Our 120-Hour AI Media Buying Test for Black Friday

Like, what is the right lever to pull?

And how many more checkpoints do you have? Or is your team making to ensure that it's, you know, course corrected and back on track? So that was really foundational for, you know, can we build some type of traffic light system, if you will,

to look at hourly data and come up with the recommendations for what we need to happen. This episode is brought to you by Miracle Connect. When ads get more expensive growth, you can't depend on spending more for the same audience. Miracle Connect helps brands reach new shoppers through leading retail marketplaces with AI

powered catalog tools, more than 450 channels, and one place to manage your catalog and workers. Find out what's possible at miracle.com/ctc. That's Miracle.com/ctc. Hey folks, welcome to the Ecommerce Playbook podcast.

I'm your host Richard Gaffin. And I'm joined here today by McCay Rasmussen, who is one of our Senior paid media buyers here at Common Threat Collective.

“We're seeing your paid media manager, McCay is that right?”

Yep, that's right. That's right. But really what I'm saying is McCay is the brains behind a lot of how we're thinking about meta media buying specifically paid media buying in general, as we move into BFCM here. And so I've worked with McCay actually directly, we did Black Friday boot camp a couple of weeks

ago in person at our CTC offices, McCay was there, breaking down, paid media for everyone, being a rock star was awesome. And so we're going to have McCay break some of that down for you all today. And really the way that we're framing this is in 2026, how is meta media buying going to look different than it didn't 2025 and in fact, any previous year.

And I think there's some very specific reasons that it's going to be different.

But let's talk overall first McCay about, well, actually, first off, how are you doing?

Yeah, doing good. Excited to be here. I mean, Black Friday is around the corner. So we're getting into crunch time. Yeah, that's right.

Because this is going to be the hell week or hell couple of months here for your team. So I salute you for that. But let's, okay, let's go ahead and jump into a little bit about how this particular, again, this period coming up is going to look different.

“So tell us a little bit about, yeah, how's 2026 going to be a brand new beast?”

Yeah, yeah, I mean, I think one of the, you know, the elephant in the room, if you will, is the fact that now we have meta, MCP access. And in a lot of the other media channels are rolling out, you know, their LLM connections, which is just a way for us to talk to chat or cloud and, you know, do things in the account, whether that's reading, read access, which is pulling, you know, reporting,

or it's right access, which is making changes on our behalf.

And I think, you know, ultimately, that's going to be, you know, a big shift in how we operate,

moving forward, because whereas most of what has happened in the past, and I have some specific stats in terms of, you know, in terms of, you know, bid and budget changes, last year our team over cyber five made over 12,000 adjustments across the entire portfolio when it comes to bid and budget. And so now we think through, well, the decisions that are being made can be evaluated, the accuracy, precision, and timing of those adjustments, and whether they're, you know, most optimal.

So I would say that's probably the biggest change from a year or a year perspective, and that sort of touches all aspects. Yeah. So I mean, to kind of unpack that a little bit, that as we've said many times before, Black Friday is a different beast in terms of how you approach

“me to buying in that, you need to make a ton of micro changes across the course of,”

like you're saying, the cyber five in order to take advantage of the sort of waves of demand that happen over the unusual five days. So obviously, I think it stands to reason that an AI agent could make those decisions better and more swiftly than a human media buyer. That's definitely like a a drum that we beat a lot on this podcast. But so let's talk about a little bit about kind of how we are executing or deploying this specifically at CTC. Yeah, that's a great question.

I mean, it all starts with our belief system. And so at CTC, we have something called the Canon, which is just a roll-up of our methodologies over the last, you know, 10 plus years of operating at CTC. And in holding, you know, weekly monthly Canon meetings, wherever aggregating before portfolio level data, I'm to sort of influence, you know, what we believe should be true for optimal performance. So in terms of, you know, how we started building out the foundation

for, you know, analyzing Black Friday spend, you know, we looked at tens of millions of dollars and spend, which is generated, you know, hundreds of millions in revenue. And analyzed, you know, what happened last year? How can we, how can we find efficiencies within that process and and build upon that? So I think one of the things that stood out to me was when looking at the portfolio data is, you know, when, because we hold daily expectations, hourly expectations

at CTC, we have a really good understanding of where the shortfalls are by any given moment.

on Black Friday, like, what is the right lever to pull? And how many more checkpoints do you have

for is your team making to ensure that it's, you know, course corrected and back on track. So that was, uh, really foundational for, you know, can we build some type of traffic light system if you will to look at hourly, hourly data and come up with the recommendations for what we need to happen? Yeah, and that touches a little bit on, on the kind of a broader question, maybe,

“which is, which is, why not just let Meta handle it, given that we have access to the MCP?”

Obviously, we're not just running on autopilot. There's a certain amount of human intervention that it's involved. So talk a little bit about what, what that relationship is, like, what, maybe a broader look, what are the media buyers doing on an hour by hour basis, actually?

Yeah, it's a really great question. I mean, ultimately, you know, anyone has access to the Meta

MCP? Now, I think the caveat is how you tie in your out-of-count changes to what's happening on the business level, and so having expectations around, you know, things like MER by hour, and being able to even pull in, like, well, what can we expect for revenue by hour throughout the entirety of cyber five? So there's 120 hours that we have data collected for, in terms of, you know, how much of the revenue by this point in the day should we expect to have,

and we can sort of overlay, you know, our business expectations into what needs to happen in the

“out-of-count to get us that result. I mean, I think in summary, you know, it's always the context”

layer is super important, because you can't just have Meta go-off and make changes without also measuring what's happening on the business side. So you can think of it, you know, similar to how we thought about status, which is the hierarchy of metrics, right? Like, we're only making these changes if there's, you know, there's, like, a decision framework that happens on the back end for, you know, it's contribution margin and a healthy place is MER and a healthy place.

And then, you know, we start evaluating incremental return on return on spend in relation to our targets and expectations. So then, I think maybe the next way to help continue to clarify this or talk about it is just an example, right? So like, talking to me about, okay, it's, let's say, I don't know, it's 8 a.m. on Black Friday. What is your, like, what's an example of a situation in which, or maybe, how would, like, the media buyer and this sort of the AI agent interact

“in a given situation to sort of solve or fix or something like? Yeah. I mean, I think one of the,”

one of the benefits of leveraging, you know, things like LLMs and automations is the fact that they don't sleep, right? And so, um, we're in past years, you know, obviously people are down in red bulls

and trying to stay up as many hours as they can throughout cyber five. But the reality is, you know,

at some point there's, you know, times where the account's not being looked at. And those are the gaps that we want to identify and solve for. And so, you know, traditionally, I think, you know, teams during this season are online. However, we are going to have, you know, 120 hour monitoring, so every hour throughout cyber five is going to be monitored against expectations. And, and so when we think about how our teams interact with this, it is, you know, presenting the

information in a way that is very clear in that way, like anyone that's looking at the data will inevitably make the same decision. Because, you know, everyone can build dashboards on chat and cloud. But the issue arises when, you know, three different team members are going to make three different decisions. And so, we can actually make it a bit more black and white, if you will, based on the business context and the letters we have in platforms to make changes for us. And

soon back to, to give back to your example, it's ADAM on Black Friday. You know, we, we know that based on our, our data from our portfolio that we can expect, you know, about 27% of revenue to come in the door by that time. And so then we can just look at our target for the day. And if we're not at at least 27% of that target, we know that something's off. And then we just sort of identify, well, how off are we? Is it, you know, think of like a traffic light system? Is it, you know,

in terms of standard deviations? Is this a, like, you know, zero to 10% gap that we can close by taking this lever? Is this a more of a red light? We're like, hey, we're like, really far off something. Probably needs to change from a larger swing or potentially evaluating, you know, things like offer. So it's, it's all about ease of use and, and providing clarity for the team. That way there's continuity and decision making. And we can be precise in, in, in, consistent with

them. If you're ad costs are climbing and growth is getting harder, you need more than another campaign. You need more places for shoppers to discover your brand. Miracle Connect makes multi-channel growth simple with AI powered catalog tools that turn your product catalog into optimized listings across more than 450 retail channels while keeping your inventory pricing and orders in sync from one place. Expand beyond your own site without building a whole new

operation. Find out what's possible at miracle.com/cTC. That's Miracle.com/cTC.

just done in any other year in this year with, with the actually agentic aspect of this? Because presumably, if you're doing an hourly check, you can just do an hourly check and discover that

“you're 10% off. So what's the, what's the difference here? Yeah, I mean, I think the difference”

is really about the, the consistency and efficacy of the, the changes that are happening. So I referenced earlier on the call, you know, last year we had over 12,000 changes throughout cyber five. The question is, were those 12,000 changes that the right levels to pull in platforms? You know, can we can rely on every single one of those decisions to drive the best, you know, efficiency against target? And so trying to standardize that in a way that, you know, again,

referencing the business targets on top of, you know, what we're seeing in platforms to, to really tie it all together. So if I summarize like the differences, the fact that we have, unified decision making and the fact that we also don't have to wait for someone to make that decision. And so if that, you know, you know, for I am potentially before, you know, you're, you're more in person wakes up to go check on results. If the, you know, if we know that revenues off

“and we have an opportunity to lean into one of the campaigns based on the I rose,”

in our expectation of where that should be, then, you know, giving the autonomy to an agent to go ahead and make that increase for us. Right, the primary thing being like given the agent does have the authority in some cases to execute if you choose to give it that. And particularly like, oh, in the midnight hour, so whatever, somebody internationally is buying a product and you wouldn't realize that you're been able to jump on it. Previously, you're actually able to do that now.

Okay, so let's talk a little bit about then, and you've obviously alluded to this a few times, but the type of preparation that needs to happen before Black Friday. So clearly, parameters have to be given in a certain way in order for you to create a situation where you can trust the agent to make those decisions before I am. So talk a little bit about what those look.

Yeah, I mean, ultimately, this is the greatest responsibility of, you know, potentially

handing your LM access to your out account where, you know, you're spending real dollars. And so just as important as building a system where the guard rails around it in terms of analyzing the types of changes that occurred last year in the bounds of, you know, reasoning that we can sort of set for an LM to make a decision. And, you know, for a very drastic example, there's no reason why an agent would want to or should ever take, you know, a target row as and, you know,

move it to a 0.0, right? Like there are expectations that we have around, you know, the lovers we can pull. And so building a guard rail system in place of, in place of that to make sure nothing goes haywire and even on top of that sort of like an alert system, if you will, to just flag an

actual human to check things is, it was crucial during the build out of this. And on top of that,

“I think, you know, as people move in this direction of autonomous, you know, buying, et cetera,”

is the test that ahead of time, right? Like you, you want to get a good understanding of how it works before you go into peak. And so that's, yeah, that's, that's a, okay. So part of what we're what we're doing here is sort of testing the hypothesis, right? Like this idea that the incorporation of the MCP or of agentic buying really on BFCM is going to make it impact. So, talking to me about like how, what, what it is, what the experiment looks like right now,

what it, what it is you're hoping to sort of prove or the hypothesis you're testing. Yeah, I mean, I think cyber five is such an interesting time to, you know, overlay this,

this methodology, ultimately because there are such drastic differences from a day of

day perspective. I have a hypothesis at least at this point that it actually requires more human intervention than other moments throughout the year, right? And so, you know, if in evergreen, you know, period, we, you know, are sort of, you know, have really good understandings of what our target efficiency expectation is. You know, we're essentially trying to prove out whether more intervention that is, you know, unified under a clear framework is going to lead us to a

better or business result than, let's say, you know, just letting meta, you know, do what it does in terms of setting the target. Now, we do have, we do have data to point to that, right, and saying that, again, our team made 12,000 changes last year. So, we know it is the time of year where there are many, I would say, it is a time of year where the volume of changes is increased, and it's trying to, you know, find efficiencies within those changes, right? Because there are

so much, there is a lot of variability and how things get enacted based on what needs to happen. And so, ultimately, the hypothesis, you know, again, is like hourly decision framework around where are we at, where do we need to go and what lovers should be pulled? Is, is what we're after?

practicals and, and one thing I like to ask is like, if somebody doesn't have access to our tools, what's one thing they can do to get closer to that and start preparing for it, obviously, I would say,

“if you want to execute this in the way that we're executing it, the best way to do it is to become a client,”

if you're a seven or eight figure business. So, commentaryco.com, you hit that high risk button, you let us know you're interested in us building something like this out for you. But, talk to it for somebody who's not in that position or not currently a client, like, what,

what is the practical, tactical approach? Like, what's the first thing that you should do to get set up

for executing something like this? Yeah, it's a great question. I mean, ultimately, it all starts with with your beliefs, right? And so, I would say, because anyone can connect, you know, they're, their MCP to their ad channels and their Shopify, I would start by forming a belief about what your expectation is for the cyber five. And you can even reference, you know, what changes you made at what time's last year. And search to dig into some of the questions as to, like, well,

was this change, you know, impactful for the business? And so, it all starts with the forecast, you know, start there. And once you have your expectation for what should happen,

which is influenced, you know, by, by your marketing moments, et cetera, then you can search

overlay on, you know, the decision framework that you can try to automate. And so, I think, once you have the forecast and you can reference even last year's data, having a good understanding of what the reality looks like last year. And this is assuming, you know, your marketing moments are staying the same. In terms of, you know, how much revenue can I expect per hour throughout all of cyber five is a good starting point, because you can overlay this year. You know, again,

ADM, Black Friday morning, what happened last year by this hour? How much revenue is in the door? If you're not there, like, should start to raise some alarm bells for you. A yellow flag,

“if you will. And then just determine the weight at which, you know, you need to course correct”

to close that gap. So, it all starts with your beliefs and a foundation of your forecast, and then you layer in the action layer from that. Right. So, yeah, I think that's a good way to sum it up. That, like, there's, as we talked about before, the initial sort of forecasting prep belief part, which is determining what you think is likely to happen based on historical data. And then running on an hour by hour basis against that with sort of human oversight. So, um,

okay. Cool. Well, anything else you want to hit, okay?

No, I think that really covers it. I mean, ultimately, I would say, like, dig into, again,

like, with the MCP meta, MCP, um, you'll be able to have more clarity around, like, what was what happened last year. And so, we analyzed a lot of things in terms of, you know, from, from post peak day, from Friday to Saturday, from a cyber Monday to Tuesday, like, what were the observed changes, because we know that after the peak that conversion rate drops, and, you know, how can we best protect ourselves and the accounts from, from overspend or inefficient spend? Um, so having

again, again, a good understanding of what those peaks and valleys are will help you overlay some some decision making framework for what we think needs to be true. Um, and similarly, you know, even on the tactic level, when it gets that into, like, you know, what, what budget, uh,

“adjustments are making, what bid adjustments. I think we did a lot of analysis into, you know,”

the hierarchy of, you know, what actually produced better efficiency in terms of, you know, 20 far windows, and whether it was a bidder budget. And so, um, I would, I would tell, you know, anyone looking to replicate something like this is to have a really good grasp on what has happened in the past, not that it will happen in the future, but at least gives you a starting point to, to build some foundational work. All right, folks. Well, I think that's going to do it for us. So,

uh, if you're interested in us building this out for you, uh, you can work with us as, as a seven or eight figure brand. Hit us up, comment through a code.com, hit the highest button. We would love to chat some more, but all right, appreciate a McCay and thank you everybody out there for listening. We'll see you next time.