was no way to stay on top of that volume consistently - so I started with a prompt.” 

“I didn’t start with coding or fancy tools. It started with asking, what sources do I keep checking and how can I pull them together?” 

 

Connect with Morgan Brown on X (Twitter), LinkedIn, and his website https://www.morganbrown.co/  

Check out Morgan’s book Hacking Growth.  

Get your hands on Morgan’s AI research prompt here. 

Listen to the full conversation with Morgan here 

 

My latest book The Health Habit is out now. You can order a copy here: https://www.amantha.com/the-health-habit/ 

Connect with me on the socials: 

Linkedin (https://www.linkedin.com/in/amanthaimber) 
Instagram (https://www.instagram.com/amanthai) 

If you are looking for mor

Episode Transcript

Speaker 1 (00:01):
What if every morning, instead of drowning in a sea
of newsletters, tweets, and podcasts, you had the day's biggest
breakthroughs already sorted for you. That's what Morgan Brown, vice
president of Product and Growth at drop Box, built for himself.
By the time he sits down with his coffee, an
AI workflow has already scanned the landscape of research, papers, substacks, podcasts,

(00:27):
and even YouTube. It spits out just three can't miss signals,
ranked from world changing to incremental, and explains what they
actually mean for his role. In today's quick Win, Morgan
shares the simple steps he used to design that system,
starting with one prompt, refining and running it daily. By

(00:48):
the end, you'll know how to set up your own
version to cut through the noise and actually stay ahead.
Welcome to How I Work, a show about habits, rituals,
and strategies for optimizing your day. I'm your host, doctor
Amantha Imber. Still staying on the topic of I guess

(01:15):
reducing or eliminating some of the grunt work through AI,
I'd love to know if they're more on the automation
or agentic AI side of things. What some of the
I guess other tasks that you've been able to automate
in interesting ways would be.

Speaker 2 (01:32):
I've really done a lot of automation around trying to
understand what's changing around me. So I have a daily
workflow that reviews all new kind of substack newsletters, important
tweets across a large domain of AI and mL ex accounts,
reviews Archive, which is the scientific paper repository for new

(01:55):
mL and artificial intelligence papers. It scans the whole landscape
to Spotify podcasts and basically takes all of the day's
information about AI and mL reviews. It all categorizes it
into world changing, interesting, incremental, and noise, and then summarizes

(02:15):
the top three quote unquote world changing potentials and then
summarizes it for me in the context of my role
at DASH, where it kind of talks about hey, things
you might consider as the head of product for Dash. So,
for example, Anthropic the other day just announced that claud
can handle now a million token context window, which effectively
means that for many reasonable size software codebases, it can

(02:39):
reason about the entire codebase, which is a pretty big
and important milestone for software development. And the other one
is I automate my personal email I can't imagine you're
inbox Atmantha, but it gets hammered all the time. And
so I built a little agent using claud code to
read my personal Gmail every day, categorize it into newsletters,

(03:01):
spam priority emails, summarize the newsletters for me, flag the
messages that I want to respond to, and draft responses
for those newsletters or not for those emails. So really
trying to kind of like manage my inbound email automatically
as well.

Speaker 1 (03:19):
Wow, okay, I love the both those examples. I want
to dig a bit deeper into how you went about
creating this automation that summarizes all the AI news of
the day. I mean, that sounds so powerful. Can I
buy that from you? Morgan? Are you selling it?

Speaker 2 (03:37):
You can link it in the show notes?

Speaker 1 (03:39):
Wow? Amazing handed over? Yeah wow. Talk me through the
process of how you put that together.

Speaker 2 (03:45):
First of all, I realized that there were a few
key sources of information that I was constantly referring to personally,
So you know, whenever I had a free moment, I
would go to archive and kind of browse the actual
published papers because that's the real source of truth cutting edge.
I would see a lot of popular posts on x

(04:05):
about kind of new research breakthroughs. I follow some of
the key people like the sam Altman's of the World
and the Frontier Labs. And then there's also several great
substack newsletters around AIS that I read as much as
I can. But I just realized there was no way
for me to stay on top of that volume consistently,
and I just started with a prompt. I told chat TBT,

(04:27):
I'd like to create a prompt to scan the entire
AIML space for important signals around research and development and
industry news that pertains to my role at Dropbox. And
I said before X, I want to look across these
accounts and accounts like it. So I kind of gave
it a seed list of accounts, but asked it to
expand where it could. I gave it specific newsletters that

(04:51):
I read on substack, but also again asked to consider adjacents,
and then I gave it specific categories on archive where
those papers are housed and asked it to consider relevant
ones that there. And then I said, I'd like to
really filter high signal, like I don't want this to
be a laundry list of everything that happened that when

(05:11):
actually helped me kind of consume it any better. So
I said, help me come up with a scale to
rank the innovations and the news that's coming out in
the day, and kind of categorize things as you can't
miss these are like foundational important, shifts incremental and important,
and then give me some synthesis around Hey, when you
put these signals together, what does it mean for my role?

(05:33):
So I fed that all just in basically talking to
chat GPT. I like to use the audio input to
kind of just stream of consciousness my thoughts into it.
Once I did that, I asked it to kind of
structure it into a prompt. I reviewed the prompt. Some
of the things I didn't like. I always try to
go back and forth with it. I think you should
kind of refine it much like you would the copy

(05:55):
for a website or you know, the script for something.
And then once I got the prompt too you get start.
I said, Okay, let's run that for today and give
me the output. And I got the output and I
was like, oh, this is a little too long. It
could be a little shorter. It looks like we're underrepresenting,
we're missing YouTube. Let's try to add YouTube in, so
on and so forth, and then I finally got it
dialed in, and then I said, great, set this as

(06:17):
a daily task every day five am Pacific. Run it
again while I'm having coffee. I just kind of read
through it.

Speaker 1 (06:24):
What I love about Morgan's approach is that it didn't
start with coding or fancy tools. It started with a
simple question, what sources do I keep checking and how
could I pull them together? So the next time you
feel buried under articles or updates, try listing your key sources,
feed them into a prompt and ask AI to filter
and rank what matters most. And of course you'll find

(06:47):
the full episode with Morgan linked in the show notes.
If you like today's show, make sure you git follow
on your podcast app to be alerted when new episodes drop.
How I Work was recorded on the traditional land of
the Warringery people, part of the Coulan nation.