Context As A System

I sit down with Augstin Da Fieno Delucci, co-founder of Trilogica Global and former Director of Global Data and AI at Microsoft, to unpack a shift that changes how global teams should think about AI: treating context as a system, not a prompt.

We’ve all gotten better at generation, better models, better prompting, better fine-tuning. Agustin argues that progress is real, but it hits a ceiling when the surrounding architecture has no memory of what “good performance” looks like across markets. When context gets rebuilt from scratch each cycle, content performance becomes unpredictable, even if everything passes QA. We explore how to move beyond linguistic correctness and brand compliance as the finish line, and start aiming for resonance: the words, framing, and emotional register that actually drive action for a specific audience.

Then we get practical. We talk about “simulation before shipping” using tools many teams already have, including semantic analysis, cultural inference, sentiment analysis, social listening, and vector databases that store market knowledge for retrieval. We also dig into what’s still emerging: the feedback loop that continuously refines audience models with real outcomes so your system gets sharper over time.

Transcript

Copy Transcript Copied

Welcome And Guest Setup

Stephanie Harris-Yee 0:00

Hello, welcome to Field Notes. I'm Stephanie, and today we have a bit of a special episode with a special guest. So we have Agustín Da Fieno Delucchi, the co-founder of Trilogica Global, and former director of global data and AI at Microsoft, and someone who's been shaping global content systems for over 25 years. So today he's gonna walk us through something he likes to call context as a system. So really what it means to treat context as this living infrastructure rather than just a prompt, and then also what it changes for localization leaders. So, Agustin, thanks so much for joining us.

Agustín Da Fieno Delucchi 0:37

Thank you so much for having me here, Stephanie.

Why Prompting Hits A Ceiling

Stephanie Harris-Yee 0:40

So to dive in then, we've spent these last couple years in the industry really obsessing over some things about which models to be using with AI, how to prompt better, how to fine-tune things. And then with this concept, you've been somewhat arguing that this is the wrong conversation. So, what is that wall that you're seeing teams hit when they're focusing just on those things?

Agustín Da Fieno Delucchi 1:04

Yeah, absolutely. But let me actually reframe it slightly. So uh I think that it's not that the conversation about models and prompting is wrong. That works matter and it's deliver real gains. I think that the issue is that it's becoming insufficient on its own. Is that teams have gotten very good at generation, faster, more fluent, more scalable, and that progress is real and worth keeping. But there is a ceiling you hit when you're optimizing for generation in isolation from a much broader system. The output gets better, but yet organizations are still finding themselves surprised by how content performs across markets. And not because the generation has failed, but because the system around it has no model of what performing well actually means. It's a bit like guesswork.

Stephanie Harris-Yee 2:07

Yeah.

Agustín Da Fieno Delucchi 2:08

A pattern I see repeatedly, a teams rolled out AI generating product content across, let's say, 15 markets. Linguistically, it passes every quality check with flying colors. No doubt about it. But content performance across those markets is essentially unpredictable. Sometimes better than expected, sometimes worse. And the system can't tell you which of those in advance because it has basically no memory of what worked in those markets before, no structure model of how the audience is writing for, each generation cycle starts from scratch. Better prompts helped at the margins. But what is actually needed is a more systemic approach. One where context isn't reconstructed each time from scratch and passed along every single time. But something that lives in the architecture as a structure and let's say persistent operational data that the whole system infer from. And that's that's not instead of the better models. We still need those. It is what makes better models actually land. The two have to work together, and right now the context infrastructure side of that equation is significantly underdeveloped.

From Correctness To Market Resonance

Stephanie Harris-Yee 3:34

So you framed this whole concept as like the next step of progression. After 40 years, we had linguistic control, we had process context, then content systems, data-driven context, now generational AI. So this would be that next shift to have that contextual ecosystem, shall we say. So, what do you see as a little bit different about this shift as compared to things in the past?

Agustín Da Fieno Delucchi 4:02

So every previous shift, I think, was about getting closer to the content itself. More control, more consistency, more scale. Translation memory gave us linguistic reuse, style guides keep giving us process control, content management is giving us structure. But data-driven approaches give us feedback signals after the fact. Generative AI is giving us the ability to produce at a completely different scale. So each step is real progress, and we're seeing it. But they were all still about the content artifact. The sentence, the segment, the asset. And the bar with measuring against has always been essentially the same. Is this correct? Does it comply with the guidelines? Does it really pass the style check? I think those guard rates are still necessary. And I want to be clear about linguistic correctness, brand compliance, regulatory adherence, those don't go away. They still need to be there. But they are a floor, not a ceiling. So for a long time we've been treating the floor as the goal. Think about you know, a major retailer manages seasonal campaigns across, let's say, 20 markets. Today, even with sophisticated tooling, the approach is essentially produce content, localize it, ship it, and wait to see what happens. The feedback loop is reactive. You learn something went wrong when the market tells you it did. What becomes possible now is to move well beyond correctness. The model that campaigns against structured market data before it shifts. Well before it shifts. And it shows and surfaces not just what's technically compliant, but what's actually going to resonate. Which words carry the most weight for this audience, which framing drives action, and which one gets ignored. And that is even before a single asset goes out. And that's a fundamentally higher bar. We are not just getting better at producing content. We are starting to get serious about choosing the content that matters for a specific market at a specific moment. And that is a new territory for the industry at that level of detail. Of course, with all the assets we have today, there are more generic indicators and there is responsibility about it. But the opportunity to unleash all this extra stuff is big.

Simulating Performance Before You Ship

Stephanie Harris-Yee 6:49

So this concept of kind of simulation before shipping, even, so predicting how content will land in the market before it goes out, what does that actually look like in practice? Is that something that's real today, or is it something that we're heading towards?

Agustín Da Fieno Delucchi 7:07

Yes, and it's partially real and partially where we are heading. And I think it's important that we are honest about that distinction. We can today build structured representations of audiences and markets. Not just demographic data. We are talking about behavioral patterns, linguistic preference, emotional registers. What resonated and what's fallen flat? We can track that. The technology is making this possible right now are things most teams already have access to. Large language model, semantic analysis, cultural inference, vector databases for storing and retrieving market unloaded knowledge. Sentiment analysis, you can do that on social listening tools that we all use that feed real behavior signal into the system. And also structured data schemas that formalize that we know about given markets into something that we can actually interpret. What's less common is the architectural discipline to connect those pieces into a coherent system rather than using them as isolated tools. And I think that's where the main difference is. We can run content against those models before deploying and then surface those risks. Cultural misalignment, semantic drift, register mismatch, all that. But if you're launching, for example, a financial services campaign in Brazil and Japan simultaneously, let's say. A structured content system can flag before anything is published, that the directness of the call to action is likely to read aggressive in one market, and the visual metaphor anchoring the copy carries an unintended connotation in the other. And that's no guesswork. Is the system really interpreting model a model to of those audiences that has been built and refined over time? And today that kind of signal often comes from a human reviewer after the fact. And it comes, if it comes at all, I think what is still developing is the feedback loop. This ability to continuously refine the model, to retrofit based on the actual performance. So the system gets better at predicting outcomes over time. And that's the full version of it. It's closing the loop and finalizing the circle. And we are not uniformly there yet. But here's what I would say to someone skeptical: the organizations that start building that content infrastructure now are accumulating something that really compounds. Every market signal, every outcome, every data point and refinement goes into a system that gets sharper. And not just by updating translation memory, not just by updating terminology, by updating real market signals. The ones waiting for the technology to mature before they start building will be starting from zero when their competitors are already operating from a significant base.

Stephanie Harris-Yee 10:12

So

A New Week For Localization Leads

Stephanie Harris-Yee 10:13

let's bring it back to say like the localization manager, right? So you talk about these sort of experts who are now moving from that reviewing the outputs to then designing the system from the end of the line to the instrument panel, as it were. For a localization lead listening right now, what does this actually mean for how they would spend their week six months from now?

Agustín Da Fieno Delucchi 10:35

Right. It's a great question. So the two things that I have very practical. The first is going back to the drawing board and how context actually travels through your pipeline, to your workflow. Now, not how it's supposed to travel, because we know that we all have uh ideal situations, but how it actually happens can be different. So map it. That's important. Where is it that the context is created? Where is it handed off? Where exactly does it get dropped? Most teams, when they do this honestly, find the context is being reconstructed from scratch, if at all, at multiple points during the public, because there is no persistent place where it lives. That map is your starting point. It tells you where the architecture needs attention. The second, I think, is like look at your current system and ask honestly whether they can tell you or they can anticipate performance. Not measuring it after the fact or separately, but modeling it before the content gets goes out and is created. Can your system tell you really before deployment that a given piece of content is likely to underperform in a specific market? If the answer is no, that's the gap you're designing towards. So six months from now, a localization lead doing this work isn't spending their weekend reviewing outputs. They are asking, what does the system know about this market? What is it telling us before we ship? That's a fundamentally different professional orientation, and I think a significant, more valuable one, where you are looking at the signals that the system is doing, understanding why, and then modeling the system to actually do that. And that requires a lot of also linguistic effort in fine-tuning, but most importantly, it's about understanding your market, understanding where you're going, mapping that into your brand, into your contest goals, and all

Where To Follow The Work

Agustín Da Fieno Delucchi 12:50

that.

Stephanie Harris-Yee 12:50

We're about out of time and we've just scratched the surface here. So is there somewhere online where someone could go to either connect with you or to learn more about these concepts?

Agustín Da Fieno Delucchi 13:00

Yes, absolutely. I think the best place to start is LinkedIn. I publish regularly on this work, including pieces of the framework we've been talking about today. And if you want to go deeper into what Trilogica Global is building in this space, the website is Trilogicaglobal.com. And there is context there on our approach to global content systems and where this work is heading. We are also developing more formal published materials, articles, additional talk sessions. So following either of those channels is perhaps the best way to connect us.

Stephanie Harris-Yee 13:37

So yeah, we'll include those links in our episode pages. So yeah, feel free, go ahead and connect with him there. Okay. Agustin, thank you so much for joining us.

Agustín Da Fieno Delucchi 13:45

Thank you so much, Stephanie.