Taming AI Business Writing
Key Points
- AI has made business writing cheap, but companies are overwhelmed by low‑quality AI‑generated documents because they lack clear standards.
- The real bottleneck isn’t the AI model’s capability but an organization’s ability to articulate concrete, testable quality criteria that replace tacit knowledge.
- Ambiguous specifications are amplified by AI, so success hinges on precisely defining requirements and encoding them in well‑crafted prompts, much like product requirement specifications.
- Companies that excel aren’t necessarily the best writers; they are the ones that can explicitly encode quality standards and evaluate output against those clear, structured criteria.
Sections
- From AI Docs to Quality Standards - The speaker explains that the real obstacle in AI‑assisted business writing is not the technology but a company’s lack of clear, testable standards, and outlines how to define concrete criteria to improve output.
- Communication Gaps Undermine AI Effectiveness - The speaker argues that vague organizational communication—not AI models—is the root problem, emphasizing how the default bland AI voice erases nuance and prevents the specificity needed for effective AI‑assisted writing.
- Strict Structured Meeting Notes - The speaker details rigorous guidelines for converting discussion into concise, intent‑driven notes that require explicitly named decision‑makers, owners for action items and open questions, strict length limits, and validation checks to eliminate ambiguity and filler.
- Combating AI Slop in Communication - The speaker urges clearer, higher‑quality writing and AI‑focused education to prevent the flood of vague, “AI slop” documents that are overwhelming workplaces.
Full Transcript
# Taming AI Business Writing **Source:** [https://www.youtube.com/watch?v=61IJSZ6GOuU](https://www.youtube.com/watch?v=61IJSZ6GOuU) **Duration:** 00:14:54 ## Summary - AI has made business writing cheap, but companies are overwhelmed by low‑quality AI‑generated documents because they lack clear standards. - The real bottleneck isn’t the AI model’s capability but an organization’s ability to articulate concrete, testable quality criteria that replace tacit knowledge. - Ambiguous specifications are amplified by AI, so success hinges on precisely defining requirements and encoding them in well‑crafted prompts, much like product requirement specifications. - Companies that excel aren’t necessarily the best writers; they are the ones that can explicitly encode quality standards and evaluate output against those clear, structured criteria. ## Sections - [00:00:00](https://www.youtube.com/watch?v=61IJSZ6GOuU&t=0s) **From AI Docs to Quality Standards** - The speaker explains that the real obstacle in AI‑assisted business writing is not the technology but a company’s lack of clear, testable standards, and outlines how to define concrete criteria to improve output. - [00:06:55](https://www.youtube.com/watch?v=61IJSZ6GOuU&t=415s) **Communication Gaps Undermine AI Effectiveness** - The speaker argues that vague organizational communication—not AI models—is the root problem, emphasizing how the default bland AI voice erases nuance and prevents the specificity needed for effective AI‑assisted writing. - [00:10:51](https://www.youtube.com/watch?v=61IJSZ6GOuU&t=651s) **Strict Structured Meeting Notes** - The speaker details rigorous guidelines for converting discussion into concise, intent‑driven notes that require explicitly named decision‑makers, owners for action items and open questions, strict length limits, and validation checks to eliminate ambiguity and filler. - [00:13:59](https://www.youtube.com/watch?v=61IJSZ6GOuU&t=839s) **Combating AI Slop in Communication** - The speaker urges clearer, higher‑quality writing and AI‑focused education to prevent the flood of vague, “AI slop” documents that are overwhelming workplaces. ## Full Transcript
AI has dropped the cost of business
writing to nearly zero. And most of the
businesses I work with or know about are
drowning in AI documents and have huge
issues with AI business writing. This
video is how you troubleshoot those.
What the principles are for using AI
well in business writing situations. And
then I'm going to walk through an actual
example of a prompt I'm using that sets
a much higher bar for AI business
writing than I've typically seen. And
we'll just go through it. So, first
let's get into the principles. The first
thing I want you to keep in mind overall
is that the real bottleneck in AI
assisted writing is never capability of
AI. People think it's the model. It's
not the model. Don't let anyone tell you
it's the model. It's organizational
ability to articulate what constitutes
good work. And typically that means
we've relied on individuals to have
instincts for what constitutes good work
instead of actual structured information
about what constitute good work. AI
forces tacet knowledge into explicit
standards and that is very very hard for
most businesses. You cannot rely on I
know it when I see it because AI cannot
read your mind. It is not that good.
It's never going to be that good. Every
quality criteria needs to be concrete
enough to specify, to test, and to
verify. That is the only way through on
the business writing side. And if people
say, "Well, I don't have time for that."
I've got to ask you, do you have time
for the business writing you're drowning
in? because I have lost track of the
number of people who are like I cannot
keep up with the business writing. It is
too much like people are sending me AI
slop at work. Well, the quality criteria
needs to be defined to make that go
away. So, what does that actually look
like? First, understand that there is a
specification bottleneck. The barrier is
not how fast can I write this anymore.
It is how clearly can I articulate what
I need. Every time you have ambiguity in
your specs for a doc, that is amplified
through generation. It is not reduced.
People sometimes think AI can reduce
ambiguity by adding detail, but anyone
who's worked with AI a lot will tell you
it doesn't reduce ambiguity, it enhances
it. And when it adds helpful detail, it
makes it worse. So the organizations
that succeed are actually not those with
the best writers. I know that's very
counterintuitive. They are those who can
articulate the quality standards
explicitly enough to encode them in
prompts that you can work with. Now,
writers can absolutely help with that.
Good writers are hard to find, but we
are moving from raw ability to generate
text according to a congruent prompt
framework or a congruent template as a
goal. And we're getting into a world
where we are just needing to specify our
requirements really, really clearly. It
reminds me of like wearing a product hat
and defining product requirements. Very,
very similar except now your product is
the dock. You also have a fundamental
evaluation issue because of the number
of prompts. I've talked in the past
about how we have this issue with
résumés. Really, it's with all knowledge
work in the business. We don't have time
to evaluate everything that got done,
which means that we have to figure out
how to scale evaluation. That is one of
the fundamental challenges for
businesses that want to go faster. And I
believe firmly that scaling evaluation
means putting AI on the evaluation side,
not just the writing side. And I want to
talk about that a little bit more
because I I think we miss that. It is
absolutely possible. I've done it. I've
written I'm writing a prompt for this
article to talk through how you evaluate
and build a prompt. Build a Claude skill
that helps you to evaluate. I've done
it. I'm doing it. it. You can make your
job so much easier if you are just
willing to let AI take a first pass and
give it really clear requirements on
what good looks like. I also want to go
beyond just hey you need to specify. The
other core issue is that we typically
have longstanding information
architecture problems in our documents
at work that we just paper over and that
we are not going to be able to paper
over when AI is writing. Because
fundamentally what AI does is it exposes
information asymmetries,
informationational vagueness that
previously hid in a lot of our writing
because people wrote it and you just
assumed that people were doing their
best thinking. One of the good things
about the AI age is we now don't assume
that everyone's doing their best
thinking which means we critique more
which is actually healthy. So when we're
critiquing I want us to think of a few
things in this information architecture
bucket. One documents really ought to be
written for goals and decisions and they
aren't always. And so if you can't tell
if this document enables person X to
make choice Y or if this well structured
information enables you to make a big
decision, if you if you don't know what
it looks like and why you're reading it,
it's it was going to be useless anyway,
right? But now we blame the AI. Your
goal at this point is actually to get
rid of that vagueness you tolerated in
the past in the business and define
theformational architecture of the
document. Your structure is the business
logic, not just a template. So many
times if someone gives you like a
product requirements document or if they
give you a business memo or a press
release, when they give it to a human,
you get a template. You actually don't
get the logical underpinnings of the doc
and people end up learning it from
experience. Templates just let you fill
in the boxes without thinking. And when
you hand AI only a template in the
prompt, that is what you get. And that
is why so often when I'm called in to
help with business writing prompts,
people say, "I don't know what I did
wrong. I gave it the template and it
filled out the template and it's
terrible. It's crap." Well, you didn't
give it the the business logic. You
didn't give it a a decision interface to
work against. You didn't give it a goal
for the document. That's why your
writing is terrible. If you don't give
it that intent, the business writing is
going to fail. So, the other piece here,
this is very counterintuitive. You can't
just give it a goal and give it business
logic. In my experience, you also have
to give good failure tests. You have to
insist that you know what bad looks
like. Isn't that funny? Isn't that
counterintuitive? But if you're trying
to tell the AI how to do something well,
it really helps if you have five to
seven examples of the kinds of quality
problems you have with these kinds of
documents. It's like, wow, this
technical specification document is
really overspeced on the design and
insists on a microservices architecture
when we don't use that. Great. That's a
failure example. Or this press release,
it is way too hypy and I hate the hype
in this press release. It doesn't
respect the actual product capabilities.
This executive summary and this
executive memo is too vague. I need more
specificity. understand where your
organization today fails to communicate
information and you will understand how
to work with AI to write better. This is
I'm going to repeat it again a people
problem at root. It is not the model's
fault here people. It is our ability in
organizations to communicate intent
clearly that is governing our ability to
work with AI and we're not doing it
well. I want to tease out some of the
organizational dynamics too.
Specifically, one of the things that
I've noticed that's subtle but painful.
We are converging on voice because of AI
and that is leading to
informationational loss in business
systems. So, we have an AI default voice
and too few people understand how to
push that voice into something that
communicates their their intent clearly.
I'm not talking about style here. I'm
talking about the ability to communicate
clearly with what really matters. And I
think the default voice that AI has
obscures that, right? The default voice
is diplomatically hedged. It's pseudo
comprehensive. It's stylistically
extremely bland. And you don't have the
ability to carry conviction with that
voice. If you want to make a bet, you
don't have the ability to articulate
real specificity, but in the same
document to articulate this area is
vague and uncertain, and I want to admit
that upfront. Good quality writing has
that range. And AI, if you just prompt
it vanilla, does not. And that leads to
critical information loss. And that is
part of why businesses feel like they're
drowning. This information is not super
high quality. And I'm going to say
again, it is absolutely possible to do
that. You can make highquality documents
with AI. The last thing I want to call
out before I go over and I show what I
mean is iteration diagnosis. So this is
sounds really complicated but very
simply we need to diagnose the failure
of people to iterate well with writing.
In other words, people are trying to say
make it better on their business
documents and that is all they're
writing and it's terrible and it's not
working. But no one knows how to do it
better unless they're educated. And what
they don't realize is that it is a
people problem to communicate intent and
that they have to specify their intent
more clearly if they're not getting a
draft they like. So I'm going to come
back to the like the core of this issue
and then I'm going to show you how I'm
addressing it with a specific prompt. I
actually put together a whole bunch of
prompts and a claude skills for this cuz
I want you to be equipped and I'm going
to show you one of the prompts and how
it works. So the thing to remember is
because AI assisted writing is exploding
because organizations are drowning. We
have that AI generation problem. The
cost of information is zero. We need to
therefore put a premium on our intent.
Otherwise, we degradeformational signal
through our businesses and it is hard to
make decisions and we feel like we're
drowning and it has real career
implications and real dollars and cents
implications. I am passionate about good
business writing. I love it. It is
getting hard to find because people
don't know how to prompt. Let's get to
an actual. Okay, this is an example of a
prompt that I think is highquality. It
is also designed to be modular and
changeable so you can make it the way
you want. Let's get into it. This is for
meeting notes. It's the simplest
possible one. I have a bunch of other
prompts for more complex docs. Meeting
notes are overlooked because most of the
time if you go into a generic AI
transcript and you get meeting notes is
just a generic summary that's very
vanilla of what was there. I wanted to
be more opinionated because I wanted to
carry through the principle that you
need to have intent around what you're
doing. So we have contacts, date,
attendees which should be pullable from
the meeting note raw purpose of meeting
input provided and you can paste your
transcript there and then you're asking
for a very specific output and you can
modify this when I tell you why I put
what I did. Your goal here is to create
notes that help the team execute, right?
Execute on what was discussed. There is
a specific goal for this. The notes are
used in and then there's a context for
this, right? You can decide where
they're used. You then have a required
structure. Did you make decisions? Do
you have action items? Are there open
questions that were discussed? What were
the key discussion points? The vanilla
notes I get. Look, I love granola. I
love some otter. Right there. There's
these AI notes. They do not do this.
They do not help you encode intent. It
is up to you to bring this level of
clarity. And I want to help, but there's
no substitute for that intent. The AI
won't bring it. You have constraints.
You have a total length that you have to
keep to. You have decisions. You have to
define an owner by name. You have action
items. You cannot include pleasantries
or general discussions. You may not
infer. You may not guess. This is the
tone. And then here are validation
quality checks. Every decision must have
a name decision maker. Every action item
must have an owner. No action item is
allowed to be vague. Open questions must
have or assigned owners. If any check
fails, revise before outputting. Is this
perfect? No prompt is perfect. Is this
going to get you a long way on intent?
Yes. And then I want to get into, and I
do, why the prompt works, right? It
communicates purpose. It communicates
structure as logic. And you can change
that structure if you want a different
intent. There's an eval mode. There's a
failure mode. Well, let's look at how to
customize it, right? And I include that,
too, right? For your workflow. You can
change it up. You can change it to your
organization's voice. You can have
different meeting types. You can have a
sprint goal instead. You can have
failure modes that are different. And
then I can give you an example of an
output, right? This is what a good
output looks like. This is what a
terrible output looks like, right? And
this is very similar to the AI notes I
get generically. Frankly, Chad GPT
launched a meeting notes feature that
looks a lot like that top part. This is
part of how I know we're losing good
quality business intelligence. Like the
bottom example is going to be much more
informative for the business than the
top. So please, please, I have a bunch
of these prompts. I don't care if you
use my prompts or not, but please put
intent
into your business AI writing. That is
the key. And if prompts help you scale
that across the business, if Claude's
skills help you scale that across the
business, I built both of those. That's
great. But that there is no substitute.
You you cannot get away from the need
for humans to define what good looks
like for AI and to define requirements.
And to be honest with you, that is the
thing I'm excited about. We have sat for
a long time with the assumption that
human best effort is kind of the bar for
docs and we just all have like I worked
at Amazon and we had like a bar for docs
that floated around best based on the
best human writer in the team in the
department etc. You don't have to have
that anymore. You can have a really
consistent highquality bar and you can
know whether someone is writing to that
bar or not. And people ask me all the
time, well does this mean people won't
think anymore? I I dare you. I dare you.
Are you going to think less if you go
through this process? If you actually
define intent for your business with
writing, no, you are going to think
more. You are going to think harder.
You're going to have to work harder to
communicate all of this to people
because so much of it was vague and
lived in people's heads. Well, not
anymore. And the reason why you're going
to have to do this is because the
alternative is not what we had pre202
where everyone wrote everything. The
alternative is AI slot forever because
AI is out of the box. Everyone's using
it and everybody I know at work that's
drowning in AI docs, which is a lot of
people. Well, that's not going to stop.
The people making them aren't going to
stop because they think it's productive.
We need AI education that emphasizes
quality, that emphasizes the different
ways we need to think. I hope this video
has helped you think about how our
brains need to change to communicate
effectively with AI when we are writing.
Best of luck out there and may you long
save and long preserve your business
from AI slop and bad business writing. I
hope these tips have helped.