Episode 39: Decision Records for AI

You look professional, Vincent. I'm I'm
I haven't seen the side to you.
>> Let's level up this podcast. Yeah, let's
start to draw diagrams directly on the
whiteboard. But was that in in in mirror
for you or was it like not mirrored? Cuz
for me it was mirrored.
>> Sorry, I wasn't looking to like one
topic. One topic I want to get to you is
tech debt, right? Tech. Oh, yeah. It
looks great.
>> Belle,
>> does it?
>> Yeah. Okay.
Cool. Well, this is good.
>> If I can get this room cuz I I just dro
dropped into It's a pot. It's a working
part.
>> Okay. So, maybe for the the context of
our avid fan base
>> of one.
Hello. Thank you for watching. Hello,
Fred.
>> It's been like a month since our last
one. So, what happened to you? You got a
you you got a you got an on-site job
now.
>> Can you can you describe what happened
to you, Vincent? is for me nothing much
has changed really.
>> No, I I I have an office that I can go
to and I can meet people now which I
didn't have for the last 6 years. So
maybe I'll be le less of a recluse. I'll
I'll learn to behave.
>> No, don't don't say that cuz my my
client has has done one of those like
return to office type policies and like
>> No, no, I said I didn't say I said I
have an office I can go to. It doesn't
mean I have to be here. Like a lot of
the colleagues right now are not here.
>> Yeah. But usually they're here on
Wednesday.
>> I guess I maybe I jumped the gun there
though.
>> It's good to be in office to some
respect, right?
>> Exactly. That's what I wasing.
>> Yeah.
>> How's it going? Are you still in
probation period? And
>> yeah, I'm just having fun, right?
Probation. This is it's just the best
time to have fun, isn't it?
>> What What What is your What is your
role? Can you talk about your work or
you can talk about other things?
>> My role is the most ridiculous. I see
myself. Let's see. Let's say how I saw
the
>> I see myself.
>> My title does not see me.
>> Well,
I'm not going to say much, but I see my
my role more as like focused on
approaching AI adoption from a platform
perspective. So the the tricky bits is
that of course they already have a
massive platform team even a dedicated
AI platform team. So when I joined I was
quite
scared but I saw gaps and I feel like I
can
I can address some of those gaps. Let's
see how long my view survive.
>> So which gap are you working on?
>> You can't say. trying to
highlight where agents struggle in
existing pipelines systems like you know
you have an established it's it's it's a
highly
sensitive environment. So compliance
requirements and so on. So there's a lot
of of of blockers there that are there
for a good reason, right? It's not a
startup where you know you want to
deploy in as to to production as fast as
possible. there's a very strict choke
hold that uh the platform team has for
good reasons. So that's kind of like the
probably the most challenging part
being, you know, I wanted to be focused
on AI adoption even though lately a lot
of people are like
really anti-AI more. I feel like I don't
know maybe not not in this company but
like generally I think the people I
think
>> I'm willing to accept that there there's
certainly places where you want a human
in the loop though at the same time like
given an incident or given a
given a use case you want you want the
agent to be unlocked to be able to
perform it in a reasonable
manner in a sense. So it's it's about
signal versus noise. I don't I never I
never said that I want to take humans
out of the loop, right? It just where
does I think auto mode is a great
example. Auto mode was able to re reduce
the sign the noise. We don't just press
enter on every prompt. It's able to
surface very clearly where your
attention is needed. It says like hold
on, you know, agent is doing something
here. Uh that probably shouldn't be
happen.
>> So the signal wasn't that great there.
>> Yeah. Interesting.
Yeah, there there is push back from AI
from from some people that I I I went I
went to like an on-site the other day
and met my colleagues. So, it was
interesting to have beers with them
because you know then you hear people's
>> behind the scenes
>> hopes and fears around AI, right?
>> Yeah.
>> Yeah. So,
to to jump into one topic I was keen to
hear from you about
tech debt.
How do you do you have any tips? Like I
remember using a a a SAS service uh back
with an Italian client where where all
the vulnerabilities were like brought in
but I think data dog can do this but
anyway all the vulnerabilities were all
brought into one dashboard
single pane and we'll able we were able
to like sort of accept the risk or you
know prioritize which ones we're going
to do. I just had I just had to ask you
quickly if you had any experience of
using data dog or something else to
manage a whole bunch of vulnerabilities
or or tech debt. But the since I'm in
security the tech debt just seems to be
out of date dependencies essentially.
I had quite a few discussions lately as
I'm you know coming into this new role
and talking to people about the business
value and like I think it's it the way
that the team the team I work with uh
sees tech is more of like a ceiling of
capabilities. So as you as you deliver
work you're you're you know elevating
the ceiling of capabilities
and until you hit the ceiling you're not
forced to make changes on those like the
ceiling may be you know able to handle a
certain capacity cuz tech in general is
not just about security vulnerabilities
that are pending. It's also about like
you know we're we're every week we have
to reset the database server because
there's this background job or we need
to truncate the logs.
>> Yeah. and and things like that are, you
know, generally
>> I like this analogy of the ceiling,
the ceiling because I'm assuming you can
use that as a as a metaphor to describe
that your team has essentially too much
toil, right? And then you need you need
to you need to uh be able to lift that
ceiling by adding I don't know a new
team member or uh addressing the tech
deb otherwise you're you're over
capacity or something. I don't know if
if you if I if I understood your analogy
correctly.
>> It's it's more of capa of capabilities
of the of the architecture and the
software not not just the team. So when
you I I can't claim this the way of
looking at at at um at at software and
software development
that view is not mine but I do like the
way that it reframes because the way
that like Google and S sur identify
sorry or define tech that it's more
about you know your error budget and
other things that trigger uh refactoring
or trigger different like maybe a code
freeze cuz cuz what is like that, right?
I have a lot of arguments in previous
companies where I go like, oh, you know,
this all of this bash, this massive bash
script that runs on our deployment is
like that. Like, we need to get rid of
this. We need to split up the deployment
pipeline. We need to support parallel uh
because it's a microser architecture, we
need to support parallel deployments and
things like that and and dependency like
a proper mono build tool. And then they
my my my team lead would be like no,
>> it works. It's not that bad. you know,
it's it's all of that what you mention
is nice to have.
>> Well, in my context, it's it's like a a
large organization,
lots of teams, and what's happening is
that we get these alerts from different
systems that that dependencies are out
of date or or are vulnerable. So, that's
that's that's my take there. And
>> that's just one. Yeah. I mean,
>> and to be honest, I kind of roll my eyes
because many many of these internal
dependency many of these systems are
only internal and many many of the the
the dependencies
are super low risk in my mind, but they
but they're flagged as high or critical
and uh what I'm struggling to do is just
essentially and I've done this before. I
feel like an idiot for not remembering
how I did it. Is is to to essentially
manage them and and govern them and and
be able to sort of flag them as like
accepted. I'm disregarding this these
ones because it's, you know, it's
internal. It's like a system. Or maybe I
have to maybe I have to be real and say
like, hey, this team doesn't exist
anymore, I'm afraid to say. and it's
running like it is and we just don't
have the the uh capability to update
this one.
You know what I mean? Like I'm I'm
looking for that sort of
governance tool more than anything else.
I mean, yeah. I mean,
>> and the same
>> when we were looking at twist lock back
at a long time ago when I was setting up
for for the Singapore government
integration like we were start cuz they
have like this IM8 requirements. What I
wanted to get to is they have like a IT
standard that they're they judge
architecture upon and you must you know
be compliant uh for example have a three
tier architecture have the the limit the
DMZ zone only allow ingress on your data
layer on a different you know that's IM8
back then
>> and one of the requirements was with
twist lock and and intrusion detection
and prevention so IDS and IDP
So you need to detect and but also
constantly scanning for like workloads
and vulnerabilities in those workloads.
And one of the most you know advertised
features of some of these platforms I
was looking at at the time Aqua Security
Twist Lock the
>> Familiar with Twist Lock but what is
that? Twist Lock. They were acquired by
I forgot they were acquired by a big
brand but they were an Israel security
startup and there was another one Falcon
from Sysdig. Yeah. Sisdic Falcon. Those
are the ones that I was evaluating
because we're a Kubernetes cloud native
platform. And so one of the hardest
things is like hey Kubernetes you have
this massive cluster that runs all the
workloads patch jobs and all. But then
IM8 is like very strict. You have to
have your ingress layer living on
completely separate nodes with like
network access control lists and if you
have a Kubernetes cluster that's hard
you know even if you you you taint
ingress nodes so no other workloads can
live on it how do you ensure that
nothing tolerates the taint and runs on
the on the ingress layer anyway. So you
need to have some web hook and admission
hook and and all kinds of enforcement.
So with twist lock we were able to to uh
achieve some of that.
What I was trying to get to was that the
security reports like what you say we
running core OS which was like this
super you know container.
>> Yeah. So so the kernel like it's a very
minimal host operating system
>> and and and a very upto-date kernel
because it's like very aggressive uhly
upgrading updating as well. It's very
security focused right? I mean the
company before they
>> who didn't they join? No, they they were
acquired by Redhead and then their
Kubernetes Yeah. solution wasn't was
basically replacing Red Hat Open Shift
replaced Tectonic.
>> Yeah. I mean I mean I'm assuming when
you run Kubernetes on the cloud it does
the same thing as Chorus, you know,
>> but chores was cool because you could
have got got the same feeling on your
own machine. Cor the the the biggest
thing that Coros did was immutable
architecture with dual dual boot. I
think we talked about this in a previous
>> Yeah. Yeah. Yeah. We did. But but
>> but what I was getting to is the
security scanning and the reports and
the twist lock vulnerability reports.
Exactly. Your problem, which is like
being able to to to flag certain
critical findings as you know, you have
to put the reason why it's not yet
addressed, right? or you have to put it
in like a backlog and and a timeline
against when it going to be addressed
and we we we twist lock helped you with
those things. The big selling point of
those frameworks was to like hey you
know most of these solutions definitely
if you go open source they just it's
very easy to get like a full scan of all
of the possible vulnerabilities and drop
and and and dumped at you. But then what
the differentiator is for the commercial
offerings is to basically help you with
exactly that like that's where they are
you know making you pay
Yeah.
Okay. I I I have to do some research. I
was just I was just hoping that you had
a quick solution for me.
But I mean, yeah, I'm sure I'm sure I
get there. Hey, I wanted to show you
change the topic to something that I
might have talked to you about about
decision- making in an organization.
So, maybe this is just me having a chip
on my shoulder as we say in English. I
don't know what you say in Belgian.
though I'm often irritated
by it's not just my own employer. It's
like the different clients find it very
curious how they poorly communicate a
policy, right? Like you you were talking
about the public sector earlier where
they had like IMA IMA they had like a
like a good spec and I think Singapore
Yeah. Like for the most part there was
good leadership and good leadership for
me is essentially very boring and it's
basically writing things down and
sharing what that that writing is and
making sure everyone's aligned on that
that piece of writing. So the thing that
I've noticed in many in many of my gigs
is that you might have a town hall or
you might have like a social media post
nowadays like like a leader saying like
oh we are changing the policy on this. I
hope you feel comfortable this if you
have any feedback but like he might not
like you know since these different
mediums like you know like a YouTube or
a like a confluence and or work vivo or
they're all they're all like kind of
different mediums difficult to to track
a but but they usually don't have a
single source of truth they don't have
like a
a a URL like you know companydecisions
do whatever.com/
the decision.
So, this inspired me to to basically
vibe code.
>> You you shared the link.
>> Yeah.
>> Right. I was just going to open it.
>> Yeah. So, this basically just inspired
me to to vibe code something. And yeah,
like I I don't know. Do you think I'm
just making a mountain of a mole
molehill? Like I it's it's the same
thing. Like I'm I'm sure you know what
architect architecture decision is,
>> but it's the same concept like
essentially you make a decision, you
have a URL,
you you you copy it around and and of
course in my mind good communication is
repeating the message saying like you
the same message all the time, but like
hey if you want to know more check out
decisions whatever and you will or
follow this QR code and you will get um
you you will uh
see see exactly all all about it. So I I
did go a little bit crazy. I did even
define a schema
and make sure that and when I build it,
it sort of like validates it. You know,
you can have like it like an RFC or a
W3C spec. You can have like whether
>> does it does it have an MCP?
>> No, it doesn't. But it it has an
endpoint and an LLM's text. It generates
LLM's text. Dude,
>> does it have like an open a API or some
other schema
>> to validate it?
>> Uh yeah, it's it well it's it's just got
a YAML schema. So when you when you
actually write the decision, you you
mark it up and it validates that these
fields are are are set and that's about
it.
It's like ADR but uh but then I guess
but
hosted.
>> Yeah, it's self-hosted. You could all
you need to do is
well ask Claude to build it or or run
this build py or this make file.
I I mean it's never mind the
implementation but but do you often feel
that communication in a company is could
be better or I mean have you seen better
communication than what I'm envisioning
here?
I mean
I'm in an environment now where
I talk to many people like one of the
biggest issue is is is not just you know
tracking decision records but basically
feeding context to agents because
ultimately the decision records are
possibly some of the stuff you want to
to have agents access to right it's
desperate it's completely separate you
know confluence bitbucket uh sorry
GitHub code like uh it's all over the
different repositories maybe there's
some in Slack so what we are focused on
is I think one of the biggest issues is
also the same data is being represented
in different ways and and and you know
documents run out of out of sync like
the problem you had in a previous uh gig
where you say like we have a whole bunch
of confluence articles and we want to
ingest them
>> into like a markdown database managed by
agents and agents can generate multiple
views Yeah, of that same markdown.
>> And and just for the context, we
actually unleash
did that migration, but the trouble is
that the the AI agents sort of made the
the content in markdown somehow
repetitive
>> like the broken mirror of different
views.
>> Yeah. And created more noise than than
what we almost had originally. I mean,
>> and that's a common problem, right?
>> It's a common problem. Even if you use
spec driven development, one of the
first issues you're going to face is
that you you write something down in
your specify like in your original user
stories given when then acceptance
criteria and then when it comes down to
you know implementation the library the
technical you know the the API routes
the data model.
>> Yeah.
>> And then when you go down all the way to
the implementation plan the phases
that's the same information.
>> Yeah. that that points back to like this
task needs to be implemented because of
this um this task exists because it this
acceptance criteria
>> needs to link back to that source of
truth otherwise there's there's an so
what happens is you get like 20 markdown
files on disk and they end up
disagreeing there will be inaccuracies
because of different terminology used
across the documents and so so that's
where I I then was like okay Matt PCO he
he solves it using the his um drill with
docs with domain language. So you
establish the terminology so that the
agent can only write documents with that
terminology.
>> Yeah, I remember that video that Yeah.
Establishing a terminology is so key,
isn't it? Yeah.
>> Yeah. So so then once you have
established a terminology, it also needs
less tokens. I mean I like what he's
saying there cuz everyone wants less
tokens and hopefully as a human you also
can read and understand it faster
because you have a shared language. That
should reduce the number of
inconsistencies across disk and across
conference and across sources. But then
you still have the problem that you know
a data model is a data model. It's it's
it's one set of of it's one set of
information and then re you know
visualizing that data model as tables or
or visualizing it in a in a sequence
diagram uh explaining the interaction
between systems and and the impact the
mutations that happens on the data
model. it's the same data model and and
and those run out of sync. So I don't
like I talked to a friend and their
solution to to solve the context problem
for agents and also Google's OKF which
is like a a markdown on disk. I think
that's not the right way. I think you
just end up with the same problem that
you had with your confluence. uh you
know you have a thousand different views
of the same even if you have a shared
language the LLM is non-robabilistic
sorry it's probabilistic
nondeterministic and it will just create
different you know slightly different
text and the data is the data
yeah I get that so don't don't you think
that that thing I just showed you
decisions
which is consumable by AI agents because
it has LLM text I purposely one view
>> it's just one view of the data. It's
just an ADR view of the data. There's
actual data behind it and that's the the
thing we need to to to to capture.
>> What do you mean like the the data
structure and like the detail some
further details? You mean
>> you may you may you may have an a
decision record and I don't use them
that much but it may
modify a data model. So the problem that
that I think a lot of people now are
trying to solve with what they call
ontologies is to to try and model this
and there's a very good talk from I
think AI engineer conference from a
professor who talks about expert systems
back in the '90s and the concept of
ontologies and how that applies to
context management for agents and and
they basically when they talk about
ontologies they talk about a not a
relational database or or or a view on
markdown but actually a graph with
relationships cause it.
>> Oh yeah, I noticed that in my feed,
maybe serendipitously,
there's a lot of talk about marrying a
graph database with your harness.
And that's exactly what Beats is, right?
I mean, if you think about Beats, it's a
it's a graph. It's a node of graphs.
Sorry, it's a graph of nodes. It's a
graph of nodes of type issue, of type
feature, of type epic. and they have
relationship uh blocked by um sure and
and and and and basically
>> that what's make beat so interesting
because you create a graph of tasks and
uh you leave comments. It's also another
node type and
>> that attaches to it.
>> You're right. I never actually made that
connection. Well, I I feel like I just
want to go go back to basics. Like I
want I want there to because because I
think
leadership in typical companies won't
won't uh even probably even grock beads
but they might grock a web page
you know and then and then from from a
decision maybe maybe you can have a like
a bead link which would have more
details and you gradually you have
progressive disclosure essentially
>> and you can see with beads like the
agent is really good that creating the
task and managing dependencies between
them, seeing which and doing a query on
the graph to find out which tasks are
on, you know, not blocked. But what you
can also do with beats is you can
generate a conbon board from it. You can
show a user which status all of the
beats are in.
>> Yeah. Yeah. You can you can sorry
>> another one that you can do is you can
show a like if you if you know the hero
and you see the the phases and the tasks
you you have a markdown document with
little check boxes when a task is done
and and you can that's like a tree view
because you have like phase and then you
have all the task you have subchildren
you can do that with beats as well right
that's basically what I was doing with
pal the the two I was just I was showing
like here's my task graph here's a tree
here's the phases here's what's
completed I can see it in both views and
because it's a one set of data. You can
get like different views from from from
beats.
>> Yeah, I guess I' I've been using beads
myself just internal to my own little
projects and I love it and I find it
useful. I haven't I haven't managed to
get my my my my team or my colleagues
adopting that sort of flow yet. I mean,
have you I mean, you must have come into
this new this this your this company
that you now work for with a ton of
ideas.
Has any of any of your ideas been
adopted? Would you say like your your
adversarial reviews your
>> No, not I mean it would be arrogant to
assume that they are not doing that
already. They were already doing that.
Yeah.
>> I often find that like the policy
>> I wouldn't have joined the company if
they wouldn't be if I wouldn't be the
dumbest person in the room.
>> Yeah. Well, I often find that this I
there's things I like to do but my team
doesn't know about and it's very and
they you know there they use Atlassian
and for or Jira and then you're just
like okay now we now we're stuck or
I want to share this many times before.
>> Oh, what was that? I want to share my
screen, but Chrome doesn't have the
ability to to uh share. You have to do
that. You do have to
>> Maybe you can share it. I'll send you
this the link. It's a
>> Are you sharing it with me? WhatsApp
hopefully.
>> No, no, I'll sh I'll share it on this
chat here and Riverside.
>> Oh my god. I don't even know where that
chat window is.
>> I don't have WhatsApp on this work
laptop.
>> Oh, okay. Okay. Okay.
I'm going to share the screen.
Paz. Oh my god, they all look the same
these sites. All right.
Where people in agent share one
understanding. Yeah. Right.
>> That's what we were discussing
basically. Right.
>> Yeah. I mean this this are several
implementations like the misilla cq cq
is one one that I've cq is one that I we
talked about in a previous pod where I
was really impressed by by uh misilla's
approach because they had these tool
calls like validating the the knowledge
uh the knowledge
I'm not too sure what they called them
now
uh and I thought that was quite powerful
But what what I'm trying to say here,
Vincent, is that there are lots of cool
projects, agent friendly projects,
though I'm looking for a way where we
start essentially with an idea like an
old idea like the ADR and then
progressively build on that using I
don't know something like this or beads
or whatever, a graph database. But it
but you must understand like I'm super
frustrated when when clients or or
different companies they just don't have
a central point. This I'm just looking
for a source of truth at this point. And
that and that's that's step one in my
opinion. Get a source of truth and then
the rest will follow.
I'm trying to see if CQ is using a graph
relationship. Um well you know beats is
also in um built using SQLite right it
represents nodes within the graph using
tables and the relationship tables and
so on. So you don't need a graph
database. But um I never used graph
database before. But in terms of like
what you just asked me of of like being
uh frustrated. I mean I think beads
it's I I got rid of it right. I replaced
it with my own implementation. Um but I
mean the idea I think under the hood the
idea of graphs and nodes the problem is
they're very very specific. Like Jira
has it right? I mean beats all look like
me like Jira right you have issues you
have child issues you have epics you
have features there's all different
nodes of different of of different types
and the relationship that can they can
have with each other so I don't think
you need to move out of those existing
platforms like when I I built spec
ledger I was like I hate jer I hate
conflence I think those systems are
horrible all you need is markdown on
disk and then I learned like the broken
mirror issue of everything is like
running out of out of sync and it's not
uh easy to manage. I think this this
approach of building ontologies for
companies to build uh graph data like
graph relationships of how things link
together and then building on top of
that that's very interesting but it
still requires you to move out of those
existing systems and I think the focus
of a lot of the like even cloud tag and
and you know the way that people are
building is to to lend those AI systems
in the tools that humans used to use use
today.
>> Yeah. And I think that's that's the
realistic approach is to get AI to live
where the humans live.
>> Yeah.
>> Yeah. I mean that's assuming like
well like
I I've I've personally noticed that in
some clients that even decisions are not
recorded properly in Slack cuz Slack is
more of like a informal space or they
they rather jump on a Zoom call or what
have you to explain what the pol what
the decision is
I mean I guess I guess it's maybe it's
maybe it's just a symptom that many many
of the clients that I work for are not
like you know
very mature software company so so
leadership in a sense is not used to cuz
like like what do you what do we do as
software engineers we we essentially
codify the business requirements but
sometimes and and that's the job but
like a and maybe we should take
responsib responsibility for just
writing down these decisions. Though
what I'm trying to say is that many many
times that like even Slack doesn't have
the context because it's it's in some
executive's head or something like that.
And like just just like I like what just
the fact that some I'm trying to think
of the name of the guy there was a a sun
executive a guy with a ponytail. I can't
remember his name now. He used to just
write blogs and and I think of course
>> J no the and then of course of course
like I think Jeff Bezos is is also good
a good example of course his blogs are
more internal but he just releases these
memos and then it's clear to the rest of
the organization what what we're trying
to achieve here the memo is the
memorandum and it's clear I just that's
what I'm I I I miss a lot of the time.
Just a blog, you know, we talk about
Jira, we talk about all these graph
databases, but like just a blog would be
so refreshing in this darn age.
And that's where I'm at. That's that's
my frustration.
>> So, you want your CEO to blog
>> essentially? That would be that would be
so awesome. But
>> I did have one co at some point that had
a blog. Yeah. at at Goodnotes, the the
the the the founder, he wrote blogs
about like what he learned, how he saw
the company evolve, how he saw the
ecosystem evolve, what he he believes
was like coming next and he he he shared
them and yeah, they were insightful.
He's a smart he's a smart. This is the
stuff I really miss cuz like when people
do their little demos on Zoom and the
Zoom recordings and no one can ever find
the Zoom recording cuz for some bizarre
reason Zoom makes it impossible to find
Zoom recordings. This is there's so much
context that's lost and hope and if we
can just start with a single portion a
blog and then progressively disclose I'd
be so much more happier and less
confused all the time. And and and it's
not so much me being confused.
It's like when you work with AI, when
you work with agents and you notice that
it doesn't have the context, you're
like, you're frustrated and like, how do
I get the context here? I have to copy
it here. I have to I have to summarize
this video for it to know what we're
talking about for this particular
activity or job that we're trying to do.
And
you know, context engineering for for me
is almost like the frustrating
experience of just gathering bits and
pieces from colleagues and what have you
to try and work out what the decision
was.
And then then when I've got it all
there, I'm not even sure it's right
because people have said different
things and what have you and things have
changed since then. Yeah. Anyway, that's
that's my rant. Yeah. Awesome.
>> Yeah. I mean, I think with agents and
the amount of, you know, these large
language models, the amount of text that
they produce and the inconsistency
between the text and and every human now
being hooked up to one of those one or
more of those generating more and more
text. I don't think the pro the the
solution is going to be solved easily by
by large text document. Apparently, when
they look at usage of these LLM, a large
part of it is write like a very short
status update that gets converted into
like a massive long blob uh from like
hey cloud can we do a quick status
update and it creates like paragraphs of
text and then somebody else goes
simplify this. Hey cloud simplify this
like the LLMs are being used to to
generate massive amount of text and then
being used to gen to summarize this
amount of text again where like if you
want to that was one of the insights of
of of a senior like leader in the
company that I'm at he's like I looked
at the statistics of token usage and if
we want to save cost because it's way
through the roof let's start by you know
stop using LLMs to generate status
updates and and and and because nobody
understands them.
>> Yeah. Like one thing that I'm thinking
of mandating in my I mean I I mean I
have sort of mandated in my team. We
don't allow people to write with into
confluence documents with a with agents.
If you're going to write a document,
write it by hand
because because often
>> how do you enforce that? Uh well, you
can well you could theoretically disable
the right tool. Um but unfortunately the
whole the rest of the organization
doesn't share my my team's view or the
at least the views I project on my team.
>> Oh my god, I'm late for a meeting. I'm
sorry.
>> You you can just you can have some text
in the in the conference document like
agents do not write into this document.
That that also works. Sorry. Oh man,
there's some
>> Oh gosh. Do you have any time more
today? There's other things I wanted to
pick up on. Otherwise, I guess this is
the pod episode. What was the last one?
I'm sorry. I I didn't give too much
updates on, but but I have another call
and a meeting.
>> Okay. No worries.
>> That was episode 39. At least we we we
kind of got back together again.
>> Okay.
>> Okay. See you.
>> If we start on the hour, then uh it can
be it can be like 50 full minutes. But
>> yeah. Yeah. Sorry, I was but I'm on
holiday so I was a bit slow out of bed.
Okay, see you.
>> Okay, see you.