ai

Copyframes: Just like wireframes, only faster, more precise, and less costly

February 2, 2025 By Doug Schumacher

It must happen on thousands of video conferences every hour around the world. A UX design project is in the late stages when the client begins to question the content. The way things are said, or even worse, the order of key page sections.

And every time that happens, the progress grinds to a halt. And then more things happen. The project leaders swoop in to avert crisis. Long meetings take place involving said project leaders, racking up hours, and costs. And those meetings are about making decisions that should have been locked down much earlier in the process.

Enter copyframes. Wireframes’ more literal cousin.

Instead of greek text, with copyframes, you’re working out first-drafts of the most critical navigation elements on the page: headlines, body copy, and CTAs.

If you’ve read the most excellent UX writing book ‘Writing is Designing’, the authors point to work done by Mig Reyes demonstrating how text is the navigation bedrock of a user experience. Take a typical web page and first, remove all the graphic elements. Then, all the text elements. Most interfaces remain usable with just text, while visual elements alone can range from slower (i.e., greater cognitiveload) to completely unusable. (Check out ‘Image 1’ for a visual that illustrates that point.)

Image 1

As a result, the traditional wireframing approach, while possibly delivering a smoother UI transition, often diverts into a bottleneck of content revisions. Tweaking visual late-stage layouts based on copy modifications eats up valuable time.

It’s about more than time and money

Strategy usually lives in text – briefs, user stories, etc. Copyframes better bridge this natural gap between strategy and execution. It’s a more direct translation of the strategy into interface.

And this clarity creates a feedback loop into the time and money issue. When clients comment on the actual words taking shape, the crucial feedback insights arrive earlier in the process.

So copy matters. Or at least, it should. Copyframes offer the fastest, most direct route to translating crucial strategic ideas into tangible page structures. Think of it like prioritizing the big rocks in that task management jar we all know and (sometimes) love. Copy is undoubtedly one of those big rocks in the UX process.

But what do copyframes look like?

After what I’ve described so far, it’s probably not a stretch of your imagination to conjure up an image of a copyframe. That said, I’ve used them at various levels of fidelity. (And using fidelity to describe a copyframe could be considered egregious.)

So regarding tools, it’s a lot like the line about the best camera being the one you have with you. Copyframes are about capturing the gist of something vs artful finesse (I admit to having done them in Powerpoint). It’s about whatever helps you most easily communicate the flow of messaging, from first view of the experience through to the final CTA.

Below is an example (Image 2) of copyframe examples; the first done in FigJam, the next two in Figma, one rough and one using a page template. (I used the Door Dash page again to illustrate what what different copyframes approaches might look like.)

Image 2

It wouldn’t be a blog post without mentioning AI

Beyond the present advantages of time, cost, and accuracy, copyframes offer a giant leap forward: copyframes are perfectly positioned to leverage the power of artificial intelligence.

The text-centric nature of copyframes means that today’s sophisticated Large Language Models (LLMs) can be reliably employed to generate compelling and on-brand copy with the right prompting and agent design.

Furthermore, AI agents can be used to create the initial creative brief and page content outlines, leveraging copyframes to further expedite the process. The link between copyframes and AI is a match made in digital heaven, promising more relevant, faster, efficient, and utlimately more impactful UX design workflows.

So, ditch the late-stage content chaos and embrace the clarity and efficiency of copyframes. Your team, your clients, and your bottom line will thank you. It’s time to put words first and build truly meaningful digital experiences, one well-designed sentence at a time.

Put another way: Use your words.

Homie & Lexy Episode – “T’was The Bot Before Christmas”

December 18, 2018 By Doug Schumacher

The Bots tell their favorite Christmas Story.

This is also functioning as my ‘audio’ holiday card this year. Wishes for a warm and bright holidays for everyone.

New podcast “Homie & Lexy” launched

March 27, 2018 By Doug Schumacher

Most anyone who’s talked to me in the past couple of years knows my interest in AI. The more I looked into AI and it’s potential impact on marketing, the more fascinated I became with the voiceweb. Accessing content currently on the web, via a voice interface.

While voice offers challenges that text and graphic information doesn’t, it’s also the most natural interface developed so far. If you’ve played around with either of the two major devices — Amazon’s Echo or Google’s Home — you’ve no doubt seen the potential. And the likely challenges.

Given how reliant these systems are on AI, how much AI stands to progress in the very near future, and how early we are in the voicebot game, I think it’s pretty clear that we’ve only scratched the surface of the voiceweb.

So for me, the personal challenge was, How to immerse myself in this new channel of established growth and greater longer-term potential?

After considering a number of content types to develop, I came to the idea of a simple, short-form comedy podcast about two voicebots.

Homie & Lexy.

As the website says:

Homie & Lexy is a podcast about two voicebots residing in the same house. When their owners step out, the voicebots discuss the perplexing human world around them.

The show integrates themes arising from the growing presence of artificial intelligence in our lives. Each episode is about 2 minutes.

Meet the stars of the show.

Homie

Lexy

The podcast’s short format is, by design, well-suited for the voiceweb, as I’m currently in development on voice apps for both Amazon and Google’s platforms. Once finished, the podcasts can be easily played on either platform. (Yes, podcasts can be played on Echo’s and Home’s currently, but having an app streamlines the process and makes it more reliable that episodes will be played upon invocation.)

The short comedy format is also a kind of return to one of my favorite advertising mediums, radio. Something I did a lot of in my early days of advertising. My radio-writing background, combined with my years of digital marketing experience and lifelong early adoption of technology, makes Homie & Lexy feel like the completion of a circle. The weekly episode process involves comedy writing, digital audio production, and then distribution and promotion.

The voices are generated using Amazon’s Polly text-to-speech technology, using Speech Synthesis Markup Language (SSML) to push, pull and wrangle the right prosody out of the voices.

If you listen to podcasts, or if this sounds interesting, please listen and subscribe at any of the providers below. Thanks.

AI: The new creative director or the new creative?

December 13, 2017 By Doug Schumacher

I’m not sure I’ve ever followed a story with the combination of awe and trepidation as AI for the past several years. The potential job displacement alone is staggering.

In the past, as a marketing person who trades in creative thinking, I’ve clung to the idea that however far technology might progress, jobs based in aesthetic judgement were in the clear zone for the foreseeable future.

Machine learning has been great on tasks with well-defined goals, like determining which ads in a campaign to give the most impressions to based on audience response. When the decision is highly subjective, though, it’s been a different situation. But that’s a barrier being broken through. Making the question not if creative jobs will be impacted, but how.

The recent AI experiment by Google is an example.

They turned an experimental deep learning system loose on their database of Street View images with the goal of artistic curation.

Per their blog post.

It mimics the workflow of a professional photographer, roaming landscape panoramas from Google Street View and searching for the best composition, then carrying out various postprocessing operations to create an aesthetically pleasing image.

Here are two of hundreds of beautiful images the AI selected, cropped and processed.

They had a team of professional photographers judge the results of the AI along side a range of other non-AI photos, with impressive results.

A threat, a tool, or both?

There should be a lot of ways to use AI for creative development. What I find interesting in the Google example is the training of the AI system. Talk to any AI expert and they’ll emphasize the importance of having good training data. Garbage in, garbage out.

Whatever you put into the system, that becomes the measuring stick. The Google team pulled the training database from several photography communities, using the human-generated rating system to define the aesthetic taste. (If you want the gory details, you can read the full research paper.)

So the tastes of the photographic communities drove the training data which defined the results. But presumably you could use whatever data you want to train the system, and that’s the direction it will go in. Your new creative brief is the training data. Deployed on the full data set, off it goes generating concepts or creatives or whatever. In remarkable volume. And it never complains or causes HR nightmares.

Sounds like a creative director’s dream. Or a chief marketing officer’s.

Using AI to help creatives generate more ideas seems pretty obvious. You start a project with 100s of loosely-relevant-but-possibly-tangentially-interesting ideas already on the board.

And AI may never be more than a powerful tool creatives have at their disposal. But like Photoshop and digital media in general, this is another way technology compresses deadlines and reduces budgets. It also gives agencies and creatives another learning curve to climb. With opportunities and pitfalls parallel to previous waves of technology.

And of course you shouldn’t ignore the possibility of AI becoming more of a threat than a tool.

The name of the Deep Learning system Google used to generate these images? Creatism. It’s stated purpose? Artistic content creation. You can almost hear a deep voice on a sizzle reel enthusing “Creatism, an artistic content creation agency.”

ai