Tiyaro
An enterprise-focused AI-powered conversational search app
Role
As a sole Product Designer in the team, I drove the project from ideation to delivery.
Duration
3 months, May 2023 - August 2023
Summer Internship in San Jose
Deliverables
Secondary research, Competitive analysis, User flow, Ideation, High-fidelity prototype
Context
Context
Context
The goal of this project was to design a conversational search app using natural language processing to enable employees to access, search, and retrieve enterprise documents efficiently.
The goal of this project was to design a conversational search app using natural language processing to enable employees to access, search, and retrieve enterprise documents efficiently.
PROCESS
Initial Exploration and Secondary Research
Initial Exploration and Secondary Research
Initial Exploration and Secondary Research
Given the completely new interface and absence of existing users, the initial UX methods focused on exploration, understanding potential customer needs, and defining the foundational aspects of the conversational search app.
As a first step I sought to understand how people search for information at workplace and what are their pain points. Secondary research revealed some important insights suggesting that information search is one the most time consuming activities at workplace
As a first step I sought to understand how people search for information at workplace and what are their pain points. Secondary research revealed some important insights suggesting that information search is one the most time consuming activities at workplace
I also researched about design principles for conversational interfaces and new developments in gen-AI.
I also researched about design principles for conversational interfaces and new developments in gen-AI.
1.8 Hrs everyday or 9.3 Hrs every week is the time spent by employees searching and gathering information.
1.8 Hrs everyday or 9.3 Hrs every week is the time spent by employees searching and gathering information.
1.8 Hrs everyday or 9.3 Hrs every week is the time spent by employees searching and gathering information.
57% of employees stated that top contributor to lagging productivity is difficulty in finding the right information.
57% of employees stated that top contributor to lagging productivity is difficulty in finding the right information.
57% of employees stated that top contributor to lagging productivity is difficulty in finding the right information.
Stakeholder and target user interviews
Stakeholder and target user interviews
Stakeholder and target user interviews
To get a deeper insight into requirements and specific use cases, I interviewed 5 stakeholders and target users. The qualitative responses are captured in the following persona below. Some of the questions asked were -
What is the typical process for browsing enterprise data?
What challenges do they face?
What types of documents do they work with?
How do they prefer interacting with data?
What are the business requirements for the first app version?
To get a deeper insight into requirements and specific use cases, I interviewed 5 stakeholders and target users. The qualitative responses are captured in the following persona below. Some of the questions asked were -
What is the typical process for browsing enterprise data?
What challenges do they face?
What types of documents do they work with?
How do they prefer interacting with data?
What are the business requirements for the first app version?
Competitive Analysis
Competitive Analysis
To design a competitive and user-friendly product, it’s essential to benchmark against existing solutions. By analyzing current market offerings, I could identify trends, industry standards and best practices that are expected by users.
To design a competitive and user-friendly product, it’s essential to benchmark against existing solutions. By analyzing current market offerings, I could identify trends, industry standards and best practices that are expected by users.
This helped in establishing a baseline for functionality, user interface design, and performance expectations.
Key takeaways from competitive analysis
Key Considerations
Key Considerations
Key Considerations
The 8 second attention span is real
With increasing digital mediums our attention span is decreasing. A Microsoft study revealed that we now have an attention span of eight seconds–making our attention span shorter than that of a goldfish (at nine seconds). Users can get frustrated and quit using the tool if they do not get the information they are looking for quickly or within first few attempts.
With increasing digital mediums our attention span is decreasing. A Microsoft study revealed that we now have an attention span of eight seconds–making our attention span shorter than that of a goldfish (at nine seconds). Users can get frustrated and quit using the tool if they do not get the information they are looking for quickly or within first few attempts.
Users want relevant information, not more information
When users search for information, they are not looking to gather as much information as possible, they just want to see the most relevant information. Going to the next level of relevancy, users expect information personally relevant to the work they do in the organization.
When users search for information, they are not looking to gather as much information as possible, they just want to see the most relevant information. Going to the next level of relevancy, users expect information personally relevant to the work they do in the organization.
Search can behave differently depending on who the user is and where they are
Different roles (like manager, IT, software developers) with the same query may have different information needs and an enterprise search system can exploit this information. While designing for enterprise search we can utilize contextual information not only about the search query but also that of the user.
Different roles (like manager, IT, software developers) with the same query may have different information needs and an enterprise search system can exploit this information. While designing for enterprise search we can utilize contextual information not only about the search query but also that of the user.
PROBLEM STATEMENT
How can we make information finding faster and reliable with conversational search?
How can we make information finding faster and reliable with conversational search?
How can we make information finding faster and reliable with conversational search?
Deciding the scope of deliverables
Deciding the scope of deliverables
Deciding the scope of deliverables
Where do we even start? What will we need in such an app? I first got my ideas out on paper with the help of user story maps. I identified 5 tasks that were crucial for the end-to end app experience and then ideated the details of each task. These detailed steps we divided into two phases.
Phase 1: High Priority, to be taken up in first iteration
Phase 2: Low priority, to be taken up later
Where do we even start? What will we need in such an app? I first got my ideas out on paper with the help of user story maps. I identified 5 tasks that were crucial for the end-to end app experience and then ideated the details of each task. These detailed steps we divided into two phases.
Phase 1: High Priority, to be taken up in first iteration
Phase 2: Low priority, to be taken up later
User Happy Path
Lets first understand what are the various scenarios that a user might encounter.
Lets first understand what are the various scenarios that a user might encounter.
User Flow
Once I had all the feature requirements, I mapped out the user flow. It started with basic conversation flow which iteratively improved to include various features. I primarily relied on stakeholder and engineering team input to selectively include these sub-flows.
Once I had all the feature requirements, I mapped out the user flow. It started with basic conversation flow which iteratively improved to include various features. I primarily relied on stakeholder and engineering team input to selectively include these sub-flows.
High-Fidelity Mockups
High-Fidelity Mockups
High-Fidelity Mockups
Enabling natural-language queries for information search
An easy conversational interface makes it easier to find contextual information. Users can look at their previous conversations by simply scrolling up.
An easy conversational interface makes it easier to find contextual information. Users can look at their previous conversations by simply scrolling up.
An easy conversational interface makes it easier to find contextual information. Users can look at their previous conversations by simply scrolling up.
Clear visual structure for conversation threads
Visual labels make it easier to identify current and previous conversations. Each output supported by feedback and user-friendly actions for sharing, saving, and finetuning.
Visual labels make it easier to identify current and previous conversations. Each output supported by feedback and user-friendly actions for sharing, saving, and finetuning.
Visual labels make it easier to identify current and previous conversations. Each output supported by feedback and user-friendly actions for sharing, saving, and finetuning.
Asking follow up questions
User can easily ask follow-up question and seamlessly switch context between all threads and current thread.
User can easily ask follow-up question and seamlessly switch context between all threads and current thread.
User can easily ask follow-up question and seamlessly switch context between all threads and current thread.
Every answer is supported by evidence
The reference section enables users to check the source of
information directly.
The reference section enables users to check the source of
information directly.
The reference section enables users to check the source of
information directly.
Key Design Decisions
Key Design Decisions
Key Design Decisions
Presenting sources and references for answers
Presenting sources and references for answers
Presenting sources and references for answers
One of the major reported issues when interacting with conversational AI applications is the credibility of answer. Whether the answer we get is trustworthy?
One way we have tried to address this issue is by presenting the information source. This creates credibility for the information and the user has flexibility to verify the answer right there.
The reference section evolved from option 1 to option 3 with the help of various stakeholder inputs and design feedback.
One of the major reported issues when interacting with conversational AI applications is the credibility of answer. Whether the answer we get is trustworthy?
One way we have tried to address this issue is by presenting the information source. This creates credibility for the information and the user has flexibility to verify the answer right there.
The reference section evolved from option 1 to option 3 with the help of various stakeholder inputs and design feedback.
One of the major reported issues when interacting with conversational AI applications is the credibility of answer. Whether the answer we get is trustworthy?
One way we have tried to address this issue is by presenting the information source. This creates credibility for the information and the user has flexibility to verify the answer right there.
The reference section evolved from option 1 to option 3 with the help of various stakeholder inputs and design feedback.
Option 1
1. Presents all references in one list.
2. Focuses too much attention on the reference section.
3. The document type is represented by the file extension., not ideal.
1. Presents all references in one list.
2. Focuses too much attention on the reference section.
3. The document type is represented by the file extension., not ideal.
Option 2
1. Separate section for primary references and other resources.
2. Use of icons to represent the file type.
1. Separate section for primary references and other resources.
2. Use of icons to represent the file type.
Option 3
1. Reduced visual weight of references section.
2. Option to open the document in a modal, giving user the preview of information in the source document.
1. Reduced visual weight of references section.
2. Option to open the document in a modal, giving user the preview of information in the source document.
Disambiguating user questions
Users frequently ask generalist questions that are applicable for different contexts. For example, "How do you change network settings?" is applicable for Product A and Product B but the procedures are different for both. What do you do in that case?
I explored 4 variants to handle this use case. Each has its own positives and negatives. And considering it all, we decided to go ahead with the fourth one.
Users frequently ask generalist questions that are applicable for different contexts. For example, "How do you change network settings?" is applicable for Product A and Product B but the procedures are different for both. What do you do in that case?
I explored 4 variants to handle this use case. Each has its own positives and negatives. And considering it all, we decided to go ahead with the fourth one.
Users frequently ask generalist questions that are applicable for different contexts. For example, "How do you change network settings?" is applicable for Product A and Product B but the procedures are different for both. What do you do in that case?
I explored 4 variants to handle this use case. Each has its own positives and negatives. And considering it all, we decided to go ahead with the fourth one.
Option 1
Directly present a list of disambiguation options and prompt the user to select one.
Directly present a list of disambiguation options and prompt the user to select one.
Option 2
Presents answer for frequently accessed or recently used context followed by a list of clickable alternatives. This increases the likelihood of user not having to select from the options and click on one.
Presents answer for frequently accessed or recently used context followed by a list of clickable alternatives. This increases the likelihood of user not having to select from the options and click on one.
Option 3
Suggests various contexts right when the user is typing the query. However, this approach is computationally heavy and may lead to issues with latency.
Suggests various contexts right when the user is typing the query. However, this approach is computationally heavy and may lead to issues with latency.
Option 4
Presents one answer up front for the frequently accessed or recently used context followed by a list of clickable alternatives. These options have some contextual data to make selection easier for the user.
Presents one answer up front for the frequently accessed or recently used context followed by a list of clickable alternatives. These options have some contextual data to make selection easier for the user.
Takeaways
Takeaways
Takeaways
Keep stakeholders in loop
In an early stage startup like Tiyaro, things move quite quickly. Constraints change and new requirements come up that influence design decisions. Hence, it's crucial to keep everyone updated about your design changes and stay on top of new developments on business and technical fronts.
In an early stage startup like Tiyaro, things move quite quickly. Constraints change and new requirements come up that influence design decisions. Hence, it's crucial to keep everyone updated about your design changes and stay on top of new developments on business and technical fronts.
In an early stage startup like Tiyaro, things move quite quickly. Constraints change and new requirements come up that influence design decisions. Hence, it's crucial to keep everyone updated about your design changes and stay on top of new developments on business and technical fronts.
Gathering feedback in the PoC stage
Since this product was in early Proof of Concept (PoC) stage, access to actual users was limited. Even then, I made sure that in PoC meetings with customers we actively make them use the application by doing certain tasks. I took this opportunity to observe how they use it, what questions they ask, and where they get stuck. This helped me uncover some critical issues that interrupted user flow and fixing them helped the team present a robust prototype during the next meeting.
Since this product was in early Proof of Concept (PoC) stage, access to actual users was limited. Even then, I made sure that in PoC meetings with customers we actively make them use the application by doing certain tasks. I took this opportunity to observe how they use it, what questions they ask, and where they get stuck. This helped me uncover some critical issues that interrupted user flow and fixing them helped the team present a robust prototype during the next meeting.
Since this product was in early Proof of Concept (PoC) stage, access to actual users was limited. Even then, I made sure that in PoC meetings with customers we actively make them use the application by doing certain tasks. I took this opportunity to observe how they use it, what questions they ask, and where they get stuck. This helped me uncover some critical issues that interrupted user flow and fixing them helped the team present a robust prototype during the next meeting.