Podcast: Play in new window | Download
Subscribe: Apple Podcasts | Spotify | Android | TuneIn | RSS
Over the past five years, Lisa Jennings Young has pioneered the adoption of AI tools in content-design practices at Twitter and Microsoft.
Lisa has watched in real time the realization of the benefits of natural-language AI tools to help govern and create content, as well as to assist with content-design research and operations.
We talked about:
- her pioneering work with AI when she as at Twitter
- her thoughts on the important role that natural language processing (NLP) plays in content-design governance
- now natural language generation (NLG) can help content designers
- how she sees NLP and NLG helping her scale content-designer operations
- the principles that guide the implementation of AI at Microsoft:
- is it good for Microsoft?
- is it good for individual teams?
- is it good for our customers?
- how her work aligns with Microsoft’s strategic objectives
- some of the work that content designers do that she doesn’t see AI replacing anytime soon: stakeholder alignment, customer research, journey mapping, content ecosystem analysis, etc.
- how implementing AI tools has resulted in new communications opportunities with cross-functional partners
- the importance of prompt engineering skills
- her hot take on AI and content design: “It’s not about replacing writers, it’s about affecting them. So AI won’t replace writers, but writers working with AI will replace writers working without AI.”
Lisa’s bio
Lisa Jennings Young is the Head of Content Design for Microsoft Teams. She has over 20 years of experience creating content strategies that scale, with a passion for bringing life and voice to digital products. With extensive experience in process design, tooling, writing AI, and content moderation, she helps teams do more than write digital interfaces. She helps them create human experiences.
Before heading up Content Design for Microsoft Teams, Lisa was Head of Content Design at Twitter. While there, she built a team that set a global example for how social media can be more inclusive, accountable, and equitable for everyone.
When not spending time with her husband and four kids, Lisa loves to read nonfiction, tend her Oakland garden, and cook for crowds. Oaktown Spice is her home away from home. Her spice game is on point.
Connect with Lisa online
Video
Here’s the video version of our conversation:
Podcast intro transcript
This is the Content and AI podcast, episode number 8. Few people have had as good a front-row seat as Lisa Jennings Young to see the emergence of AI tools for content-design practice. First at Twitter, where she pioneered some of the earliest use of natural language processing tools in a content-design operation, and now at Microsoft, where she leads a team of content designers and technical writers, Lisa has led the way in showing how AI technology can both help content professionals and democratize writing skills for non-experts.
Interview transcript
Larry:
Hey everyone, welcome to episode number eight of the Content and AI podcast. I’m really happy today to welcome to the show, Lisa Jennings Young. Lisa is a principal content design director at Microsoft Teams, and welcome to the show, Lisa. Tell the folks a little bit more about what you’re doing these days.
Lisa:
Thank you so much, Larry. It’s great to be here. So yeah, so I am at Microsoft Teams right now, leading content design for that product. I’ve been there six months. I resigned from Twitter last November, so almost a year now. And yeah, I’ve been settling into Microsoft. It’s a huge company, getting to know the lay of the land, really connecting with my amazing team there. So yeah, so it’s been a good six months.
Larry:
Yeah, that’s interesting. I think when we talk historically, I think of you and I were just chatting a year and a half ago at Confab, and it was just a normal conversation about work stuff and things. And then we connected again earlier this year in February. I put together a panel for Tracy Playle, that Utterly Content, about AI. And you were the first person I thought of for that panel, because you’ve been working with AI tech, and you had been doing stuff at Twitter, and I know you’re doing it again at Microsoft.
So anyhow, I just want to observe that our relationship over the last year and a half has been a microcosm of all the craziness we’re all going through, watching this stuff evolve.
Lisa:
Yeah, we were just having a casual conversation and things changed.
Larry:
Tiny bit. Yeah. But the thing that’s been a steady across that is your interest in, and use of, AI. I don’t know, maybe talk a little bit about the stuff that you and Jordan had done at Twitter, because that was really interesting and promising.
Lisa:
When I first started at Twitter, one of the things… Because my career started as a tech writer. Then I moved into content strategy, enterprise content strategy, marketing websites, etc, etc. And so I’ve always been really interested in how you work at scale.
I had usually been a team of one, a content strategist of one or a content designer of one. And how do you really make an impact? So one of the first things I did when I joined Twitter was I put together a proposal for bringing in this AI platform I had heard about right before I left Advent Software called, at the time it was called Cordoba, and they’ve since rebranded as Writer.
Lisa:
But yeah, that’s one of the first things I brought in, because I really wanted to, we actually were a very small team then, there was two of us who were working on the consumer side of Twitter. How could we do that at scale? And I was very intrigued from content, brand adherence… At the time, there wasn’t Gen AI, there was one type of writing AI, this was back when I started Twitter, which would’ve been four, five years ago? Oh my gosh.
Lisa:
And it’s natural language processing. And especially at a place like Twitter, the words are at the center of the design. And we learned that over and over. And when you’re at the center, everything is magnified like a thousand times. So I’ve always been fascinated by, and intrigued by, and motivated by, how do we ensure that the words we craft so carefully remain intentional, consistent, and relevant over time?
Lisa:
So it comes down to governance, content governance, and how we can achieve that singular consistent brand voice at scale. So at the time, the role of AI in Twitter’s content design practice was brand adherence, enforcing our brand guidelines. A way to ensure that consistency and cohesion over time, so that whoever writes the copy for the next experience just doesn’t have to start from scratch. I mean, you’re talking about all the user research you do, the drafting, the revisions, the experimentation. You don’t want to lose that. So at the time, writing AI for us, again, was natural language processing, or NLP.
Lisa:
So NLP is that branch of artificial intelligence concerned with giving computers the ability to understand text and spoken words in the same way people do. At Twitter, we used it like we’re doing at Microsoft now, to keep our writing on brand and ensure our guidelines, ensure we can enforce them across all those touch points of of microcopy that can make the digital experience.
Lisa:
So when you’re working on a global… It’s like the one constant, it does come down to build on our successes, rather than starting from scratch each time. So that’s the NLP part, kind of basically where we were when we were at Confab the last time, is what we were talking about.
Larry:
Well, and actually, you’re reminding me even before that, I think it was at Lavacon about the time you started at Twitter, but I think I saw a Cordoba demo, and they likened it to a writing coach standing over your shoulder going like, “Oh no, that’s not how we say that here.” And that’s NLP in action. It understands what you’re doing and says, “Well, actually we do that a little differently.” But I gather you were just going to talk about the other thing that’s kind of been more in the headlines lately about AI.
Lisa:
Yeah, and it’s funny, because when we were talking last Confab, the way I was presenting writing AI was like, “Hey, we as content designers aren’t using NLG, Natural Language Generation.” This, again, this is over a year ago. And at the time, it didn’t have the research insights, and I still believe this today, when you get to content design, AI doesn’t have those research insights. It doesn’t understand our product strategy, our business goals, our user needs, which is why writing AI won’t replace content designers for absolute sure.
Lisa:
It’s not aware of our content formats at this time, or our surfaces, or of our cultural zeitgeist. But since that time, and I don’t know, the audience probably knows NLG, but just in case not, NLG is that branch of AI that produces natural or spoken language from both structured and unstructured data. And so again, so at the time, I had a different perspective on AI, and it’s evolved over the year, and I really see now that I’ve been in it into it for a while, how it can really give writers that boost.
Lisa:
It’s like having the jet pack on your back, and that’s because of the structured and the unstructured. So for example, at Microsoft, we’ll be using it not only for the rewrite, simplify, shorten, which is great when you’re working in tiny boxes, five characters or two words can make a huge difference. But also for that structured part, we were able to work with and build our own custom templates, so we can feed it the inputs and the outputs ,so that when, for example, there’s absolutely more writing than my help team can do.
Lisa:
That’s one of the exciting things that I do love about Microsoft, is I get to have work with content designers and help and support. So we really get that whole content experience, we get to work on that together. But yeah, so we’re building custom templates where our writers will eventually be able to just give it a spec, and it can give them a boost, producing anywhere from 30% to maybe even as high as 80% of that help article.
Lisa:
And because there’s so much more than we could ever possibly do, what we are excited about for, is it will give us more time to do impactful, that deep work, whether it’s more A/B testing, experimentation, more research, journey map and those kinds of things. So I’ll pause for a minute.
Larry:
Yeah, no, I was going to say, as you’re talking, I’m really curious about… Because I remember when we talked earlier, you mentioned you have both tech doc folks as well as content designers in your preview. But also, as you were talking, you said, and I’m hearkening back to the very first part of the conversation, when you said there were two of you at Twitter when you first started working on this stuff, and you talked about scale.
Larry:
So I’m curious, the scaling, it’s both for the content, you’ve given a couple of examples already of how it can really help content people, but in terms of scaling, is it also a way to increase your impact? Because I’m going to assume that if there’s never enough content people around, so are UX designers and engineers and other folks, product people, doing some of the writing? And do they use this tooling as well?
Lisa:
Yeah, exactly. Yeah. And that’s what we’re rolling out right now at Microsoft. One of the things, it’s a pilot right now, I’m very curious to see what I call reach, how many different orgs, different lines of business, different use cases can it support? And that’s really, in my experience, the power of the writing AI, whether it’s NLP, NLG, it’s at that scale.
Lisa:
It’s not just it’s going to help content designers go faster. It’s when you look at an enterprise, when PMs are creating mocks, and designers are doing prototypes, and sales is creating materials and marketing. When you all get those same suggestions in line, it can be super powerful. One of the big things, and it’s not Microsoft, it’s not just Twitter, it’s everyone, staying consistent on terminology especially.
Lisa:
Most product orgs do work in silos. You have a team building X and a team building Y, and someone over there doing Z. And when you all have your own style guides, or maybe you’re using the same style guide offline, there’s so much chance for discrepancies. Someone’s going to come up with a new term that another team has been using differently and it just starts to clash. So having those suggestions come in line, as everyone is writing as one, is super powerful. It’s more powerful at the enterprise level than necessarily a single content designer working alone. That’s really where it comes.
Larry:
No, and that’s a classic. As you’re talking about, that’s a classic challenge in an enterprise, is aligning people on terminology across departments and silos and lines of business and all those things. And I can see where having a tool like this would help, but there’s still some fundamental underlying human behavior, humans aligning to agree on what that terminology is in the first place.
Lisa:
Oh, absolutely. So that offline piece is a lot. And at Microsoft, we have experts who do that. I’m like, “You all make the decisions. I’m just making sure that they’re implemented in the way that you want and it’s done.” We have our principles, when we started this at Microsoft, and it’s guiding principles, good for Microsoft, meaning the more you single source your style guides, the more everyone shares the same one.
Lisa:
It’s not only better for your brand, but it’s less expensive. You don’t have so many style guides you’re trying to maintain and branch, but also good for teams because teams need flexibility. And if you ever want to take away a team style guide, you know how that can be. It’s very… People get very attached. So there are times when teams need to have independence and go their own way in autonomy. So that’s our second guiding principle.
Lisa:
And you do have to balance that, right? When can someone give up a little of their autonomy for the good of all? And then we have good for all writers, which gets to… A lot of it, honestly, is the NLG, but the NLP too, especially if English isn’t your first language, having that is super powerful. Just enabling more writers, democratizing writers.
Lisa:
And the last one is good for our customers. I mean, as much as product A thinks they have the right usage for a term, product C thinks so too. And when they eventually, two years from now, they come together in the same experience, that’s not good for customers.
Larry:
You mentioned that there’s a team working on this alignment. I’m curious, is that like a taxonomy terminology team? Or who’s kind of in charge of language at Microsoft, or language alignment?
Lisa:
Yeah, a virtual team, a VT, we call that. And they do that, and they have processes and guidelines that they follow because it’s a big company, 200,000 people, a lot of people are using that. So some of those people are on the Writer pilot, I’m working with them. And we’ve made a conscious decision for the pilot. We’re actually maintaining a whole… Several of our style guides separately. So we’re maintaining our Microsoft that the whole company uses, and then a version of that within the Writer platform, that we’re maintaining and giving ourselves a little bit more flexibility to make decisions without the whole governance process, just so we can see how it runs.
Lisa:
We have, really, three strategic objectives at Microsoft, which is aligning product and brand. It’s so important. Now, for example, with Copilot, which is developed in multiple teams coming together as a single experience, branded that way as a single experience, aligning that product and brand, improving writing, consistency, efficiency across all of Microsoft, and then managing those style guides.
Lisa:
One of the things with… As you set up all the AI, the inline suggestions, being able to easily manage all of those is super important. And some of the way we’re measuring the success on that is just cost savings. It’s a lot of work to maintain style guides of that size. Brand and legal compliance is another way we’re looking at measuring that.
Lisa:
So our first objective is aligning product and brand. The next is shifting time to higher value work. And that’s so important for content creators, because a lot of times, we just spend our time just filling in the boxes or… Rather than really getting into that deep, research driven work that we want, and really connecting with our customers.
Lisa:
So the NLP especially can automate low level edits, rather than having to go out and search a style guide, or find the style guide, and then search through it. It just comes right up in your suggestions. Streamline the review process, and then again, eliminating the time to actually search and find the thing you need from the style guide.
Lisa:
And what’s interesting, as you get in and you do this work, you see all the inconsistencies that it may have been in your style guide, you start seeing things that maybe weren’t totally clear, and being able to get those surfaced in your writing, and have people across the company getting that, you start getting feedback really, really quickly.
Lisa:
And it’s kind of fun for word people, really digging in, is this, “Don’t use word.” Or maybe it’s a use with caution word, and how can we move from three words to describe the same thing to one. So yeah, it’s fun. But then the third one, again, we talked about, is democratizing and scaling content creation, and that’s enabling more writers accelerating content creation. Of course, the Gen AI is amazing at that. And then boosting creativity. And I always think of, I use Gen AI a lot as my brainstorming buddy, right? It’s nice to have a little… Another thought partner by your side to give you a boost.
Larry:
Yeah, it’s like we all have a bunch of friendly collaborative colleagues that we didn’t have before. Now a couple of things on those last two points. You mentioned both the move, the ability to move to more high value work, and to enhance creativity and all that. That’s like, people are just, I think, legitimately in many cases, worried about their jobs, and will there be content work going forward? But a lot of the stuff you’re saying, and you’ve said explicitly even earlier in the interview, it sounds like you’re convinced that there’s just going to still be plenty of work for us to do.
Lisa:
Absolutely. Absolutely. Yeah. Especially, maybe if you’re writing the top 10 lists of things to do in New York, maybe not, right? But if you’re doing that work that requires really meeting customers where they are at a particular touchpoint in a customer journey, whether they’re feeling nervous about it, or they’re angry, or they’re excited, AI is not going to know that particular thing.
Lisa:
And to know that thing, you need time. You need time to research, you need time to journey map. You need time to think about your content ecosystem, and you can’t necessarily do that when you’re always jockeying the strings. So I believe this will… This is part, it’s one of the tools. It’s going to help us do more deep and impactful work.
Larry:
Yeah, no, I love that. That’s one of the benefits of this. It seems obvious to us, but I just still worry a little bit that people are… I don’t know. But the more research that we can do, the better informed our work is, the more attuned we’re to our customer’s journeys and stuff. It’s just not hard to picture how that’s going to make all of our content more effective.
Lisa:
And we talked about this, but I just want to… When we were doing some demos of this to our product design group, we were excited for them to be able to use this as well, when there’s spinning up a mock, or we don’t have a content design partner, but one of their fears was, it’s like, “Oh my gosh, am I responsible for the content now? Am I now a content designer?”
Lisa:
And I assured them, at least at Microsoft, our relationship isn’t changing. If we have a partnership, if we’re able to engage with a design team on a particular work stream or feature set, it’s really a tool that’ll make our lives just simpler and more productive. It is literally a tool. It’s like back in the day when you had word processors came on, it’s just a tool, but we’ll use it. This is what I tell our design partners. We’ll use it to improve consistency, writing efficiency across products and teams, right? Things like capabilities that automate low-level edits.
Lisa:
Again, it really is a boost to creativity, streamlining review processes, which can get cumbersome and messy, and then also facilitating content reuse. But it’s about delivering, having time to deliver the products that people really love.
Lisa:
But then again, if you don’t have content design coverage… At Microsoft Teams, we don’t have enough to cover all the features that are coming out. So something that, at least, if it’s a PM, spinning something up, or a designer, at least it’s going to be on brand in terms of terminology, in terms of writing style, which is a win.
Larry:
Yeah, no, I can see that working just on its own, per se, but it just occurred to me, and I don’t know why, to ask, does this inspire any more interactions between product and design folks and the content design teams? As they’re like, “I don’t understand the suggestion.” Or…
Lisa:
Yeah. Oh my gosh, yes. We’re getting lots of things. One of the things we spun up right away is a feedback form, because especially when you’re launching something like this, you’re going to have a lot of noise. Things will be over flagged, the settings are too sensitive, or not sensitive enough, and it does… I’m interested to see what, especially product designers, are giving in terms of feedback. Just again, we’re just talking right now about the NLP, the natural language processing.
Lisa:
But yeah, kind of unearthing dusty portions of the style guide as you put it into the AI. So we’re spending a lot of time now training, we meet every Friday, we review the feedback. And again, this is a lot, again, I’m talking about the NLP, but again, there’s a lot of use cases now, contrary to what I thought a year ago, a year and a half ago, when we first started talking for the Gen AI, especially if you’re a researcher.
Lisa:
So this is going to go bigger, like the lines of business that I can tell you that we’re hoping to support at Microsoft. Eventually, sales and support marketing, of course, brand comms, PR. But in our org, we have product design and research, right? So research, I’m excited, on Monday we’re going to train our research team, but the analytics that are available now, summarizing research, video calls, transcripts, pulling out the sentiments. So for a researcher, instead of, “I remember the days when I transcribed videos by hand, and madly jotted down notes from what customers are saying.”
Lisa:
And now you can do that so fast, in minutes, and get on with some of the other work that you want to do. But yeah, so within our product org, it’s summarizing research. This is for the NLG video calls, transcripts, market landscape research, things like email campaigns, blog and email headlines, help and support articles. So there’s a lot of things. Ideation, that’s one of my favorites, we talked about the brainstorming buddy. So yeah, there’s a lot of different uses across the …
Larry:
You’ve covered a huge swath of our work in that last little list that you did there. Hey, but one thing I want to go back to, but one of the newer things that’s emerging from this tooling is kind of the skill of prompt engineering, especially on the NLG side, the gen AI stuff, and you talk, especially when you talk about ideation or researcher, I have so many questions about this, I’m realizing, as I rattle this off. But the first thing I’ll ask is, are your content designers becoming… Because a lot of people have pointed out the similarities between prompt engineering and content design. Are you just kind of running with that? Are you-
Lisa:
Love it, I love it. Yeah. In fact, I asked one of the writers on my team, who really… She’s working on Copilot and has experience with prompt engineering, if she might be willing to take on being our capturing use cases that work brilliantly and ones that don’t work. There’s one she was working on, there’s a word, what was it? Reschedule. She needed to get it shorter. So she was using a combination of ChatGPT and Writer.
Lisa:
She came up with rebook, but then when she asked in the same prompt, she wanted a term that could be translated into the top 20 languages, it just failed. And I think it’s because Writer and ChatGPT thought that the prompt that she wanted that to actually translate the word into the top 20 languages. She was more interested in, “Is this translatable into those languages?”
Lisa:
So yeah, so prompting is super important, and that’s one of the things I’m going to try to start gathering, which these tools have prompts built in. But to really… When you want that brainstorming buddy or quick, how cool is that, to be able to find a word, a shorter version of it, and then also know, “Hey, is this going to localize in the languages I care about?” All just on a desktop. You don’t have to wait for it to kicked out of localization, and realize now the new word doesn’t fit in the box. And so yeah, there’s a productivity boost.
Larry:
Yeah, that’s a super interesting one. Hey, and you also mentioned that one of your folks is working on Copilot, so maybe that’s a whole other episode about this, but I think, in addition to the applications where we use these technologies in our jobs, we’re also doing our craft in those products.
Lisa:
Exactly.
Larry:
Are a lot of your folks in that situation, like working on Copilot and other-
Lisa:
Yeah, right, because there’s Copilots in many of the Microsoft products, and they will be eventually in all of them. So different… We’re just bringing in someone now to be responsible for the overall Copilot UX within teams, but then individual content designers and feature areas will continue that work, so those writers are getting a lot of experience in that.
Lisa:
This is a whole other topic, but something that I really came to understand fully at Twitter, is when you are working with generative AI, it’s really, as a content designer trying to build an experience that people trust enough to use it, I was saying it’s building trust through transparency. You have to be really explicit. What is this AI feature doing with my data? Are others going to be able to see that I’m using this feature? Where’s my data going to be stored? Who will it be shared with? It’s super, super important that you’re very clear about what’s happening with the AI experience.
Larry:
Yeah, and that’s a whole evolution of craft. I’m thinking, I’m doing this podcast once or twice a week now, and I’m thinking I might have to do it daily to keep on top of all this stuff, but hey, Lisa, I can’t believe it. We’re coming up close to time, but before we wrap, I just want to make sure, is there anything last, anything you want to make sure we talk about, or that you want to revisit from the conversation before we close?
Lisa:
Yeah, yeah. I’m going to end with a hot take. We’ll see what your listeners think about this. As writers, when we talk about AI, it’s not about replacing writers, it’s about affecting them. So AI won’t replace writers, but writers working with AI will replace writers working without AI. We have to be able to work, at least in our jobs in tech, we have to be able to work at scale.
Lisa:
Think of what AI is happening with engineering, right? Engineers who know how to use AI for their jobs, or illustrators, they’re going to need to know how to use that as well. How do you guide it? I know we have the term Copilot, which I think makes sense in the product, but as a writer, you’re the actual driver. You’re riding that horse, so you need to know how to saddle it up, how to guide it down the trails.
Lisa:
But yeah, it is really true. I believe the writers who really can harness that power, who know how to use it to their advantage, will produce the most outstanding, the most scalable, the most impactful work.
Larry:
And that’s all any of us want, is impact and scale. Well, one very last thing, Lisa, if folks want to follow you online or connect, what’s the best way to find you online?
Lisa:
Oh, LinkedIn. Yeah, I’m on Linkedin. Please connect with me, or drop me a message. I’d love to hear. I’d love to hear and keep the conversation going. We’re just starting out. We’re just learning. Gosh, six months from now, maybe I’ll change everything I said today, and we’ll start again.
Larry:
Yeah, a friend likened the current situation to like a giant skyscraper, teetering over a pit of quicksand with constant earthquakes. Anyhow, that’s how it feels. Yeah, it’s a little crazy.
Lisa:
Yeah.
Larry:
Well, thank you so much, Lisa. This was a really fun conversation.
Lisa:
It was a joy. I’m so glad to be here. You take care.
