Branded Language Translator
Using Natural Language Processing, we built a product to translate any text into branded corporate language of a company. The translator aims to make communication towards customers or business partner more consistent while reducing workload of editorial writers and marketing.
Disclaimer: as this project was developed under NDA, I am showing simplified designs I custom made for this showcase.
My Role
Lead Product Designer
Company & Industry
Vodafone Center of Excellence AI
Telecommuncation Industry
Team Composition
Lead Product Designer
Product Owner
2 Frontend Devs
Data Scientist
Data Engineer
Agile Coach
1 Backend Dev
Solution Architect
My Key Contributions
Stakeholder Interviews
User Research
Lo- & HiFi Designs
User Testing & QA
Feature Prioritization
KPI Definition & Refinement
Market & Competitor Research
Roadmap Planning
Vision Crafting
Selected Final Designs
The Challenge
1/4
Especially high impact and customer-facing projects demand strict adherence of branded language guidelines
In busy times this can mean delayed content launches, missed opportunities, and higher operational costs
The design system was chaotic as components and tokens were reused inconsistently as well as improperly
There was no single source of truth as developed designs were not consistent to the design system components
Different departments used inconsistent language which was weakening brand clarity and trust
Editorial writers at the company have a high work load causing bottlenecks and inconsistent branding
Checking every piece of content for brand adherence takes hours often requiring multiple approvals
This causes teams to skip wording refinement to not compromise dead lines leading to inconsistent communication
Editorial Writers have more responsibilities within companies than checking and refining texts which they could focus more time on if this problem was solved
Branded writing is something that can be automated well but as of the beginning of this project, there was no solution for it
This meant for us that we need to start from scratch, with no prior work that could be utilised
Especially as GenAI was a hot topic at the start of this project, we had to figure out how we can utilise these advancements to reaching our goals
We needed to build something flexible enough to work across departments
My Objectives
2/4
Understand user workflows across various departments such as marketing, legal or design
Define and validate MVP based on real user needs and business requirements
Design intuitive interactions for text transformation and tone customization
Support the team in reducing development risks through clear prototypes and early testing
Ensure the product could scale in value and complexity over time
My Key Contributions
3/4
Research & Discovery
Conducted in-depth interviews and contextual inquiries with stakeholders across various departments
Analyzed how and why existing content gets edited manually
Redesigned the map view and designed new map features so network operators and other target groups could access needed information quicker
Cleaned up overloaded dashboards to focus on what actually matters
Designed several must have features that were lacking in the app but needed by the users such as image upload or task ticketing
Design & Testing
Led and executed the design in tight collaboration with PO, Devs and Data Engineers
Sketched and prototyped ideas to understand user requirements more deeply, explore further opportunities and reduce development efforts
Ran usability tests to validate core flows like text input, translation or onboarding and refined interactions such as loading state
Designed interactions for tone previews, rewrite suggestions, and user feedback
From MVP to Iteration
Designed the first working version of the product, focusing on the needs of the primary target group, clarity and ease of use
Continued improving the interface and adding features based on feedback and usage
Supported development with deliverables such as user research insights, edge case explorations, and QAs
Strategy & Vision
Contributed to the product vision and long-term positioning starting as a helpful tool and becoming a smart writing companion on the way
Contributed in defining meaningful KPIs to help with strategic decision making and transparency
Contributed and facilitate prioritising features balancing user and business needs and taking in account impact, effort, vision-fit and enablement
Introduced a hypotheses driven way of working to keep of the focus on the most important issues
Impact & Reflection
3/3
Users across various departments reported saving circa 30% to 60% of their time compared to manually writing branded texts
Users felt more confident sending out copy using the translator without the extra step of checking in with the branding editorial team
Feedback showed that users trusted their translated texts and felt they were aligned with company guidelines helping them focus more on the content
For high-impact communication a check in with branding was still needed but even in those cases the translator saved time for both sides
The translated texts were compliant with the official branding rules in almost all cases
While here and there mistakes and bugs occurred, safety features like the compliance ranking helped users identify errors before sending those texts out
For departments and sub-companies with own distinct branding guidelines, a customised ruleset can be integrated
Users utilised the translator in way more use cases than we anticipated
The translator was reportedly used for all kinds of communication from basic emails to website copy or job postings
Various departments approached us with feature requests for their individual use cases which helped us identify optimal next steps and opened up opportunities
This helped immensely with securing a backing of important stakeholders for the products future
