Jan 2025 - Jan 2025
Jan 2025 - Jan 2025
Iago
Chats
Iago
Chats
Iago
Chats
Company: Iago
Project Type: Native iOS mobile app redesign to improve usability
Company: Iago
Project Type: Native iOS mobile app redesign to improve usability
Iago is a mobile app that teaches Japanese through immersion by having learners navigate a visual novel game and speaking from day one. In each situation, learners participate in prompt-guided chats that increase in difficulty, eventually forming a full conversation at the end.
Iago is a mobile app that teaches Japanese through immersion by having learners navigate a visual novel game and speaking from day one. In each situation, learners participate in prompt-guided chats that increase in difficulty, eventually forming a full conversation at the end.
Iago is a mobile app that teaches Japanese through immersion by having learners navigate a visual novel game and speaking from day one. In each situation, learners participate in prompt-guided chats that increase in difficulty, eventually forming a full conversation at the end.
Goal
Goal
Iago Chat is an immersive way to allow users to practice the concepts they’ve learned through AI-powered guided chats. However, users find the conversations difficult to complete, leading to app drop-off.
Iago Chat is an immersive way to allow users to practice the concepts they’ve learned through AI-powered guided chats. However, users find the conversations difficult to complete, leading to app drop-off.
Solution
Solution
Add display mode settings to accommodate beginner learners
Allow users to edit their last response through typing and auto submit ticket to
Move hints in-line with the chat
Add display mode settings to accommodate beginner learners
Allow users to edit their last response through typing and auto submit ticket to
Move hints in-line with the chat
01
Problem Discovery
01
Problem Discovery
01
Problem Discovery
About 4 months prior, the app pivoted from an “open-world” format to one that was more structured like a visual novel. During that time, the Stories (lessons) and Practices were redesigned to align to the changed format, but the Conversation remained untouched.
The Iago team wanted to ensure that the app captures the entire learning cycle (Kolb’s Learning Cycle), so we agreed that the next step was to improve the Chat / Conversation experience , which provides "life-like" experiences (Concrete Experience) to learners.
About 4 months prior, the app pivoted from an “open-world” format to one that was more structured like a visual novel. During that time, the Stories (lessons) and Practices were redesigned to align to the changed format, but the Conversation remained untouched.
The Iago team wanted to ensure that the app captures the entire learning cycle (Kolb’s Learning Cycle), so we agreed that the next step was to improve the Chat / Conversation experience , which provides "life-like" experiences (Concrete Experience) to learners.
Note: Currently, there is no visual difference between Chats and Conversations. The only differences are in difficulty; chats increase in difficulty / length over levels 1-4, while the conversation is the hardest and longest. Conversations are mandatory and acts as an overall situation evaluation, while Chats are optional.
Note: Currently, there is no visual difference between Chats and Conversations. The only differences are in difficulty; chats increase in difficulty / length over levels 1-4, while the conversation is the hardest and longest. Conversations are mandatory and acts as an overall situation evaluation, while Chats are optional.
Note: Currently, there is no visual difference between Chats and Conversations. The only differences are in difficulty; chats increase in difficulty / length over levels 1-4, while the conversation is the hardest and longest. Conversations are mandatory and acts as an overall situation evaluation, while Chats are optional.
This made me wonder: If we encourage learners to complete more Chats, would they be likelier to become committed learners? In other words:
This made me wonder: If we encourage learners to complete more Chats, would they be likelier to become committed learners? In other words:
“
How might we allow users to complete chats more easily (without adjusting content difficulty) so that they feel motivated to keep studying?
“
How might we allow users to complete chats more easily (without adjusting content difficulty) so that they feel motivated to keep studying?
This made me wonder: If we encourage learners to complete more Chats, would they be likelier to become committed learners? In other words:
“
How might we allow users to complete chats more easily (without adjusting content difficulty) so that they feel motivated to keep studying?
02
Research
02
Research
02
Research
I conducted competitive research through heuristic analysis to understand industry standards and design patterns in voice recording, chat interfaces, and audio transcription to identify whether there are any gaps in the current Chat experience or feature offerings.
This analysis helped me acknowledge that we'd potentially need more features that gives users more guidance in what to say and greater control of the chat since audio input is quite finicky.
I conducted competitive research through heuristic analysis to understand industry standards and design patterns in voice recording, chat interfaces, and audio transcription to identify whether there are any gaps in the current Chat experience or feature offerings.
This analysis helped me acknowledge that we'd potentially need more features that gives users more guidance in what to say and greater control of the chat since audio input is quite finicky.
Next was internal research, which was mainly conducted by sifting through the bug reports and collecting comments on Iago’s social media channels. The majority of comments touched upon these three issues:
Next was internal research, which was mainly conducted by sifting through the bug reports and collecting comments on Iago’s social media channels. The majority of comments touched upon these three issues:
03
Ideate
03
Ideate
03
Ideate
After conducting competitive research, I conducted a small brainstorming session with the frontend engineers and community manager to generate solutions to improve the Chat experience using the user stories I created beforehand to ensure that these potential solutions are aligned to our specific users.
Below are some ideas we came up with. And after sifting through everyone's ideas, 3 themes emerged. So, I decided to choose one solution from each theme in order to cover the gaps in the current Chat experience.
After conducting competitive research, I conducted a small brainstorming session with the frontend engineers and community manager to generate solutions to improve the Chat experience using the user stories I created beforehand to ensure that these potential solutions are aligned to our specific users.
Below are some ideas we came up with. And after sifting through everyone's ideas, 3 themes emerged. So, I decided to choose one solution from each theme in order to cover the gaps in the current Chat experience.
01
Edit Response
Changed recording behavior from hold to record to tap to start/stop recording, confirm message to send.
WHY: Learners can confirm that their responses were accurately recorded or attempt again. Unintended responses will not be sent and run the chat off-course by the AI.
01
Edit Response
Changed recording behavior from hold to record to tap to start/stop recording, confirm message to send.
WHY: Learners can confirm that their responses were accurately recorded or attempt again. Unintended responses will not be sent and run the chat off-course by the AI.
01
Edit Response
Changed recording behavior from hold to record to tap to start/stop recording, confirm message to send.
WHY: Learners can confirm that their responses were accurately recorded or attempt again. Unintended responses will not be sent and run the chat off-course by the AI.
02
Switch Display Mode
Added ability to change display mode (Japanese Writing System) for specific messages.
WHY: Allows the user to challenge themselves with Kanji + Kana if they want or easily revert back.
02
Switch Display Mode
Added ability to change display mode (Japanese Writing System) for specific messages.
WHY: Allows the user to challenge themselves with Kanji + Kana if they want or easily revert back.
02
Switch Display Mode
Added ability to change display mode (Japanese Writing System) for specific messages.
WHY: Allows the user to challenge themselves with Kanji + Kana if they want or easily revert back.
03
In-Line Hinting
Added ability to change display mode (Japanese Writing System) for each chat message.
WHY: Allows the user to challenge themselves with Kanji + Kana if they want or easily revert back.
03
In-Line Hinting
Added ability to change display mode (Japanese Writing System) for each chat message.
WHY: Allows the user to challenge themselves with Kanji + Kana if they want or easily revert back.
03
In-Line Hinting
Added ability to change display mode (Japanese Writing System) for each chat message.
WHY: Allows the user to challenge themselves with Kanji + Kana if they want or easily revert back.
04
Reiterate
04
Reiterate
04
Reiterate
After a discussion with the co-CEO/frontend engineer, he decided to reduce the project size to two weeks due to limited engineering resources. By bumping up the timeline, we had to ruthlessly prioritize solutions that required the least amount of changes that resulted in short term wins.
After a discussion with the co-CEO/frontend engineer, he decided to reduce the project size to two weeks due to limited engineering resources. By bumping up the timeline, we had to ruthlessly prioritize solutions that required the least amount of changes that resulted in short term wins.
01 V2
Edit Typed Response
Allow users to manually override their recorded responses by submitting typed responses. A ticket is also automatically submitted.
WHY: Circumvent voice recognition limitations while still giving users the opportunity to learn.
Before
After
01 V2
Edit Typed Response
Allow users to manually override their recorded responses by submitting typed responses. A ticket is also automatically submitted.
WHY: Circumvent voice recognition limitations while still giving users the opportunity to learn.
Before
After
02 V2
Change Display Mode
Change overall display mode of chat instead of individual messages.
WHY: Reuse designs from account settings and reduce engineering lift.
Before
After
02 V2
Change Display Mode
Change overall display mode of chat instead of individual messages.
WHY: Reuse designs from account settings and reduce engineering lift.
Before
After
02 V2
Change Display Mode
Change overall display mode of chat instead of individual messages.
WHY: Reuse designs from account settings and reduce engineering lift.
Before
After
03 V2
Manual In-line Hints
Content team manually sifted through difficult prompts to adjust wording and add true hints.
WHY: Avoid huge changes to entire page layout. Stopgap solution due to AI limitations to give true hints.
Before
After
03 V2
Manual In-line Hints
Content team manually sifted through difficult prompts to adjust wording and add true hints.
WHY: Avoid huge changes to entire page layout. Stopgap solution due to AI limitations to give true hints.
Before
After
03 V2
Manual In-line Hints
Content team manually sifted through difficult prompts to adjust wording and add true hints.
WHY: Avoid huge changes to entire page layout. Stopgap solution due to AI limitations to give true hints.
Before
After
01 V2
Edit Typed Response
Allow users to manually override their recorded responses by submitting typed responses. A ticket is also automatically submitted.
WHY: Circumvent voice recognition limitations while still giving users the opportunity to learn.
Before
After
01 V2
Edit Typed Response
Allow users to manually override their recorded responses by submitting typed responses. A ticket is also automatically submitted.
WHY: Circumvent voice recognition limitations while still giving users the opportunity to learn.
Before
After
05
Results
05
Results
05
Results
After two weeks, we've noticed a 24% increase in chat use across the board. We've also noticed that average session length increased (from ~15 minutes to ~18 minutes) while average completion days of a situation remained at 5 days for chat users. In other words, users are spending more time studying.
After two weeks, we've noticed a 24% increase in chat use across the board. We've also noticed that average session length increased (from ~15 minutes to ~18 minutes) while average completion days of a situation remained at 5 days for chat users. In other words, users are spending more time studying.
An increase in Chat use, an increase in overall studying
An increase in Chat use, an increase in overall studying
An increase in Chat use, an increase in overall studying
+24%
+24%
chat use
chat use
+25%
+25%
daily study time
daily study time
Takeaways
Takeaways
01
Loop engineers in sooner
Due to AI voice recognition limitations, we needed front-end workarounds. Discussion happened late in the process, which led to infeasible designs. I could have prevented this if I had presented mid-fi designs earlier in the process with engineering.
Due to AI voice recognition limitations, we needed front-end workarounds. Discussion happened late in the process, which led to infeasible designs. I could have prevented this if I had presented mid-fi designs earlier in the process with engineering.
02
More guidance != better
As designers, we aim to prevent user mistakes, but in learning, too much leniency can backfire. The AI chat’s flexibility frustrated users, preventing them from improving. I lost sight of our users’ needs.
As designers, we aim to prevent user mistakes, but in learning, too much leniency can backfire. The AI chat’s flexibility frustrated users, preventing them from improving. I lost sight of our users’ needs.
Next Steps…
Next Steps…
Monitor user reports
Track chat report trends. Conduct usability testing if needed
Rework Hinting
Redesign in-line hinting to accommodate AI improvements for personalized hints
Summarization Screen
Design a summary page that surfaces after the user completes Chats / Conversations for them to reflect