Iron Software Design · 2026
Ender Turing SaaS B2C Analysis
- A' Design Award 2026 Iron Winner in Software Design
- Awarded April 15, 2026
- CLIENT: Ender Turing
- Estimated Number of Design Views: 5,817
- Verification code 7A0CBC1342 · Verify this award
About Ender Turing SaaS B2C Analysis
Ender Turing is a cloud based software platform for the analysis of customer service conversations. Calls and chats are scored automatically by artificial intelligence, which shortens quality assurance routines. Natural language processing supports text classification, sentiment analysis, entity recognition, translation and summarization. Custom models can be built with a drag and drop interface, and pre-trained models can be added to other applications. Flexible filters, custom scorecards and data visualization help supervisors monitor interactions.
Ender Turing SaaS B2C Analysis by Lidiia Suslova represents a significant achievement within the specialized domain of enterprise software interface design and data visualization, demonstrating sophisticated understanding of how complex business intelligence can be rendered both functionally accessible and visually refined through thoughtful application of contemporary digital design principles. The work engages with established traditions of information design pioneered by foundational theorists and practitioners who established that quantitative data visualization serves not merely as functional necessity but as opportunity for aesthetic consideration and user-centered communication, positioning this dashboard within ongoing conversations about how digital interfaces can balance analytical density with visual clarity and cognitive ease. The compositional architecture reveals careful attention to systematic grid structures and modular organization principles that enable scalability and responsive adaptation across viewing contexts while maintaining visual coherence, suggesting familiarity with design systems methodology and component-based interface construction that characterizes mature digital product design practice. The chromatic strategy demonstrates particular sophistication in its deployment of color as both categorical encoder and affective communicator, where the segmented donut charts employ warm-to-cool progressions that intuitively map to qualitative gradations from problematic to excellent performance, enabling rapid pattern recognition while maintaining aesthetic harmony through related hue families and consistent saturation levels that avoid harsh contrast or chromatic discord. Technical execution throughout reveals mastery of vector-based digital illustration, typographic refinement with appropriate hierarchy through size and weight variation, and strategic use of subtle dimensional cues including soft shadows and gentle gradients that suggest layered depth without compromising the predominantly flat contemporary aesthetic, demonstrating understanding of current interface design conventions that favor clarity and directness over decorative elaboration. The integration of three-dimensional product visualization within the lower right portion introduces material tangibility and surface realism that effectively complements rather than conflicts with the abstract data representations, suggesting the dashboard's connection to physical product analytics while providing visual variety and focal interest through rendering technique that captures light behavior on glossy cylindrical forms. The work invites consideration of how business intelligence tools can transcend purely utilitarian function to become environments where professionals spend substantial portions of their working lives, raising questions about the role of visual refinement, chromatic thoughtfulness, and compositional grace in reducing cognitive fatigue and supporting sustained analytical engagement, while the careful balance between information density and generous negative space demonstrates respect for human perceptual limitations and the value of visual breathing room in complex data environments. One might contemplate how this dashboard's particular formal choices, from its soft purple accent color to its circular visualization motifs to its systematic spatial organization, create not merely functional clarity but also distinctive visual identity that differentiates one analytical platform from another in an increasingly crowded marketplace, and whether such aesthetic considerations ultimately serve user experience through creating memorable, pleasant, and visually coherent working environments that support rather than impede the serious analytical work these tools enable.
Press Kit
- Unique Properties
- Ender Turing offers unique customer experience solutions, enhancing revenue and loyalty. Real-time analytics on employee-customer interactions empower informed decision-making.
Our AI platform automates QA routines, uncovers business insights, and boosts agent performance through continuous coaching. - Dimensions & Packaging
- The core purpose of the Ender Turing engine is to facilitate users in crafting and refining AI models capable of comprehending and generating human-like language. This platform offers a comprehensive suite of Natural Language Processing (NLP) capabilities, encompassing tasks such as text classification, sentiment analysis, entity recognition, language translation, and text summarization, among others. Users have the flexibility to construct tailored models through Ender Turing's intuitive drag-and-drop interface, or seamlessly integrate pre-trained models into their applications via the platform's API.
- Tags
- Artificial intelligence, AI, Natural language processing, NLP, Machine learning, ML, Text classification, Sentiment analysis, Data processing, Text summarization, API, Cloud-based platform, Language modeling, Text mining, Call center, Analysis, Scoring
- Production Technology
- Utilizing a data-driven design methodology, we collected feedback by directly observing and interviewing our product's customers. Our decisions were guided by the identification of user pain points and areas of frustration. The outcome is a product solution that effectively addresses the concerns of business. Leveraging insights gained, our solution drives revenue growth by enabling informed decision-making and strategic planning, enhancing business productivity, reducing stress, and offering an intuitive user experience. Moreover, our interface supports over 10 languages, ensuring accessibility and usability across diverse user bases.
- Design Challenge
- Experiments were conducted to assess hypotheses and validate design decisions. Our findings revealed that our user base consists largely of non-technical individuals who favor a more prominent communication style. Consequently, we refrain from employing complex logic constructions and cumbersome interface designs. Instead, our UX solutions undergo continual refinement to ensure simplicity and ease of use.
- Project Duration
- The project commenced its journey in June 2020 in Tallinn, Estonia. Design efforts for the project began in January 2022 and are currently ongoing, with continuous development and enhancement. Notably, the product achieved recognition as the winner at the Latitude59 pitching competition in May 2022, held in Tallinn, Estonia. Additionally, it secured the 2nd place position at the Infoshare Startup Contest in October 2022, hosted in Gdansk, Poland, amidst stiff competition from 500 startups worldwide. Moreover, our team achieved the distinction of Best Seed startup at the Valencia Digital Summit conference in October 2023!
- Operation Flow
- Our solution offers a 20-fold speed increase in scoring calls and chats, powered by automated AI pre-scoring and quality assurance. It also extracts valuable business insights, allowing users to efficiently monitor interactions with flexible filters. With seamless scorecard customization and robust data visualization tools, informed decision-making is empowered. These capabilities optimize operations and enhance customer experiences, contributing to revenue growth.
- Research
- Engaging with end users, including data center supervisors and stakeholders, we collected data via interviews, surveys, observations, and competitive analysis. Our key finding is the potential of call center data analysis to boost revenue through invaluable insights for informed decision-making. This approach unveils user and business needs, guiding tailored solutions.
- Inspiration
- Market Demand: Recognizing the growing need for effective CX solutions in various industries.
Efficiency: Seeking ways to streamline processes within contact centers, QA automation, real-time analysis and revelation business insights.
Customer Satisfaction: Understanding the importance of delivering exceptional customer service to foster loyalty and drive revenue growth.
AI Technology: Leveraging advancements in AI and ML to develop innovative solutions that can adapt and evolve over time. - Image Credits
- Lidiia Suslova
- Patents
- Scientific publications: 1. Transferability Evaluation of Speech Emotion Recognition Between Different Languages January 2022 DOI:10.1007/978-3-031-04812-8_35 In book: Advances in Computer Science for Engineering and Education (pp.413-426) Ievgen Iosifov Olena Iosifova Oleh Romanovskyi Vladimir Sokolov 2. Automated Pipeline for Training Dataset Creation from Unlabeled Audios for Automatic Speech Recognition July 2021 DOI:10.1007/978-3-030-80472-5_3 In book: Advances in Computer Science for Engineering and Education IV (pp.25-36) Oleh Romanovskyi Ievgen Iosifov Olena Iosifova Vladimir Sokolov 3. Analysis of Automatic Speech Recognition Methods January 2021 Conference: Cybersecurity Providing in Information and Telecommunication SystemsAt: Kyiv, Ukraine Olena Iosifova Ievgen Iosifov Vladimir Sokolov Oleh Romanovskyi Igor Sukaylo 4. Sentence Segmentation from Unformatted Text using Language Modeling and Sequence Labeling Approaches October 2020 DOI:10.1109/PICST51311.2020.9468084 Conference: 2020 IEEE International Conference on Problems of Infocommunications. Science and Technology (PIC S&T) Ievgen Iosifov Olena Iosifova Vladimir Sokolov 5. Methods and components of natural language processing August 2020 Adaptive automatic control systems 1(36):93-113 DOI:10.20535/1560-8956.36.2020.209780 Olena Iosifova Ievgen Iosifov Oleksandr Rolik 6. Techniques Comparison for Natural Language Processing June 2020 DOI:10.5281/zenodo.3895814 Conference: 2nd International Workshop on Modern Machine Learning Technologies and Data ScienceAt: Lviv-Shatsk, Ukraine Olena Iosifova Ievgen Iosifov Oleksandr Rolik Vladimir Sokolov
Colors of Ender Turing SaaS B2C Analysis
Design Interview about Ender Turing SaaS B2C Analysis
The project started from a very practical observation:
companies already have huge amounts of customer insight inside conversations, but most of it is never really used.
Traditional QA workflows usually review only a small percentage of calls manually. Everything else disappears into archives because there’s simply too much information to process consistently.
What interested me most wasn’t only the AI side of the system. It was the human side.
How do you help people quickly understand what actually matters?
How do you surface patterns without overwhelming users with dashboards and noise?
How do you make large-scale conversational data feel clear instead of intimidating?
That became the core direction of the design.
A lot of the work was really about reducing complexity at the interface level while still preserving depth underneath.
companies already have huge amounts of customer insight inside conversations, but most of it is never really used.
Traditional QA workflows usually review only a small percentage of calls manually. Everything else disappears into archives because there’s simply too much information to process consistently.
What interested me most wasn’t only the AI side of the system. It was the human side.
How do you help people quickly understand what actually matters?
How do you surface patterns without overwhelming users with dashboards and noise?
How do you make large-scale conversational data feel clear instead of intimidating?
That became the core direction of the design.
A lot of the work was really about reducing complexity at the interface level while still preserving depth underneath.
The biggest focus was usability under real operational conditions.
The platform processes large amounts of conversational data across multiple languages, but raw AI output alone is not very useful if people cannot confidently act on it.
So the goal became making the system feel understandable for non-technical users:
supervisors, QA specialists, operations teams, business stakeholders.
I wanted people to open the platform and quickly understand:
what needs attention,
what changed,
what patterns are repeating,
where the problems actually are.
A lot of AI products look impressive during demos but become exhausting in everyday use. I wanted this system to feel useful in real workflows, not just visually sophisticated.
The platform processes large amounts of conversational data across multiple languages, but raw AI output alone is not very useful if people cannot confidently act on it.
So the goal became making the system feel understandable for non-technical users:
supervisors, QA specialists, operations teams, business stakeholders.
I wanted people to open the platform and quickly understand:
what needs attention,
what changed,
what patterns are repeating,
where the problems actually are.
A lot of AI products look impressive during demos but become exhausting in everyday use. I wanted this system to feel useful in real workflows, not just visually sophisticated.
The platform is gradually evolving from a QA-focused system into something closer to customer intelligence infrastructure.
Initially the focus was operational:
agent performance, call quality, compliance, coaching.
Now the more interesting direction is understanding broader customer behavior through conversations:
complaints, product friction, pricing concerns, sentiment shifts, recurring patterns.
That changes the design challenge quite a lot.
A supervisor and a business owner consume information very differently. One lives inside the platform daily. The other needs strategic clarity very quickly.
So a lot of the current work is around adaptive dashboards, information hierarchy, data visualization, and helping different types of users navigate large amounts of information without getting overloaded.
Initially the focus was operational:
agent performance, call quality, compliance, coaching.
Now the more interesting direction is understanding broader customer behavior through conversations:
complaints, product friction, pricing concerns, sentiment shifts, recurring patterns.
That changes the design challenge quite a lot.
A supervisor and a business owner consume information very differently. One lives inside the platform daily. The other needs strategic clarity very quickly.
So a lot of the current work is around adaptive dashboards, information hierarchy, data visualization, and helping different types of users navigate large amounts of information without getting overloaded.
The project evolved over multiple years.
The early stages involved a lot of research into how contact centers actually work day-to-day:
observing workflows, speaking with supervisors, understanding where decisions slow down or break.
The first versions were honestly much more complicated than they needed to be.
That became one of the biggest lessons of the project:
the more powerful the underlying system becomes, the more clarity the interface requires.
Over time the design moved toward simpler navigation, clearer prioritization, and faster access to actionable information.
And realistically, systems like this are never fully finished. They continue evolving together with the workflows around them.
The early stages involved a lot of research into how contact centers actually work day-to-day:
observing workflows, speaking with supervisors, understanding where decisions slow down or break.
The first versions were honestly much more complicated than they needed to be.
That became one of the biggest lessons of the project:
the more powerful the underlying system becomes, the more clarity the interface requires.
Over time the design moved toward simpler navigation, clearer prioritization, and faster access to actionable information.
And realistically, systems like this are never fully finished. They continue evolving together with the workflows around them.
The project itself was commissioned, but many of the core design decisions came from the research process rather than the original brief.
The original goal was relatively straightforward:
build an AI-powered analytics platform for conversation quality management.
But after observing real operational environments, the problem became much more interesting.
The challenge was not simply displaying AI-generated information.
It was helping people make faster and clearer decisions under pressure.
That shifted the entire direction of the design.
The original goal was relatively straightforward:
build an AI-powered analytics platform for conversation quality management.
But after observing real operational environments, the problem became much more interesting.
The challenge was not simply displaying AI-generated information.
It was helping people make faster and clearer decisions under pressure.
That shifted the entire direction of the design.
Yes, the platform is actively used by companies across multiple industries including fintech, insurance, operations, and customer support environments.
It’s a real production system used in daily workflows, not a conceptual project.
That was actually one of the most valuable parts of the experience for me:
seeing how the design behaves under real operational conditions and continuously refining it based on live usage.
A lot of design decisions only reveal their strengths or weaknesses once real teams start depending on the system every day.
It’s a real production system used in daily workflows, not a conceptual project.
That was actually one of the most valuable parts of the experience for me:
seeing how the design behaves under real operational conditions and continuously refining it based on live usage.
A lot of design decisions only reveal their strengths or weaknesses once real teams start depending on the system every day.
I’m naturally drawn to products where complexity is unavoidable.
Enterprise SaaS, fintech, analytics platforms, Voice of Customer systems - these environments force you to think beyond individual screens very quickly.
What interested me here was the combination of AI, large-scale data visualization, and operational decision-making.
The difficult part wasn’t “how do we show more information?”
It was:
how do we make large amounts of information understandable and usable for actual humans?
That balance between complexity and clarity is probably the type of problem I enjoy most.
Enterprise SaaS, fintech, analytics platforms, Voice of Customer systems - these environments force you to think beyond individual screens very quickly.
What interested me here was the combination of AI, large-scale data visualization, and operational decision-making.
The difficult part wasn’t “how do we show more information?”
It was:
how do we make large amounts of information understandable and usable for actual humans?
That balance between complexity and clarity is probably the type of problem I enjoy most.
Probably more product systems than individual designers.
I’ve always appreciated products that make complex environments feel manageable without pretending the complexity doesn’t exist.
Systems like Stripe, Linear, and some financial platforms influenced how I think about clarity, hierarchy, and structured information flow.
Dieter Rams also influenced my thinking quite a lot, especially his focus on restraint and reduction.
In enterprise systems every unnecessary element creates cognitive load very quickly, so simplicity becomes operationally important, not just aesthetic.
I’ve always appreciated products that make complex environments feel manageable without pretending the complexity doesn’t exist.
Systems like Stripe, Linear, and some financial platforms influenced how I think about clarity, hierarchy, and structured information flow.
Dieter Rams also influenced my thinking quite a lot, especially his focus on restraint and reduction.
In enterprise systems every unnecessary element creates cognitive load very quickly, so simplicity becomes operationally important, not just aesthetic.
The platform serves several types of users at the same time.
Operational teams use it daily for quality management, coaching, performance tracking, and workflow monitoring.
At the same time, higher-level stakeholders use it to identify broader customer behavior patterns and operational trends across conversations.
One of the more interesting design challenges was building a system that works both for people deeply inside operations and for people who need fast strategic visibility without spending hours inside dashboards.
Operational teams use it daily for quality management, coaching, performance tracking, and workflow monitoring.
At the same time, higher-level stakeholders use it to identify broader customer behavior patterns and operational trends across conversations.
One of the more interesting design challenges was building a system that works both for people deeply inside operations and for people who need fast strategic visibility without spending hours inside dashboards.
I think the biggest difference is the focus on operational usability rather than simply showcasing AI capabilities.
A lot of AI analytics products become extremely feature-heavy very quickly.
Too many dashboards.
Too much information.
Too much cognitive overhead.
We focused much more on prioritization, clarity, and helping users navigate large amounts of information without feeling overwhelmed.
Another important aspect was scalability.
The system handles multilingual workflows, complex analytics, and large amounts of conversational data simultaneously, so maintaining coherence across the experience became a major part of the design work.
A lot of AI analytics products become extremely feature-heavy very quickly.
Too many dashboards.
Too much information.
Too much cognitive overhead.
We focused much more on prioritization, clarity, and helping users navigate large amounts of information without feeling overwhelmed.
Another important aspect was scalability.
The system handles multilingual workflows, complex analytics, and large amounts of conversational data simultaneously, so maintaining coherence across the experience became a major part of the design work.
The name was inspired by ideas around intelligence, pattern recognition, and understanding large amounts of information quickly.
The goal of the platform was never simply “analyze conversations.”
It was helping people identify meaningful signals inside extremely large amounts of communication data.
So the naming direction reflected that broader idea of interpreting complexity rather than just processing data.
The goal of the platform was never simply “analyze conversations.”
It was helping people identify meaningful signals inside extremely large amounts of communication data.
So the naming direction reflected that broader idea of interpreting complexity rather than just processing data.
Figma was the primary environment for interface design, prototyping, and system structure.
For research and workflow mapping I used Miro and Notion quite heavily.
More recently the workflow also expanded into AI-assisted design pipelines using tools like Cursor, Claude, Figma Make, and Storybook for design system consistency and component validation.
As systems become larger and more iterative, maintaining coherence across design, logic, and implementation becomes just as important as creating screens themselves.
For research and workflow mapping I used Miro and Notion quite heavily.
More recently the workflow also expanded into AI-assisted design pipelines using tools like Cursor, Claude, Figma Make, and Storybook for design system consistency and component validation.
As systems become larger and more iterative, maintaining coherence across design, logic, and implementation becomes just as important as creating screens themselves.
Probably the balance between scale and clarity.
The platform processes very large amounts of conversational information continuously, but the interface tries to surface only what is contextually important for a specific user at a specific moment.
That required a lot of work around hierarchy, progressive disclosure, adaptive design systems, and data visualization.
As the platform grew, maintaining coherence became much harder than generating new functionality.
In many ways the real design work was not creating screens.
It was keeping the system understandable while the complexity underneath kept increasing.
The platform processes very large amounts of conversational information continuously, but the interface tries to surface only what is contextually important for a specific user at a specific moment.
That required a lot of work around hierarchy, progressive disclosure, adaptive design systems, and data visualization.
As the platform grew, maintaining coherence became much harder than generating new functionality.
In many ways the real design work was not creating screens.
It was keeping the system understandable while the complexity underneath kept increasing.
Very closely.
The project involved collaboration with engineers, product teams, AI specialists, data teams, QA teams, and operational stakeholders.
For systems like this, design decisions are deeply connected to technical constraints and workflow realities, so constant communication across disciplines was necessary.
A lot of the strongest design decisions came from understanding how people actually work under pressure rather than designing from assumptions.
The project involved collaboration with engineers, product teams, AI specialists, data teams, QA teams, and operational stakeholders.
For systems like this, design decisions are deeply connected to technical constraints and workflow realities, so constant communication across disciplines was necessary.
A lot of the strongest design decisions came from understanding how people actually work under pressure rather than designing from assumptions.
Technology creates the possibility space, but design determines whether people can realistically use it.
The AI layer processes huge amounts of information:
speech recognition, sentiment analysis, conversational patterns, multilingual processing.
But without good interface structure, that complexity quickly becomes overwhelming.
The design work was really about translating large-scale AI outputs into something understandable, actionable, and operationally useful for humans.
The AI layer processes huge amounts of information:
speech recognition, sentiment analysis, conversational patterns, multilingual processing.
But without good interface structure, that complexity quickly becomes overwhelming.
The design work was really about translating large-scale AI outputs into something understandable, actionable, and operationally useful for humans.
Yes, heavily.
The project involved direct observation of operational workflows, structured interviews, usability testing, and continuous iteration based on real usage patterns.
One important thing I learned is that users often behave very differently in real environments compared to how they describe their behavior during interviews.
So a lot of the most valuable insights came from observing friction points during actual usage:
where people slowed down,
what they ignored,
what created confusion,
what required unnecessary cognitive effort.
That research shaped most of the major structural decisions inside the platform.
The project involved direct observation of operational workflows, structured interviews, usability testing, and continuous iteration based on real usage patterns.
One important thing I learned is that users often behave very differently in real environments compared to how they describe their behavior during interviews.
So a lot of the most valuable insights came from observing friction points during actual usage:
where people slowed down,
what they ignored,
what created confusion,
what required unnecessary cognitive effort.
That research shaped most of the major structural decisions inside the platform.
One of the biggest challenges was balancing complexity and usability.
The system processes enormous amounts of information, but the users are not necessarily technical specialists.
So the interface needed to feel clear without oversimplifying the underlying logic.
Another challenge was multilingual scalability.
Different languages create very different interface and communication behaviors, especially in conversational systems.
And probably the hardest long-term challenge was maintaining coherence while the platform kept expanding in scope over time.
As systems grow, consistency becomes much harder than feature creation.
The system processes enormous amounts of information, but the users are not necessarily technical specialists.
So the interface needed to feel clear without oversimplifying the underlying logic.
Another challenge was multilingual scalability.
Different languages create very different interface and communication behaviors, especially in conversational systems.
And probably the hardest long-term challenge was maintaining coherence while the platform kept expanding in scope over time.
As systems grow, consistency becomes much harder than feature creation.
The project solved a genuinely difficult design problem, but most people outside the industry would never normally see this type of work.
Enterprise systems and operational platforms often stay relatively invisible compared to consumer products.
Submitting it to an international competition felt like a good opportunity to present the thinking behind the system:
the UX challenges,
the information architecture,
the AI-human interaction layer,
the operational complexity.
The recognition also helped bring visibility to a type of product design work that usually stays behind the scenes.
Enterprise systems and operational platforms often stay relatively invisible compared to consumer products.
Submitting it to an international competition felt like a good opportunity to present the thinking behind the system:
the UX challenges,
the information architecture,
the AI-human interaction layer,
the operational complexity.
The recognition also helped bring visibility to a type of product design work that usually stays behind the scenes.
Probably the biggest lesson was that trust matters more than technical sophistication.
People don’t trust systems simply because the AI is powerful.
They trust systems when the behavior feels understandable, predictable, and transparent.
I also learned a lot about designing for operational pressure instead of ideal conditions.
Real users are busy.
They’re interrupted.
They switch contexts constantly.
They don’t have time to “figure out” complicated systems.
Designing for those realities changed how I approach product design in general.
People don’t trust systems simply because the AI is powerful.
They trust systems when the behavior feels understandable, predictable, and transparent.
I also learned a lot about designing for operational pressure instead of ideal conditions.
Real users are busy.
They’re interrupted.
They switch contexts constantly.
They don’t have time to “figure out” complicated systems.
Designing for those realities changed how I approach product design in general.
One thing that became very clear during this project is that customer conversations contain far more business intelligence than most organizations realize.
People say things in conversations that never appear in surveys, dashboards, or reports:
confusion,
frustration,
pricing concerns,
unexpected needs,
competitor comparisons.
The interesting challenge now is not collecting more data.
Most companies already have more than enough data.
The real challenge is helping humans understand it clearly enough to make better decisions from it.
That’s the direction I’m most interested in continuing to explore.
People say things in conversations that never appear in surveys, dashboards, or reports:
confusion,
frustration,
pricing concerns,
unexpected needs,
competitor comparisons.
The interesting challenge now is not collecting more data.
Most companies already have more than enough data.
The real challenge is helping humans understand it clearly enough to make better decisions from it.
That’s the direction I’m most interested in continuing to explore.