How I condensed a day of research into 5 minutes (without losing quality).

If you’re serious about working smarter (not harder) and unlocking 10+ hours of your week, Inventium’s GenAI Productivity Upgrade course is for you. Learn how to use Gen AI as your second brain - to speed up research, streamline content creation, and make better decisions in less time. 

Spots are limited, and the next cohort kicks off on July 14. Don’t miss this chance to radically transform the way you work. Learn more and sign up here: https://inventium.com.au/genai-cohort/ 

*** 

If you’ve lost hours falling down a Google rabbit hole while prepping for a workshop or writing a strategy paper, there’s a better way. Gen AI can act as your personal research assistant, helping you tackle complex topics in a fraction of the time. 

In this mini-episode, we are joined by Inventium’s GenAI guru Neo Aplin to unpack the power of “deep research.” Neo explains how AI tools like ChatGPT, Perplexity, and Gemini can scan hundreds of sources, summarise key insights, and create detailed reports - all in a matter of minutes. 

Today we learn: 

• What deep research is and how it works 

• The Gen AI tools that offer deep research (and Neo’s go-to choice) 

• Why you need to co-create the research plan with AI for the best results 

• Tips for writing prompts that get you better outcomes when undertaking deep research 

Key quotes: 
“It’s like outsourcing four hours of online digging in five minutes.” 
“The better the background and context you can give, the better the results.” 
“Review everything. Click on it. Make sure it’s correct. But you’ll get a super-detailed report that saves you hours.” 

 

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

Episode Transcript

Speaker 1 (00:00):
If you've ever fallen down a Google rabbit hole trying
to prepare for a workshop, or write a strategy paper,
or just get your head around a new topic, you
are going to love this episode. Today, Neo Applan, Inventium's
Jenai Guru, is back to explain one of Jenai's most

(00:21):
powerful hidden tools, deep research. It's like outsourcing four hours
of online digging in five minutes. Welcome to How I Work,
a show about habits, rituals, and strategies for optimizing your day.

(00:41):
I'm your host, Doctor Amantha Imber. Before we get into
today's episode, I have been geeking out over the research
on AI adoption in the workplace, and the data is
really clear. The people who master Jenai now aren't just
getting ahead, they are creating entirely new level of productivity
that seemed impossible just like a year ago. Because in

(01:05):
a nutshell, there are two types of professionals, those who
are fluent in AI and those left scrambling to catch up.
Inventium's Genai Productivity Upgrade is how you can make sure
that you are in that first group. It is a
twelve week course designed to move you from dabbler to
productivity machine. No fluff, just practical strategies that will pay

(01:27):
off from week one, saving you at least ten hours
every single week. You'll learn how to make AI sound
exactly like you use AI as your second brain to
excel at your job and use it to become a
much more effective leader, and so much more. Whether you're
a complete beginner or already dabbling, we've got you covered,

(01:48):
starting with prompting fundamentals and going all the way through
to advanced automations and digentic AI week kickoff on July fourteen,
and spots are limited. Visit inventi do au forward slash
Jenai hyphen cohort to secure your place now and there's
a link to that in the show notes. You've got
nothing to lose because there's a seven day money back guarantee,

(02:12):
so head to the show notes click on the link
to read more about the program today. Okay, neo, what
exactly is deep research and what problem is it solving? Oh?

Speaker 2 (02:24):
You know how when you've got to do a lot
of research and you think I'm going to have to
spend a couple of hours working with Google to learn
about this thing, to research about this thing, so it
might be a lot of manual research that you need
to do instead of doing that manually, which can take
many hours, so you can learn the topic and know
that you're getting the right information. You can automate that

(02:45):
with using Jenai tools and the deep research function. So
it's great if you want to do things like market trends,
best practices, science updates and all those kind of things. Effectively,
you're getting the ai to be your research assistant and
it goes away. It plans what the research is going
to be, and it goes and searches so many websites
for you.

Speaker 1 (03:05):
Okay, So which genai tools actually offer deep research and
how do they differ?

Speaker 2 (03:13):
The main functions are pretty much the same between the
different ais. So chatchpt does it on the paid and
the free version. You get five deep researchers a month
on the free and thirty a month on the paid.
Perplexity has it, as well as Gemini, which is Google's
Genai tool. And yeah, they're all very good. They're slightly

(03:35):
different in the way that they approach the results. However,
I'd say play with one many of them. They're awesome
at what they do.

Speaker 1 (03:43):
Do you have a personal.

Speaker 2 (03:44):
Favorite At the moment, I'm enjoying Gemini, and the reason
for that is that I can use it as much
as I want to. It's free at the moment. So
I do many deep researchers, but look, all of them
are excellently in the way that they operate.

Speaker 1 (04:00):
And I think what's useful with Gemini If you are
on the Google ecosystem, it exports the deep research report
to Google Docs and then chat, GPT and Perplexity export
to word and PDF, so that is useful as well.
Now I want to know what is actually happening in
the background when AI is doing its deep research.

Speaker 2 (04:21):
It's a true agentic flow and I'm doing like air
quotes here agentic, so gentic is where the AI is
going off and doing things on its own. So it's
great where the interface actually shows you what the AI
is thinking about in order to do that deep research.
So it will say these are the sources that they
need to look at. Then I need to look at this,
Then I need to research this particular thing, and it

(04:43):
will then plan how it's going to approach this problem
and all the different types of pages it's going to search.
So behind the scenes, it's doing the plan first. Now
before you get it to do the work. You can
agree with that plan or not, and you could say
I need to do more of this than that. So
work with it first the plan, and then when you
hear the go button on the deep research button, then

(05:04):
it does exactly what it planned to. So it'll go
and research many different websites. So I've had ones where
it's like one hundred and fifty websites kind of common.
I've had some up to four hundred and ninety different
websites that it's looking at in order for it to
go through the plan. So it gives you so much
information from those sites. And then what it does is

(05:24):
it builds you a report. And the report is very detailed.
We're talking on it five ten pages worth of information.
Plus it also sites where it got the information for
so you can click on the links and learn more
and just make sure that it's got it right. So
in summary, it plans the search, work with it on
the plan. It then does the search, and it produces

(05:45):
you an excellent report, so you've got an outcome.

Speaker 1 (05:47):
Okay, So something I have wondered about is how exactly
should I best write the prompt to get the best
result from deep research? Because I know that in the
past I've sometimes been quite lazy. I've just written a
quick one sentence prompt. I mean, the results have been
pretty good, But ideally, what should I be doing with

(06:08):
the prompt?

Speaker 2 (06:09):
Same as any other prompt, If it knows what you're
trying to achieve, and it knows what the goals are
and the context and things like that, you will get
a much better result. So instead of saying what's the
modern strategy for banking or something like that, very generic,
you need to say what specific strategy you're looking at.
So this is the actual area I'm looking at, and

(06:30):
these are the types of things I'm trying to solve.
So work with the AI on this. You can even
do what they call meta prompting, which is working with
the AI giving it all the context and what you're
trying to achieve and then get it to produce you
a prompt, which is a nice little cheats way. But
the prompt is not the most important part. It is
equally as important as working with AI on that search strategy,

(06:54):
So making sure it's going to search the right kind
of pages and trying to get the right kind of
outcomes in the two of them together equally is important
for a great result.

Speaker 1 (07:03):
And what's your advice on working with the AI to
design a good approach to doing the deep research?

Speaker 2 (07:10):
Saying my goals are and here's the context, like it's
the business, here's what I'm trying to achieve. These are
the two main things that it really needs to know
to be able to nail a great deep research prompt
or a deep research process. So once you've got those
things absolutely agreed with the AI, then you'll find you're
going to get a much better result. So better background

(07:31):
and better context you can give the better the results.

Speaker 1 (07:34):
Okay, Now, a question that I'm sure a lot of
listeners are asking in their brains is can we trust
the results? I mean, we all know about hallucinations, where
the AI just makes stuff up, it creates sources out
of nothing. Is deep research different in that sense?

Speaker 2 (07:54):
It isn't in that you can get hallucinations. However, I
found that there are few hallucinations, and the reason for
that is it's effectively summarizing web pages that it has
already just read. It's not hallucinating out of its own knowledge.
And if there's a knowledge gap, there's a problem. And
so out of the box you will find that there
are fewer hallucinations. The worst that I've found is it's

(08:17):
interpreted a page slightly differently than I would have interpreted it.
And the page may have been for a tangentially related
problem or industry, and I can see how it's got
the things kind of together, but in reality, I would
have said, yeah, probably that page wouldn't have been something
that I would have included on my search. So it's
very accurate. It's more of an interpretation issue that I

(08:40):
have found, and even then it's really rare for it
of me to have found it after all the deep
researches that I've done, so it is a very thorough search.
It is really good at summarizing the pages that it
has read, and even if it has read fo one
hundred and eighty pages do notes, so just because it's
done a deep research that it isn't the world's expert

(09:00):
on those things. So it's just summarized the four hundred
odd pages that it's read, and it's done an awesome
job at the summarization. However, you might need to still
do some more research on top of it so know
that it could potentially hallucinate. It also might not have
searched a really important page that's out there, just as
you and I when we do a Google search, we

(09:21):
may not have searched every paper out there. So the
probably the biggest risk, biggest takeaway is review everything. Click
on it, and if you're wanting to know more about it,
click on those links so you can be sure that
everything in there is correct.

Speaker 1 (09:34):
Neo, thank you so much for taking us through deep research.
It is hopefully a function in people's GENAI that they
are going to now use a lot more frequently. If
you like today's jow, make sure you follow on your
podcast app to be alerted when new episodes drop. How

(09:55):
I Work was recorded on the traditional land of the
Warrangery People, part of the Cool and Nake. A big
thank you to Martin Imma for doing the sound mix.