September 9, 2026
5 mins

How to Operationalize a Content Spec in 2026: The System Behind Better Content, Part 2

This is Part 2 of our series, The System Behind Better Content, co-authored by Content Design Hub. You can read Part 1 here.

A content spec is a structured, testable document that defines how content should look, sound, and behave across a product, built from real user research so your team (and your AI tools) have a shared set of rules to work from. In Part 1, we showed you how you can create a content spec and what it might look like, but having the spec is only half the work. A document sitting in a folder doesn't change anything on its own, it has to be operationalized to earn its place in your workflow.

What’s inside

  • 7 places to add your spec so the whole team actually uses it
  • What AI gets wrong without a spec, and a full example prompt to fix it
  • The full spec cycle from research to AI guardrails to closing the loop

Embedding a content spec into existing workflows 

A content spec only delivers value if the whole team uses it. The spec makes that possible. If it’s in the spec, anyone can check against it. That includes product managers writing acceptance criteria, engineers writing automated test cases, and QA testers checking final screens.

7 places you could add your spec to

A spec needs to be embedded in the places where decisions happen. This could be your team’s:

  • Design system: make the spec into a component on Figma so content rules live where design happens.
  • Product management tool: include spec compliance in your definition of done so that no ticket closes without a content spec check.
  • Code repository: store the spec as Markdown (.md) in the repository so developers can reference it without leaving their workflow.
  • AI project files:  upload the spec to Claude project files or in a new chat of your preferred AI tool as a Markdown (.md) with your brand and tone guidelines and keywords list. Structure your instructions to read and strictly adhere to the guidelines so the AI tool applies the approved language every time they generate content (more on this in section 4). 
  • Sprint kickoffs: reference the spec when writing user stories and defining acceptance criteria.
  • Definitions of done: add "content checked against spec" as a required condition before any feature ships.
  • QA checklists: include spec compliance as a structured check alongside usability tests and live site tests

The key is to keep the spec visible to your teammates and easy to reference wherever your team works, including the AI tools your team uses.

Add AI guardrails: writing for your users, not someone else's defaults 

When AI tools generate content, they use their training data, but much of the publicly available digital content used to develop AI systems is disproportionately produced in Western and North American contexts. These perspectives differ from the lived experiences, cultural contexts, and perspectives of the users you are designing for. 

What AI gets wrong without a spec

Without a spec grounded in user research, AI writing tools can produce content that is grammatically correct and seemingly polished, but culturally misaligned.

For an Australian student finance app, that might look like: 

  • ‘Your 401(k) contributions’. In Australia, it’s called superannuation or super.
  • ‘Apply for social security benefits’. In Australia, this is Centrelink. The term, ‘social security’ means something entirely different.
  • ‘File your federal income tax’. In Australia, you lodge a tax return with the ATO (Australian Taxation Office).

These are not AI trivial errors. Nor are they hallucinations. AI got these terms correct, but for a different audience.

When content is not localized, you may not only alienate your users, but also create anxiety and erode trust. In a regulated industry like financial services, it can also create compliance risk.

What the content spec does for AI 

A content spec is one of the most effective prompt engineering assets your team can have. Prompt engineering is the practice of writing precise and reusable instructions that guide AI tools to produce consistent and predictable outputs.

When you feed your spec rules into an AI prompt, you give the model the guardrails so it doesn’t fill in the blanks and default to its training data.

Example prompt using a content spec

Role

You’re a content designer writing for a money management app aimed at Australian young people aged 18 to 24.

Context

Users may be managing money independently for the first time. They are familiar with informal language but need to learn formal financial terminology as part of using the app. Australian financial, tax, and welfare systems have specific terms that differ from other English-speaking countries.

Task

Write content for the app onboarding flow. Users will experience this flow when they sign up for the first time. The flow includes the welcome screen and account setup steps. It’s the first time a user will encounter key financial concepts like superannuation, HECS-HELP, and Centrelink payments. Each screen should introduce one concept at a time, explain it in plain English, and tell the user what action to take next.

Output

Screen-by-screen onboarding content, including headings, body copy, and button labels. Keep all sentences under 20 words. Each screen should have one heading, no more than 3 sentences of body copy, and one call-to-action.

Constraints

Use the content spec to guide your content decisions.

Use the acceptance criteria and user story to guide your deliverables.

Key rules include:

  • Use 'superannuation' on first mention, then 'super'
  • Use 'Centrelink payment,' not 'government benefit' or 'welfare'
  • Use 'lodge a tax return,' not 'file taxes'
  • Use 'transaction account,' not 'checking account'
  • Address users as 'you', never 'the user' or 'our customers'
  • Do not use North American financial terms (401k, social security, federal income tax)
  • Legal disclosures must use terminology required by ASIC guidelines and cannot be rewritten for style.

Validation

Before finalising any content, check it against the content spec. If a term does not appear in the approved list, flag it for review rather than substituting a synonym.

Confirmation

Before you draft the content, confirm you can:

  • Access and read the spec.
  • The screens you will create.
  • The user you are writing for.
  • User story and acceptance criteria.

With these prompt rules, your AI tool has a strong starting point and will give you a better first draft. 

The spec also helps teams evaluate AI output consistently. Instead of asking, “Does this sound right?’, you may question, “Does this align with our rules?”

Courses like AI Prompt Engineering for Content Creators can be a useful way to learn how to write effective AI prompts grounded in content design principles.

View content as a system, not a document

A content spec is a living system that connects user research to design decisions, team workflows, and AI tools. It's like a muscle; the more you use it, the stronger it gets. The more you add to it, the more accurate, reliable, and valuable it becomes.

Here's the full spec cycle:

  • Research: discover how your users think, talk, and group information.
  • Spec creation: turn those findings into explicit, testable rules.
  • Spec storage: add your spec to systems and places where it can be used and updated.
  • Team alignment: embed the spec in design reviews, sprint kickoffs, and definitions of done.
  • AI guardrails: feed the spec into AI prompts to get consistent, culturally appropriate and accurate outputs.
  • Close the loop: when research reveals a gap between user language and spec language, update the spec. The updated spec flows through everywhere content decisions are made (design guidelines, AI prompts, QA checklists, and developer documentation).

The content spec keeps your product human. It's rooted in research and reflects the context of your users; how they think, speak, and make sense of the world.

AI is now a standard part of content workflows. This means that the spec is no longer optional and is no longer just an engineering tool. Without a content spec, AI tools default to someone else's language, someone else's culture, and someone else's assumptions.

Product teams that invest in a content spec now are building a system that scales, learns, and most importantly, keeps the user at the centre of every decision.

Start with research. Build the spec. Keep your users in every decision.

Meet with us to learn how teams are using Optimal to transform interviews into insights and create content that truly connects. 

Share this article
Author
Optimal
Workshop

Related articles

View all blog articles
Header graphic for the article 'Ella Stoner: A three-step-tool to help designers break down...'
Learn more
1 min read

Ella Stoner: A three-step-tool to help designers break down the barriers of technical jargon

Designing in teams with different stakeholders can be incredibly complex. Each person looks at projects through their own lens, and can potentially introduce jargon and concepts that are confusing to others. Simplicity advocate Ella Stoner knows this scenario all too well. It’s what led her to create an easy three-step tool for recognizing problems and developing solutions. By getting everyone on the same page and creating an understanding of what the simplest solution is, designers can create products with customer needs in mind.

Ella’s background

Ella Stoner is a CX Designer at Spark in New Zealand. She is a creative thought leader and a talented designer who has facilitated over 50 Human Centered Design Workshops. Ella and her team have developed a cloud product that enables businesses to connect with Public Cloud Services such as Amazon, Google and Azure in a human-centric way. She brings a simplistic approach to her work that is reflected in her UX New Zealand talk. It’s about cutting out complex details to establish an agreed starting point that is easily understood by all team members.

Contact Details:

You can find Ella on LinkedIn.

Improving creative confidence 🤠

Ella is confident that she is not the only designer who has felt overwhelmed with technical and industry specific jargon in product meetings. For example, on Ella’s first day as a designer with Spark, she attended a meeting about an HSNS (High Speed Network Services) tool. Ella attempted to use context clues to try and predict what HSNS could mean. However, as the meeting went on, the technical and industry-specific jargon built on each other and Ella struggled to follow what was being said. At one point Ella asked the team to clarify this mysterious term:

“What’s an HSNS and why would the customer use it?” she asked. Much to her surprise, the room was completely silent. The team struggled to answer a basic question, about a term that appeared to be common knowledge during the meeting. There’s a saying, “Why do something simply when you can make it as complicated as possible?”. This happens all too often, where people and teams struggle to communicate with each other, and this results in projects and products that customers don’t understand and can’t use. Ella’s In A Nutshell tool is designed to cut through all that. It creates a base level starting point that’s understood by all, cuts out jargon, and puts the focus squarely on the customer. It:

  • condenses down language and jargon to its simplest form
  • translates everything into common language
  • flips it back to the people who’ll be using it.

Here’s how it works:

First, you complete this phrase as it pertains to your work: “In a nutshell, (project/topic) is (describe what the project or topic is in a few words), that (state what the project/topic does) for (indicate key customer/users and why). In order for this method to work, each of the four categories you insert must be simple and understandable. All acronyms, complex language, and technical jargon must be avoided.  In a literal sense, anyone reading the statement should be able to understand what is being said “in a nutshell.” When you’ve done this, you’ll have a statement that can act as a guide for the goals your project aims to achieve.

Why it matters 🤔

Applying the “In A Nutshell” tool doesn’t take long. However, it's important to write this statement as a team. Ideally, it’s best to write the statement at the start of a project, but you can also write it in the middle if you need to create a reference point, or any time you feel technical jargon creeping in.

Here’s what you’ll need to get started:

  • People with three or more role types (this accommodates varying perspectives to ensure it’s as relevant as possible)
  • A way to capture text - i.e. whiteboard, Slack channel, Miro board
  • An easy voting system - i.e., thumbs up in a chat

Before you start, you may need to pitch the idea to someone in a technical role. If you’re feeling lost or confused, chances are someone else will be too. Breaking down the technical concepts into easy-to-understand and digestible language is of utmost importance:

  1. Explain the Formula to the team..
  2. Individually brainstorm possible answers for each gap for three minutes.
  3. Put every idea up on the board or channel and vote on the best one.

Use the most popular answers as your final “In a Nutshell” statement.

Side note: Keep all the options that come through the brainstorm. They can still be useful in the design process to help form a full picture of what you’re working on, what it should do, who it should be for etc.

Header graphic for the article 'Content design for startups: how to work lean, have maximum...'
Learn more
1 min read

Content design for startups: how to work lean, have maximum impact, and get all the high-fives

When you have a small design team or none at all, how do you ensure that your content is consistent, has the right tone, and is captivating? It can be difficult, but it doesn’t have to be! Julia Steffen, Principal Content Designer at Varis, spoke at UX New Zealand, the leading UX and IA conference in New Zealand hosted by Optimal Workshop, about how startups can achieve impactful content and delight users. 

In her talk, Julia shares her most useful tips, tricks, and rules of thumb to ensure meaningful content design. She also shares some helpful tools to achieve maximum efficiency.

Julia Steffen bio 🎤

Julia has worked in content for 10+ years at St.Jude, Wunderman Thompson, MetaLab, and Grubhub. She is based in the United States and is the Principal Content Designer at Varis.

Contact Details:

Email address: julia.steffen@govaris.com

You can find Julia on LinkedIn

Content design for startups - How to work lean, have maximum impact, and get all the high-fives ✋🏽✋🏻✋🏿

Why should you care about content design? Julia argues that “content design is product success”. Because Julia specifically talks about content design in relation to startups, she focuses on how to achieve the best results possible with a small, lean team. To that end, Julia discusses four must-haves for content design:

  1. Voice
  2. Tools for efficiency
  3. Words in the experience
  4. Ways to check, test, and perfect your words

Voice 🎙️

Why is your company’s voice important? Voice tells your users who you are, creates meaningful connections, and provides valuable signals that convey whether or not your company is deserving of trust. Choosing the voice for your startup begins with a competitor audit.  Documenting who you compete against, and how you might want to differentiate your startup is crucial to finding your corner of the market. For example, is your voice welcoming, gentle, and positive, or are you more formal and technical? 

User research can also be really helpful when determining and monitoring your voice. Involve your research team and learn what does and doesn’t delight your audience when it comes to your messaging.

It’s also important to map your voice to your startup’s values. Be sure to connect to your mission and your brand. Julia sums up product voice as:

Product voice = your values + space to differentiate + what research tells you

So, when you find your voice, where can you lean into it? There are several key areas or moments that provide opportunities to share your unique voice, such as:

  • Notifications: Emails, SMS, and in-app messages are a great place to delight customers
  • Success states: Celebrate with your users in your voice (and remove any anxiety that may be there)
  • Empty states: They aren’t just a chance to educate, they’re a chance to add some interest or fun (or to mask a UX issue).
  • Placeholder text: If a field is well labeled, you can use this section to bring joy and reduce a user’s anxiety.
  • Onboarding: You never get a second chance to make a first impression. Make it count!

Tools for efficiency ⚒️

To remain lean and efficient as a startup, one of the best things you can do is create a style guide. This helps to keep your content and voice consistent. For example, what pronouns do you use in your interface, do you capitalize certain words, etc? There is actually a lot to consider here, so Julia points viewers to various resources that allow you to copy and paste, such as Quinn Keast’s Product Language Framework.

A glossary or language bank is also important. Record branded words, terms that you never use, and terms that you’ve heard your users say organically. This helps to ensure that you’re using language that resonates with your audience and language that reduces cognitive load as much as possible.

Pro tip: Use the Writer app with Figma. This integration helps to ensure that your style guide is actually used! It includes your style guide and glossary so that you’re being consistent as you work. You can also use the Hemingway app or Grammarly to look out for passive voice, hard-to-parse sentences, and overall readability.

Words in the experience – writing for content design 📝

The first thing Julia points out when approaching writing is the need to be user-focused. This might seem obvious to UX practitioners, but word selection can be nuanced, and subtle changes can be powerful. For example, instead of writing “[Your company] introduces a new feature”, think about how can you change the statement to be more about what the new feature means for the user, rather than your company. Here are a few rules of thumb to help refine your writing.

  • Clarity over cleverness. Unless you’re clear and the message is understood by your user, even the best jokes and wittiest phrases in the world will be wasted.
  • Write like you’re having a conversation with your Grandmother. Be clear and don’t use too much jargon.
  • Think like the best content designers. Writing is a process and there are several things to consider, such as the purpose of your copy, the context that it’s being read, and what emotion the reader might be feeling at that moment, etc. Julia offers the Microcopy Canvas as a useful tool for startups, which is a helpful writing template/worksheet created by Jane Ruffino.

Ways to check, test, and perfect your words 👀

Julia suggests that design reviews are the perfect place to sense-check your words and content. Review your designs intentionally and through a content lens. Again, the Microcopy Canvas can be a useful tool when conducting this step, helping to ensure you have considered the right tone and achieved your purpose with your words.

Following a design review process, it’s important to test for clarity and affinity. Conduct user tests frequently to ensure your words and content are clear, understood, and hitting the mark in the intended way.

Finally, make sure your content goals are recorded in your dashboards. Be accountable to your own success measures, KPIs, and OKRs (Objectives and Key Results). Some metrics that help track success are:

  • Onboarding flows
  • Notification metrics
  • Feature adoption
  • Conversion rates

If you’re falling short on some metrics, review your content and try to figure out where words can be sharpened to be clearer, more friendly, or less technical, for example. Then, feed this information into your prioritization and planning. What changes are going to have the most impact on your product’s success? What changes are quick wins? 

Why it matters 🤯

Julia’s talk is important for UX and content designers, particularly those working in startup environments, as it highlights the critical role of content design in achieving product success. The content you share, the voice and tone you adopt, and the clarity of communication, all add to the user's overall experience with your product. Investing time into your content is critical and, as Julia explains, it doesn’t have to put too much stress on your team's workload. If time isn’t invested, however, you may find yourself with poor content, delivering poor experiences, resulting in high customer attrition. 

Efficiency, therefore, should be a focus for startups wanting to achieve great content design without being weighed down. Julia offers pragmatic advice on maintaining consistency through tools like style guides and language banks and by leveraging apps like Hemingway and Grammarly. Tools like these are incredibly helpful when streamlining processes and ensuring a cohesive and polished user interface. 

At the end of the day, Julia stresses the impact that content design has on user experiences and encourages startups to pay close attention to content in ways that are achievable for small teams.

Learn more
1 min read

How to Operationalize a Content Spec in 2026: The System Behind Better Content, Part 2

This is Part 2 of our series, The System Behind Better Content, co-authored by Content Design Hub. You can read Part 1 here.

A content spec is a structured, testable document that defines how content should look, sound, and behave across a product, built from real user research so your team (and your AI tools) have a shared set of rules to work from. In Part 1, we showed you how you can create a content spec and what it might look like, but having the spec is only half the work. A document sitting in a folder doesn't change anything on its own, it has to be operationalized to earn its place in your workflow.

What’s inside

  • 7 places to add your spec so the whole team actually uses it
  • What AI gets wrong without a spec, and a full example prompt to fix it
  • The full spec cycle from research to AI guardrails to closing the loop

Embedding a content spec into existing workflows 

A content spec only delivers value if the whole team uses it. The spec makes that possible. If it’s in the spec, anyone can check against it. That includes product managers writing acceptance criteria, engineers writing automated test cases, and QA testers checking final screens.

7 places you could add your spec to

A spec needs to be embedded in the places where decisions happen. This could be your team’s:

  • Design system: make the spec into a component on Figma so content rules live where design happens.
  • Product management tool: include spec compliance in your definition of done so that no ticket closes without a content spec check.
  • Code repository: store the spec as Markdown (.md) in the repository so developers can reference it without leaving their workflow.
  • AI project files:  upload the spec to Claude project files or in a new chat of your preferred AI tool as a Markdown (.md) with your brand and tone guidelines and keywords list. Structure your instructions to read and strictly adhere to the guidelines so the AI tool applies the approved language every time they generate content (more on this in section 4). 
  • Sprint kickoffs: reference the spec when writing user stories and defining acceptance criteria.
  • Definitions of done: add "content checked against spec" as a required condition before any feature ships.
  • QA checklists: include spec compliance as a structured check alongside usability tests and live site tests

The key is to keep the spec visible to your teammates and easy to reference wherever your team works, including the AI tools your team uses.

Add AI guardrails: writing for your users, not someone else's defaults 

When AI tools generate content, they use their training data, but much of the publicly available digital content used to develop AI systems is disproportionately produced in Western and North American contexts. These perspectives differ from the lived experiences, cultural contexts, and perspectives of the users you are designing for. 

What AI gets wrong without a spec

Without a spec grounded in user research, AI writing tools can produce content that is grammatically correct and seemingly polished, but culturally misaligned.

For an Australian student finance app, that might look like: 

  • ‘Your 401(k) contributions’. In Australia, it’s called superannuation or super.
  • ‘Apply for social security benefits’. In Australia, this is Centrelink. The term, ‘social security’ means something entirely different.
  • ‘File your federal income tax’. In Australia, you lodge a tax return with the ATO (Australian Taxation Office).

These are not AI trivial errors. Nor are they hallucinations. AI got these terms correct, but for a different audience.

When content is not localized, you may not only alienate your users, but also create anxiety and erode trust. In a regulated industry like financial services, it can also create compliance risk.

What the content spec does for AI 

A content spec is one of the most effective prompt engineering assets your team can have. Prompt engineering is the practice of writing precise and reusable instructions that guide AI tools to produce consistent and predictable outputs.

When you feed your spec rules into an AI prompt, you give the model the guardrails so it doesn’t fill in the blanks and default to its training data.

Example prompt using a content spec

Role

You’re a content designer writing for a money management app aimed at Australian young people aged 18 to 24.

Context

Users may be managing money independently for the first time. They are familiar with informal language but need to learn formal financial terminology as part of using the app. Australian financial, tax, and welfare systems have specific terms that differ from other English-speaking countries.

Task

Write content for the app onboarding flow. Users will experience this flow when they sign up for the first time. The flow includes the welcome screen and account setup steps. It’s the first time a user will encounter key financial concepts like superannuation, HECS-HELP, and Centrelink payments. Each screen should introduce one concept at a time, explain it in plain English, and tell the user what action to take next.

Output

Screen-by-screen onboarding content, including headings, body copy, and button labels. Keep all sentences under 20 words. Each screen should have one heading, no more than 3 sentences of body copy, and one call-to-action.

Constraints

Use the content spec to guide your content decisions.

Use the acceptance criteria and user story to guide your deliverables.

Key rules include:

  • Use 'superannuation' on first mention, then 'super'
  • Use 'Centrelink payment,' not 'government benefit' or 'welfare'
  • Use 'lodge a tax return,' not 'file taxes'
  • Use 'transaction account,' not 'checking account'
  • Address users as 'you', never 'the user' or 'our customers'
  • Do not use North American financial terms (401k, social security, federal income tax)
  • Legal disclosures must use terminology required by ASIC guidelines and cannot be rewritten for style.

Validation

Before finalising any content, check it against the content spec. If a term does not appear in the approved list, flag it for review rather than substituting a synonym.

Confirmation

Before you draft the content, confirm you can:

  • Access and read the spec.
  • The screens you will create.
  • The user you are writing for.
  • User story and acceptance criteria.

With these prompt rules, your AI tool has a strong starting point and will give you a better first draft. 

The spec also helps teams evaluate AI output consistently. Instead of asking, “Does this sound right?’, you may question, “Does this align with our rules?”

Courses like AI Prompt Engineering for Content Creators can be a useful way to learn how to write effective AI prompts grounded in content design principles.

View content as a system, not a document

A content spec is a living system that connects user research to design decisions, team workflows, and AI tools. It's like a muscle; the more you use it, the stronger it gets. The more you add to it, the more accurate, reliable, and valuable it becomes.

Here's the full spec cycle:

  • Research: discover how your users think, talk, and group information.
  • Spec creation: turn those findings into explicit, testable rules.
  • Spec storage: add your spec to systems and places where it can be used and updated.
  • Team alignment: embed the spec in design reviews, sprint kickoffs, and definitions of done.
  • AI guardrails: feed the spec into AI prompts to get consistent, culturally appropriate and accurate outputs.
  • Close the loop: when research reveals a gap between user language and spec language, update the spec. The updated spec flows through everywhere content decisions are made (design guidelines, AI prompts, QA checklists, and developer documentation).

The content spec keeps your product human. It's rooted in research and reflects the context of your users; how they think, speak, and make sense of the world.

AI is now a standard part of content workflows. This means that the spec is no longer optional and is no longer just an engineering tool. Without a content spec, AI tools default to someone else's language, someone else's culture, and someone else's assumptions.

Product teams that invest in a content spec now are building a system that scales, learns, and most importantly, keeps the user at the centre of every decision.

Start with research. Build the spec. Keep your users in every decision.

Meet with us to learn how teams are using Optimal to transform interviews into insights and create content that truly connects. 

Seeing is believing

Explore our tools and see how Optimal makes gathering insights simple, powerful, and impactful.