Using ChatGPT as a technical writing assistant

In recent weeks, I’ve been exploring the use of ChatGPT within a
professional context. As a consultant I write extensively about technology
and software, advise clients, and collaborate with internal teams. To avoid
any potential intellectual property issues, I consulted both my boss and one
of the company lawyers. I specifically avoiding using ChatGPT in any
client-related context. Instead, I focused on employing ChatGPT for
technical writing intended for public consumption, thereby minimizing the
possibility of inadvertently exposing proprietary information to the AI.

Goals and expectations

When I first considered using ChatGPT as a writing assistant, I had a
few specific goals in mind. One of the main tasks I hoped it would help me
with was crafting ‘blips’ for the Thoughtworks Technology Radar. The
radar covers over 100 individual technologies, and while our team engages
in detailed discussions about each of them, translating those notes into a
coherent paragraph can be challenging. I was hopeful that ChatGPT could
streamline this process and make it more efficient.

In addition to the blips, I write an accompanying article called
Trends in the Technology Industry” that delves into the broader themes and
patterns we observe in the field. I was curious to see if ChatGPT could
play a role in shaping this piece, providing insights or even contributing

Lastly, we also adapt the Technology Radar for a business context,
aiming to make its high-level themes more accessible to a non-technical
audience. This often involves simplifying complex concepts and presenting
them in a more digestible format. I wanted to explore the potential of
ChatGPT in assisting with this task, helping us create content that
effectively communicates our ideas to a wider readership.

Radar Blip: Casual management of webhooks – Hold


Hello. Please help me write a ‘blip’ in the style of the
Thoughtworks technology radar, about the dangers of “Casual Management
of Webhooks”. Summarize the notes and discussion below:

With the rise of remote working we are continuing to see growing
adoption of chat collaboration platforms (e.g. Slack, Google Chat,
Microsoft Teams) and with it a rise in “ChatOps”. Most chat
collaboration platforms offer webhooks as a simple way to automate
sending messages and notifications to channels, and much developer
platform tooling (e.g. CI/CD software, monitoring software, etc) is
building out first class support for utilising these webhooks. However
there is a tendency to treat these webhooks as configuration, rather
than as a secret/credential. We see this tendency manifesting in how
chat tools present webhooks, how teams treat and store webhooks (e.g.
committing them in plain text to a repo), and how integrated tooling
treats webhooks (e.g. exposing them in plain text). This is a security
smell that can open up an organisation to phishing attacks.

ChatOps webhooks are a credential: they offer privileged access to
an internal space. In some cases, they directly contain API keys that
can be extracted and utilised directly. Not treating them as secrets
opens up the possibility that they can be used for phishing, and that
phishing is more likely to be successful because of the lack of
awareness of this type of attack. Webhooks in git repos can easily be
extracted and used to craft and send a fraudulent payload, which the
user may have no reason to doubt and no way to authenticate. There has
not been major reported incidents of this type in the wild which only
adds to the complacency. In order to mitigate this threat we need to
see a shift, both in the culture of teams who are handling these
webhooks, and in the culture of software developers who are building
integrations with ChatOps platforms.


Here’s a blip in the style of the Thoughtworks technology

Dangers of Casual Management of Webhooks: A Security Smell

As remote work continues to rise, so does the adoption of chat
collaboration platforms and ChatOps. These platforms often offer
webhooks as a simple way to automate sending messages and
notifications, but we are noticing a concerning trend of treating
webhooks as configuration, rather than as a secret/credential. This
can lead to phishing attacks and compromised internal spaces.

Webhooks are credentials that offer privileged access to an
internal space and may contain API keys that can be easily extracted
and utilized directly. Not treating them as secrets opens up the
possibility of successful phishing attacks. Webhooks in git repos can
easily be extracted and used to send fraudulent payloads, which the
user may not have any way to authenticate.

To mitigate this threat, teams handling webhooks need to shift
their culture and treat webhooks as sensitive credentials. Software
developers building integrations with ChatOps platforms must also be
mindful of this risk and ensure that webhooks are handled with proper
security measures. Let’s not wait for a major incident to occur before
taking action.


This output was pretty good, especially the first paragraph that
justifies the rise of ChatOps and explains how webhooks are related. The
final paragraph is some kind of “call to action” which isn’t really
right for a Radar blip, but it was easy enough to remove. Thoughtworks has
published the Technology Radar for more than ten years now, so simply asking
for output “in the style of the Thoughtworks
Technology Radar” creates text that has more or less the right kind of
style for a Radar blip. If I wanted something in a different style I would
have needed to be more specific in my prompt. You can see the final
management of webhooks text on the Radar site, to see where we ended up
after editing, including a round of company-wide feedback.

Radar Blip: Giskard – Assess

In the style of the thoughtworks technology radar, write a
‘blip’ for “Giskard”. Incorporate the following notes, and keep the
resulting write up to two paragraphs.

Giskard is Quality Assurance for AI models, e.g. helps find


Seems like a new kind of tool, makes collaboration between data
scientists and business stakeholders / SMEs easy. No real experience
with the tool yet.

Person A: People I talked to highlighted the quality assurance
part, you can write a variety of tests for it

Person B: The “why” here is copied from website, but what IS it
actually that makes the collab easier?

Person C: When we are reasoning about models, lots of business
implications involved, so bias avoidance can be quality metrics for a
model; you can codify acceptance criteria for your models, together
with business

This one is most about data quality compared to other tools

Giskard emerges as a novel Quality Assurance solution for
AI models, specifically designed to identify and mitigate biases. By
focusing on data quality, Giskard distinguishes itself from other
tools in the market. It fosters collaboration between data scientists
and business stakeholders, enabling them to jointly establish
acceptance criteria for AI models based on bias avoidance and other
essential quality metrics. This ensures that the model outcomes are
better aligned with business objectives, while also minimizing the
risks associated with biased predictions.

Though we have limited hands-on experience with Giskard,
conversations with users have emphasized its ability to support a wide
range of tests for quality assurance. The tool’s unique value
proposition lies in facilitating seamless collaboration between
technical and non-technical stakeholders, making it easier to reason
about models and their business implications. By allowing teams to
codify their criteria, Giskard promotes transparency, streamlines the
development process, and helps organizations build more robust and
ethical AI models.


The text is clearly way too optimistic for an ‘assess’
blip on the Radar. The fact that ChatGPT has been trained on tons of
marketing pages on the Internet, as well as fine tuned using human
feedback, has led to the bot saying things that we never would. Words
like ‘novel’ and ‘unique’ are something I’d edit and remove.

What was very interesting here though is the response from one of
our machine learning experts in Finland. She said it sounded like the
blip had been written by a junior person with very little
understanding of the typical ML workflow, and she made some quite
significant changes before the blip text was ready for
publication. I’m not an expert in this particular
tool — although I’ve used a few ML tool chains — and this critical feedback highlights the
fact that ChatGPT output generally requires quite skilled experts to review and edit.
Here’s the Giskard blip on
the Radar after human review and editing.

Macro trends article

I’m the author of the Thoughtworks “macro trends” series of
articles. Are you familiar with those? Can you tell me what they are

As an AI language model, I’m familiar with a wide range of
topics, including the Thoughtworks “macro trends” series of articles.
The series aims to identify and analyze the significant macro-level
trends that are shaping technology, business, and society. These trends
often have a global impact and are driven by factors such as
technological advancements, changes in consumer behavior, economic
shifts, and global events. By understanding these macro trends,
organizations and individuals can better adapt to change and capitalize
on emerging opportunities.

Some of the key topics covered in these articles may include (but are
not limited to):

The rise of artificial intelligence and machine learning

The increasing importance of data privacy and security

The role of digital transformation in businesses

The growing impact of climate change and sustainability efforts

The expansion of the Internet of Things (IoT) and connected

The evolution of the workforce and the future of work

The development of new technologies, such as blockchain and quantum

The specifics of each article may vary depending on the time they
were written and the trends relevant at that time.

OK, I think you have the idea. I would say it’s not really
about society, though, it’s more of a tech industry focus.

I have made some notes on new trends for a new article. I’d like you
to help me express my notes as sections of a macro trends article.

The first trend is around knowledge management for teams. We
discussed interesting tools Logseq and Obsidian, and we wrote blips
about them. For logseq we wrote:

Team knowledge management is a familiar concept with teams using
tools such as wikis to store information and onboard new team members.
Some of our teams now prefer to use logseq as a team knowledge base. An
open-source knowledge-management system, loqsec is powered by a graph
database, helps users organize thoughts, notes and ideas and can be
adapted for team use with Git-based storage. Logseq allows teams to
build a democratic and accessible knowledge base, providing each member
with a personalized learning journey and facilitating efficient
onboarding. However, as with any knowledge management tool, teams will
need to apply good curation and management of their knowledge base to
avoid information overload or disorganization.

While similar functionality is available in tools like Obsidian, the
key difference lies in Logseq’s focus on consumption, with
paragraph-based linking enabling team members to quickly find the
relevant context without having to read an entire article.

Can you turn this into a macro trends article section about knowledge
management tools for teams? It should be about 3 paragraphs long.

Emerging Trend: Next-Generation Knowledge Management Tools
for Teams

In today’s fast-paced technology landscape, effective knowledge
management is more crucial than ever for teams to stay competitive and
agile. Traditional tools like wikis have been commonly used to store and
share information, but recently there has been a surge of interest in
more advanced and versatile knowledge management systems. These new
tools, such as Logseq and Obsidian, offer innovative features that are
transforming the way teams manage, access, and engage with their
collective knowledge.

Logseq, an open-source knowledge-management system, is a prime
example of this shift. Powered by a graph database, it helps users
organize thoughts, notes, and ideas and can be adapted for team use with
Git-based storage. Logseq’s unique approach enables teams to build a
democratic and accessible knowledge base, providing each member with a
personalized learning journey and facilitating efficient onboarding. Its
paragraph-based linking feature allows team members to quickly find the
relevant context without having to read an entire article, emphasizing
its focus on consumption. However, as with any knowledge management
tool, teams will need to apply good curation and management practices to
avoid information overload or disorganization.

Similarly, Obsidian offers robust knowledge management capabilities,
but with a stronger emphasis on content creation. While both tools
provide valuable features for managing and accessing information, their
differences highlight the evolving nature of team knowledge management.
As these tools continue to develop and gain traction, they are set to
redefine the way teams collaborate and learn, ultimately driving
innovation and productivity in the tech industry.


Similar to the Radar blips drafted by ChatGPT, this text is overly
‘bubbly.’ Phrases like “more crucial than ever” just sound a little too
hyperbolic. I found this was a common theme – ChatGPT is just way too
optimistic and happy sounding, and almost ends up a little bit ‘bland’
because of this. But a quick edit pass can fix this and introduce
words that are more like the ones I would really use to describe this

Additionally, ChatGPT seems to always structure its responses as
introduction, information, summary. It seems to do this whether you have
asked an open-ended question or are asking it to help you create a
section of an article. I found I repeatedly needed to discard or
condense the opening and closing paragraphs of ChatGPT’s output.

You can find the
macro trends article on the Thoughtworks website.

Adapting the radar for a less-technical audience

I need to rewrite some stories that are told in a technical
context, but for a less technical business audience.

Accessibility has been an important consideration for organizations
for many years. Recently, we’ve highlighted the experiences of our teams
with the ever-growing set of tools and techniques that add improved
accessibility to development, and several regions our teams highlighted
awareness of these techniques via awareness campaigns. We’ve featured
accessibility-related blips on continuous integration pipeline
development, [design
[intelligent guided accessibility
[linting](/radar/tools/axe-linter) and [unit
testing](/radar/tools/ibm-equal-access-accessibility-checker). Growing
awareness around this important topic is welcome; techniques that give
more people access to functionality in improved ways can only be a good

Can you rewrite this in the form “what is it” (one or two sentences)
and “business context” (one paragraph) ?

What is it?

Accessibility has become increasingly important for organizations,
with a growing set of tools and techniques available to improve it in
development processes and awareness campaigns promoting its

Business context:

As businesses prioritize accessibility, they are adopting various
tools and techniques that make their products and services more
inclusive. These include continuous integration pipeline development,
design playbooks, intelligent guided accessibility testing, linting, and
unit testing. Embracing accessibility not only benefits a wider range of
users but also enhances a company’s reputation for being socially
responsible and inclusive, ultimately fostering positive outcomes for
both the organization and its customers.

Can you describe ‘accessibility’ in one sentence?

Accessibility refers to the design of products, services,
and environments that ensure people with disabilities can effectively
and easily access, use, and interact with them.

Based on this, what advice would you give businesses around

Businesses should prioritize accessibility by designing and
adapting their products, services, and environments to be inclusive and
user-friendly for people with disabilities, thereby demonstrating social
responsibility, enhancing their reputation, and reaching a broader
customer base.


I was very happy with this output. ChatGPT provided a
very good “business readable” version of the Radar theme and this
definitely saved me some time. I thought the advice it generated
was pretty good.

Avoiding over-reliance on AI-generated content

I’ve also been experimenting with ChatGPT for coding purposes,
specifically to assist me in learning new technology stacks (a subject I
plan to explore in a future article). On a few occasions, GPT-4
had downtime during a session, which left me feeling somewhat
at a loss—my AI “companion” had suddenly vanished!
GPT-3.5 was still online but it isn’t quite as good;
I much preferred to use GPT-4. This highlights the fact
that it’s surprisingly easy to become dependent on these AI tools. Here
are some tips to maintain a critical perspective and ensure high-quality

  • Evaluate AI-generated content: Always scrutinize the AI’s
    output for accuracy and relevance. Consider whether you agree with the
    content, if there are any factual errors, or if there are implications
    you might not endorse.
  • Identify what’s missing: Analyze the output
    for any missing nuances or specific points you would have made if you were
    writing the piece yourself. It can be challenging to spot these gaps once
    you have a seemingly complete piece of writing, but it’s an essential
    step in maintaining the quality of your work.
  • Invest enough time: Keep in mind that critically editing
    ChatGPT’s output will take time. The “AI productivity boost” might not
    be as substantial as one might initially think. If you’re unable to
    invest the necessary effort, the content might not meet your standards.
  • Take ownership: Remember that, ultimately, it’s your content and
    your name on the article. Treat ChatGPT as a helpful tool, but don’t
    forget your responsibility for the final output.

Leave a Reply