The UX of AI: Making AI-Powered Apps Your Users Don't Hate - Kathryn Grayson Nanz, Progress Software

AI Engineer · 35 min · 306 sentences · from YouTube's caption track

Each timecode opens YouTube at the start of that sentence. Line anchors (#s42) are the cue ids in the WebVTT, and every line carries its start and end seconds. All transcripts has every talk, and the whole corpus as one file.

00:00Hi.
00:01My name is Kat.
00:02I'm a senior design and developer advocate at Progress Software, and I have spent most of my career focused on the front end.
00:10After taking a somewhat meandering path through design and into development, I eventually found my niche in the space where those two worlds overlap.
00:19My design background has given me a lot of insight into the UX side of software engineering, and the user research that I get to do as part of my work as developer advocate
00:28is one of my favorite parts of the world.
00:31I have spent a lot of my career teaching developers about design, about UX, and about how to build more user-friendly software.
00:39Something that's always been valuable, but is more crucial than ever now that AI has entered the picture.
00:45I don't need to tell you that AI is a pretty unique new technology.
00:49It is rapidly developing and has so much potential to improve systems and software in ways that we couldn't have even dreamed of just a few years ago.
00:59However, along with all of that potential is also quite a bit of risk.
01:04AI's non-deterministic nature means that the output can wildly range in quality, format, style, and accuracy, even when we're trying our best to prevent that.
01:14On top of that, it requires entirely new types of interaction patterns to use.
01:19In fact, we've seen the emergence of new vocabulary, techniques, and sometimes entire roles meant to address that need.
01:27For those of us that are living and breathing this technology every day, concepts like prompt engineers, hallucinations, retrieval augmented generation, and so much more have all become regular parts of our lives.
01:39But for the vast majority of our users, that simply isn't the case yet.
01:45In any kind of technology, there's a gap between the developer, who has by nature kind of become the subject matter expert, and the user.
01:53The technical literacy of the average software engineer is always going to be higher than the average user of said software.
02:00That's where UX comes in.
02:02It's how we bridge the gap between what we intended when we built an application and what the user actually experiences.
02:10After all, it doesn't actually matter what our software can do if our users hate using it so much that they will avoid it at all costs.
02:18And right now, AI has a kind of serious UX problem.
02:23Our users are seeing AI features get added to basically everything right now, from their work software to their social media apps, right down to their computer and phone operating systems.
02:34But, as a wise technologist once said, "Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should."
02:43We're really pushing our users to adopt these new tools and features, but we're not always making it easy to do so.
02:51It's common to see situations where a user is presented with a poorly designed AI feature that they really only have the barest idea how to use.
02:59Then, when they try it and it doesn't do what they wanted or expected it to do, they feel annoyed and off-put and kind of negative about AI generally.
03:09The more times they try an AI feature and get sub-par results, the less likely they are to engage with it again in the future.
03:17Which means that, as the creators of these features and software, we really only have so many chances to get this right before our users just disengage and stop trying at all.
03:28In my personal opinion, this knowledge gap between developer and user when it comes to AI is one of the widest that I've seen with any technology.
03:37That makes it extremely hard for us to build AI-powered features that our users are actually going to get the full benefit from.
03:47When Macintosh introduced their graphical user interface, it was, like AI is now, something that was very different and unfamiliar to their users.
03:56But a large part of their success and reputation was built on their ability to create a user experience that met users where they were.
04:05They borrowed vocabulary and user flows from real life.
04:08They included lots of icons and visual representations, and they really made sure to walk users through how to get the most out of their new personal computers.
04:17And over time, as the average user became more comfortable and more literate in the space, the user experience of the Macintosh evolved with them.
04:26We start to see more technical terms and fewer abstractions.
04:30Look at the difference here between the control panels in Macintosh system 1 and system 6. If you had presented a system 1 user with the words rate of insertion point blinking or RAM cache,
04:41it would have been pretty much meaningless to them.
04:44Similarly, we see that those low and high volume icons are gone in system 6, along with the little turtle and rabbit speed icons, right?
04:52That kind of more literal depiction wasn't needed anymore.
04:57Right now, we are probably somewhere around system 3 in this metaphor of introducing AI to users.
05:04We may not need the turtle and rabbit icons anymore, but we also can't yet assume that they will sit down with our AI software as experts.
05:13The good news here is that, unlike the Macintosh UI, we're not totally starting from scratch here.
05:19Our users have existing mental models about software usage that's going to carry over to what we're building.
05:26They're just not always going to map over exactly one to one.
05:30But that's where we come in.
05:32As developers, it's our role to leverage these patterns that our users are already familiar with, start to combine them in new ways, and then introduce them to our users gradually
05:42in a way that's not going to feel overwhelming.
05:45A good user experience will not only provide a user with the tools, but also guide them how to use them.
05:52For instance, let's look at an AI chat interface.
05:56From a purely UI perspective, chatting with an LLM is almost, but not quite, like chatting with another user.
06:04So, we'll be able to borrow some familiar patterns here, like having the user's chats show up on one side and the AI chats on the other, messages that appear above an input field with a send button,
06:15a scrollable message history, and more.
06:18That gives our users a really good jumping off point and a lot of visual clues about how to start interacting with an AI chat.
06:26However, the experience isn't quite close enough that we can just lift an existing interface from direct messages and repurpose it wholesale.
06:35A chat interface that was originally built for two people is not going to have the accommodations that we need for things like adding reference sources, pausing or stopping an in-progress reply from the LLM,
06:46leveraging agentic tools and integrations, or more.
06:50So, those are going to be the places where we have to adapt existing UX and UI patterns into something new.
06:56We have to be the bridge and help our users transition into familiarity with these new AI experiences.
07:03We can see the difference here, right?
07:04Compared this Copilot research agent new chat with the new Teams chat.
07:09Both of them have familiar aspects, right?
07:11We see text boxes, we see the plus to attach files, and so on.
07:16But, the Teams chat assumes a much higher level of familiarity.
07:20It's not spelling out any of the iconography it uses, and we don't see some of the things intended to lower the barrier of entry, such as the examples, large text buttons, or voice interaction options
07:31that show up on the agent chat.
07:34Now, before we really dive into this, I do think we have to take a moment to address kind of the elephant in the room, right?
07:42Why not just have AI create these solutions for us?
07:46Why do we have to be the ones who design and build new AI patterns when we have technology that can generate interfaces for us now?
07:54The problem with that is that AI can only really remix things that already exist.
07:59It's fantastic for looking at those existing common patterns and replicating them, but the patterns for AI interfaces don't fully exist yet.
08:10Or at the very least, they are still in the process of being rapidly developed, and they are changing all the time as that technology advances.
08:18There's just not a long history of standardized and familiar AI-related interfaces that we can reference to solve this problem.
08:26So, at least for now, we're kind of on our own here, and we can't yet defer it to AI.
08:32Maybe that will change down the road, but for the time being, this is still a very human problem.
08:38Additionally, as many folks have begun to notice, the design that an AI creates is going to be a lot like every other design out there.
08:48AI can reference and remix, but you're just not going to get brand new concepts from it.
08:54An AI-generated UI tends to look pretty darn average.
08:58And while that can be a really great starting point, it's not usually a great ending point.
09:04If you just need a quick landing page, it's probably going to do the trick.
09:07But since we're dealing with whole new interaction modes that need more attention paid to the UX rather than less, it's just not going to be enough to get us where we need to go right now at the quality level that our users need and deserve.
09:21So, if we're going to build new patterns and new interfaces to help our users get the most value out of this technology, where do we start?
09:30Well, like most things in design, it's best to start with the user.
09:34Specifically, the user's problems.
09:37That means that when we're thinking about building our AI features, we need to be thinking about what challenges our users have with AI and the user flows that will mitigate those issues as much as possible.
09:49From the user research I've been doing and the users I've had the chance to speak to, I've started to group the main challenges here into five categories.
09:58Trust, clarity, control, transparency, and meaningful benefit.
10:05In this talk, we're going to discuss each of these in depth, understanding the problems our users have when they're using AI, and looking at some examples of new patterns and techniques we can employ to address them.
10:18By making sure that we are addressing each of these, we can start to create AI experiences that support our users through the introduction of this new technology and ensure that they are in a place to use it to its fullest potential.
10:32So, let's get going.
10:34[snorts]
10:34Trust.
10:36The number one, by far, biggest hurdle that we need to overcome in order for our users to engage with the AI features we build is trust.
10:46Right now, to the average user, AI is a black box.
10:50Many simply do not understand from a technical perspective how it works.
10:55And when you don't understand how something works, it makes it very, very hard to trust the output.
11:02On top of this, just about everyone who has interacted with an LLM before has, at some point, seen them hallucinate.
11:09Even as the models keep getting better, we're still not at the point where we can claim any tool will be 100% guaranteed hallucination-free.
11:18There's always a chance, even if it's a small one, that the AI is going to provide an incorrect response.
11:24So, how many times can a user see output that's wrong and still trust it?
11:30It can be easy to think that the answer to this problem is to try and position the feature that we're launching as some kind of exception to this rule.
11:37We say things like, "Other AI tools may not be trustworthy, but ours is different.
11:42Ours is higher quality, it's safer, it's more reliable."
11:45So on and so forth.
11:47But not only is this questionably true, right?
11:50I mean, after all, and not many of us are really training our own models here.
11:54So a lot of this is going to be simply outside our control.
11:58But it's also a very difficult thing to try and sell your users on.
12:02In situations where we cannot promise the truth, we have to go above and beyond to earn it.
12:09Our honesty about current capabilities and limitations of our AI tools will go a lot further with our users than the denial of any potential problems.
12:20So rather than trying to convince users that our solution is inherently trustworthy, we can instead build in patterns that empower them to see when incorrect information is returned and give the tools to correct or mitigate it.
12:32You know the saying, "Trust, but verify"?
12:35That's kind of the goal here.
12:37By citing the references in an AI-generated response and linking users back directly to the source material, we give users the information they need to validate AI output themselves.
12:48The more a user is able to click through and see where an answer came from, the more they'll be able to trust the content, even if they don't choose to check every source every time.
12:58In addition to allowing our users to vet the answers, citations also have a second important purpose.
13:04They allow users to repurpose the material in their own work while maintaining a trail of accuracy.
13:10This is really important for their own credibility and reputation.
13:14After all, how often would you share content from an unverifiable source if you knew that any errors would ultimately be attached back to your own name?
13:23Generating output for the user might be the last step in our process, but it's really just the beginning for them.
13:30Users want to take that content and turn it into a report, an email, a campaign, a presentation.
13:35And if the output can't be cited and trusted, then it's just not going to be used.
13:41There are a handful of different ways we can implement this, and which one you pick is going to depend on what you're building and the context in which it's being used.
13:50But a few popular approaches include things like tooltips, inline links, and side panel reference windows.
13:56Tooltips allow you to provide a small snippet of a relevant quote, which can be really great for increasing credibility.
14:03Links, of course, are ideal if the content is coming from an external source, like another webpage, as opposed to an internal source, like a document in a shared drive.
14:12And if the feature you're building is meant to support more research-oriented work, then you might consider adding a side panel, where the user can explore the source material in more detail,
14:22which kind of positions the AI assistant as more of a librarian than inherently a subject matter expert.
14:29The other place where trust factors heavily into AI work is agentic workflows, where the AI is thinking and executing work on its own.
14:38This, understandably, can be kind of concerning for users, depending on the stakes of the project and how easy or hard it would be to roll back any incorrect actions,
14:47which is when keeping that human in the loop really becomes crucial.
14:52One of the best ways to help users trust these systems enough to use them is to show an action plan to the user and allow them to approve it before the agent begins work.
15:02This has become a pretty common flow in a lot of foundation models, right?
15:05If you're using agentic features in Claude or ChatGPT, you will have seen it create a list of the steps it will take to accomplish a given task and then ask for your confirmation before beginning.
15:16Of course, there are also settings you can add to toggle this off or always allow it, all of which is important if you're going to allow users to repeat a flow over and over and don't want them to have to baby sit it.
15:27Spoiler alert, we will talk a little bit more about permissions in the transparency section later.
15:33But if you're creating some kind of an agentic tool and no plan is ever shown to the user and an action happens without them understanding why or how, it can be very, very hard for them to trust both the result of that action
15:48and the agentic tool itself.
15:52There is also, undeniably and I would maybe even argue correctly, quite a bit of skepticism around whether or not content is AI-generated right now.
16:02You've probably seen exchanges online where someone shares a photo or video and another person is immediately commenting to tell them that's not actually real.
16:11When we spend so much of our time and energy second-guessing and investigating content that's shared with us, it doesn't exactly foster an environment of trust.
16:21For now, AI-generated content is highly polarizing with users.
16:26While some have heavily leaned into using it in their daily lives, others will react to it negatively and dismiss it as slop, right?
16:34The ability for AI to generate text, images, and video that is nearly indistinguishable from human-created work is very new.
16:42And for many users, that still feels uncanny and unsettling.
16:47I don't say this to start any kind of debate, right?
16:49I mean, seems harsh to say it, but our own personal opinions on AI-generated content don't really matter too much in this context.
16:57What's more important is the awareness that our users will react to AI-generated content in a wide variety of ways and not all of those ways are going to be positive.
17:08So, if we want to include AI-generated content in our applications and we're not exactly sure how our users will feel about it, what can we do to retain their trust?
17:18One of the easiest things is to just mark any AI-generated content as AI-generated.
17:25This could be as simple as a disclaimer in the App Store description, a watermark uh on a photo, whether that's digital or visible, or maybe even just an asterisk at the end of a sentence that denotes something as AI-created.
17:38When we do this, we remove that potential user perception of them feeling like we tried to sneak AI-generated content into our apps or somehow like pull one over on them.
17:50If we're using AI and we think it's the right fit for our work, or we feel strongly that our users should be able to share AI-generated content, then there's really no shame at all in designating
18:01where it's been used.
18:03Depending on where that AI is used, it might also be helpful to clue our users into which aspects of output they might need to manually verify, rather than having to review everything as though it was AI-generated,
18:16if that's not truly necessary.
18:20Hand in hand with trust comes clarity.
18:23Clarity is one of the most important aspects of creating a good user experience kind of generally, and the stakes only get higher when we start incorporating AI.
18:32Because, as we said, so much of AI still feels like an unknown to our users, we need to be as descriptive and straightforward about what's happening at any given time.
18:42The more insights we can give them about what our software is doing and what they can expect to happen next, the more comfortable they will feel engaging with AI.
18:52I've noticed that there can be a kind of impulse to frame AI to our users as magic, right?
18:58We don't even have to look further than the prevalence of the sparkle icon to designate AI as an example of that.
19:05However, while that might feel kind of mysterious and cool, it's really not accurate, right?
19:11AI is just another technology, and our users deserve clarity over dramatics.
19:16They want to know what's going on, how a given output was created, and there's really no reason for us not to pull back that curtain whenever we can.
19:26One of the most obvious ways for us to do this is with streaming text or similar live generation of content.
19:32Not only is this a really great way to disguise the latency issue of AI generation, right?
19:37Nobody likes to watch a loading spinner, but it's also a fantastic way to show the user what's happening in real time.
19:45If we make the user wait until an entire response is generated, there's a non-zero chance that it won't actually be what they wanted.
19:53However, if we start showing a partial response as it's being generated, we give users the chance to start assessing it immediately.
20:00That means they can be coming up with follow-up questions or adjustments or maybe just stopping the process entirely if it's not returning what they expected.
20:09This also keeps the user as an active participant in the process, preventing that like XKCD my code's compiling experience of pressing a button and walking away.
20:19You've probably experienced yourself how much harder it is to complete a task if you are constantly disengaging from the workflow.
20:26Even if you know a process will only take a minute, if there's not something to keep you there, you're going to start checking your emails or replying to Slack messages
20:35or scrolling on your phone and just like that, a 1-minute wait has become a 5-to-10-minute side quest, making it much harder to pick up where you left off.
20:45The more we can prevent this for our users, the more productive they can be when they're using our tools.
20:52Another thing that can help remove the wall between the AI and the user is having it think out loud as much as possible as it processes a request, especially in chat-based interactions.
21:03Similarly to live streaming, this improves the user's confidence level in the output cuz they can kind of follow the breadcrumbs and have a deeper understanding of how a given conclusion was reached.
21:14After all, we do this all the time when we talk to other people, right?
21:18If we're presenting an idea, we know it's going to be helpful for us to kind of talk through the rationale behind how we got there and why we think it's the right choice.
21:26Explaining ourselves is such a natural part of human interaction that we've really come to inspect it.
21:32And when we don't see it mirrored in the systems that we use, it can feel kind of frustrating.
21:37Like something is being unintentionally kept from us.
21:41Additionally, seeing that chain of thought process allows for better, more accurate revisions when the output wasn't what they expected.
21:48If the user can understand all the steps that happened between point A and F, then they can really pinpoint where things went off the rails.
21:56And that allows them to give more specific instructions or clarify ambiguous parts of their request.
22:04Some existing patterns are a little bit easier to adjust from their previous non-AI usage into this context.
22:11And highlighting new content is one of those.
22:13It's not groundbreaking, but when it's combined with everything else, it can be immensely helpful in helping users keep track of AI actions, especially in situations where an agent is acting autonomously.
22:26The basic idea is that when new content appears or something gets changed or updated, it gets specially marked for the user in a way that draws their attention to it.
22:35Sometimes that might mean literally moving the focus up or down the page to see what's changed, right?
22:40Like when new messages appear in an ongoing chat and the message history scrolls down to display it.
22:47Other times though, it could just mean drawing the user's eye back to a space they might not have been actively watching.
22:53Even if that doesn't include literal movement on the page.
22:56Things like changing the color of revised text or putting a box or highlight around new material or even marking lines of code that are different.
23:06AI tools are often framed as being a kind of personal assistant for the user, an intelligent junior co-worker that they can delegate tasks to.
23:15However, as anyone who's ever delegated a task can already tell you, sometimes that means that things don't get done in the way that you would have done them.
23:24When users are working with our AI tools, they need to know that they are still ultimately the ones in the driver's seat.
23:31After all, there's very little value in being able to assign the AI tasks if you can't then step in as you like to make adjustments, corrections, and fixes.
23:41In that vein, it is also important for the user to be able to stop or override an AI action at any point, whether that's during content generation, partway through an agentic workflow,
23:52when it's running code or scripts, or something else entirely.
23:56If the user is unable to abort the process, then they're not actually the one in control, and frankly, that's not really acceptable.
24:04One of the most reassuring things we can offer nervous users is a clear and prominent emergency brake that they can slam to bring everything to a halt for any reason.
24:13That means it can't be tucked away in a menu somewhere or involving some specific command they have to remember, which they won't in a high-stress moment.
24:21We want to give them the equivalent of a big red button they can slam to make everything stop whenever they need.
24:29Of course, once a user has stopped a process, we can probably guess what they want to do next, right?
24:34They want to undo the incorrect things that changed.
24:37Even way before AI, Nielsen's heuristics list safe exploration as one of the core principles required for a good user experience.
24:46That means that users should be able to navigate back and forth, click and unclick things, and generally just kind of mess around in a piece of software without getting stuck or unintentionally
24:56making big permanent changes.
24:59Sometimes a user will try something and then change their mind, decide they don't like it, or it didn't do what they thought it would.
25:07In those cases, we want to make it as easy as possible for them to roll things back to an earlier state.
25:13This kind of safety net was always valuable, but now that we're dealing with non-deterministic output, having some kind of a version history is going to be pretty much a non-negotiable.
25:24Of course, the level of version history that's required will differ based on the task.
25:29The Git style of version control that we are used to as developers is probably more than you will need in a user-facing application.
25:37If this is a truly simple conversational interface, you may not need it at all.
25:42The user could just rephrase their question and try again if they don't get the answer they wanted.
25:47However, if your tool is doing something more complex, like creating and editing a document, simple undo and redo actions that allow users to move back and forth within the last
25:5810 or so steps would be really helpful.
26:01And if you're wanting them to do truly advanced work with your tools, then it's worth building in the mechanisms for checkpoints or save states.
26:09Consider what kind of tasks your user is going to be working on with your AI features, and think about how significantly each step forward is likely to change the existing content.
26:21Ideally, this will also allow users the specificity to make targeted targeted adjustments.
26:26You don't necessarily want them to have to wipe out and replace everything that happened in a given step if they weren't happy with it.
26:33It's common for AI-generated results to have a mix of quality in the output.
26:38Users may want to keep some aspects while reverting others.
26:42And the more control we can give them over that creative process, the more enjoyable it will be for them to collaborate with our AI tools.
26:49This is especially true now as the cost of tokens is starting to tick up.
26:54Having granular control over what gets reworked allows for more specific and production productive iteration without them just having to say, "Try again."
27:04and start over from scratch each time.
27:08AI tools are strongest when they seamlessly integrate into the rest of a user's workflow.
27:14Referencing internal documents, sending emails, making calendar appointments, drafting and sharing content, so on and so forth.
27:22However, most users won't integrate what they can't see and don't understand.
27:27If the AI applications we build are going to become part of their daily lives, then users need transparency into exactly what they do, what they have access to, and what it will cost them in both time and money.
27:40The more transparent we can make these features, the less hesitation our users will have in adopting them.
27:47The concept of asking for user permissions is certainly not AI specific, but the stakes can feel a lot higher when you're asking users for permission to allow AI to act on their behalf.
27:58That means we need to make it easy for users to see which applications we've allowed our tool access to and in what ways, keeping in mind that permissions are often more than just a binary yes or no.
28:10So, can your agent just reference data from this database?
28:13Or is it also allowed to delete tables?
28:16Can only read your user's emails, or can it send from their addresses well?
28:20Can it run scripts, search their local files?
28:23Each one of these actions requires direct user sign-off.
28:28Permissions are also not a one-and-done situation.
28:31A user might feel comfortable allowing an action to happen once under their direct supervision, but they might not want to allow it permanently.
28:39They could give access to a specific folder, but not every folder.
28:43They might approve an action, but then want to be notified every time it's taken.
28:47Consider which of these gray zones might exist in your permission structure and try to accommodate as many different options as you can.
28:56Another common sticking point with AI is data collection.
29:00Often, it can be helpful to save information from past interactions, but storing this kind of data requires real attention to user permissions and data management.
29:10If you want to create a system that can remember things, then you also need to make sure that it can forget and that the user can not only see,
29:18but has the final say in what exactly gets remembered.
29:22An ideal permissions flow will not only ask for a user's approval in the moment, but also create a space where they can see the history of what they've given access to and when,
29:32as well as allowing them to revoke that access or permission at any time.
29:38Now, this one's pretty simple, so we won't spend too much time on it, but another crucial aspect of transparency is making sure users know exactly what they are committing to when they approve an action request.
29:49In addition to approving those actual steps and plan, as we already discussed in the trust section, they also need to know how much time something is going to take and what it's going to cost them in money or tokens or credits,
30:02however you are counting this.
30:04Even if we can't specify an exact amount, if we can provide a rough estimate, that's generally going to give users enough information to work with and to potentially revise their request if it's going to exceed what they're comfortable with.
30:19Similarly to the marking that denotes which content was AI-generated, it's also a really good example uh of an chance to have a visual signal for when an AI tool is acting independently.
30:31If, for example, you're going to allow an agent to take control of the user's browser, then there needs to be some kind of banner or sidebar or outline, an indication that the user is no longer driving that interaction.
30:44Not only is this a good thing to do just for transparency, so the user understands the current state of the system, but it's also helpful to make sure they don't unintentionally
30:53interrupt or confuse an ongoing process.
30:57It's an especially important consideration for processes that you know are going to take an extended period of time where the user might have stepped away and then come back
31:05without necessarily keeping track of everything going on while they were gone.
31:11Finally, all of the interesting technology and cool functionality in the world is meaningless if what we build isn't solving the problems that our users need solved.
31:22To do that, we need to create experiences that make it as simple as possible for our users to get the output they need from our AI features and start to leverage it in their work or daily lives.
31:34One of the biggest mistakes we can make when developing AI features is assuming that our users know how to use them.
31:41As mentioned at the beginning of this talk, right?
31:44We know how to do things like provide context or specify formatting requirements or break large tasks into smaller ones and then iterate, but our users often don't.
31:54So, when we place a blank text box in front of a user and just tell them to ask AI, we're actually kind of asking them to do a lot of work in figuring out how to really use it.
32:06They need to understand what kinds of problems the tool can solve, how specific they need to be, what information the AI tool needs to succeed, if they need to add sources or references,
32:15how to recognize when a response needs refinement.
32:19Rather than expecting this level of AI literacy from our users on day one, we can help them by providing examples, templates, suggested prompts, and guided workflows that demonstrate what success looks like.
32:33Now, what will your users be doing with the content that your AI feature generates?
32:39If they're going to run a search or analyze a spreadsheet, what happens next?
32:43What do they do with the results?
32:45If they create an image, who are they showing it to?
32:49How are they sharing it?
32:50Is it getting printed or posted online or sent to a friend?
32:55By introducing next step action buttons, we can make it as easy as possible for them to leverage the output of our tools in their own work.
33:04If they're not able to action on the content that was created, it's never going to be more than a novelty to them.
33:10It's not going to be of realistic use.
33:13But we can help guide them to suggested next actions that will help them make the most of what they created.
33:20If we want to take this one step further, we can start to build in direct integrations with their other most used tools.
33:26Like, maybe they want to generate a new document with the content in their word processing software from a draft.
33:32Maybe they want to push new code to a linked repo.
33:35Maybe they want to open a new ticket in a tracking system with their findings from a test.
33:39The simpler we make it for them to get the information from our tool into the rest of their workflow, the more useful it's going to be to them.
33:50Now, AI can generate content, write code, analyze data, automate tasks, empower our users to do all kinds of amazing work.
33:59But only if they're willing to try it, and only if we make it easy enough for them to do.
34:05When everything our AI tools are doing is hidden behind a curtain, it makes users feel like things are happening without their input, which is hard, especially when many of them are already kind of feeling some level of AI skepticism
34:17or hesitation.
34:19If we unintentionally create AI experiences that take away our users' power, understanding, and autonomy, then they'll never be interested in using what we build, because they'll never feel truly comfortable engaging with it.
34:32By focusing on patterns that reinforce those pillars of trust, clarity, control, transparency, and meaningful benefit, we can set guardrails around our AI features that will help make our users feel safe and confident.
34:47Cuz the technology is here, right?
34:50The models are already really good, and they just keep getting better and better, faster and more efficient.
34:56That means that the differentiator for the AI-powered software we build isn't performance anymore.
35:02It's the quality of the experiences that we can build around them.
35:07The line between design and development is blurring a little bit more every day.
35:12How users interact with the system, how much information they see, how much control they have, and how we earn their trust are now questions that developers have to consider when building AI-powered software,
35:23whether your title includes designer or not.
35:27The technology may be incredible, but for it to be truly successful, users still need to be at the center of everything we build.
35:37Thank you guys very much for listening to this talk.
35:40I really hope this is helpful to you as you start integrating AI features into your own applications and software.
35:46You can find these slides, as well as a full transcript of this talk, at the following links.
35:51And, of course, feel free to reach out to me online if you have any questions at all.
35:55I'm always happy to chat.