Product design and strategy at Kodex
A B2B SaaS platform that helps companies transform their scattered team knowledge into a fully searchable, AI-summarized, and transcribed video repository.
Making organizational knowledge easy
to capture, find, and reuse
As organizations grow, so does the knowledge their teams create. Yet much of that stays confined to a few team members, ends up deep in Slack threads, or in some shared Google Doc.
To address this, I led the end-to-end design and development of Kodex. Starting with qualitative user research, I worked closely with cross-functional teams to build an enterprise platform that provides institutional knowledge with a permanent, searchable home.
Client
Zein Zoulfikar (Financial Sponsors Group J.P. Morgan)
Industry
AI knowledge Platform, SAAS Product
Timeline
September 2024- January 2026
My Role
Lead Developer and Designer
Accessing team expertise felt slow and fragmented
Research showed that employees weren't struggling because information didn't exist; they struggled because it was scattered.
Finding information often meant messaging coworkers, searching multiple tools, or rewatching long recordings for a single detail. The larger the company became, the more time people spent looking for knowledge instead of using it.
01 text-heavy documentation; 02 Long, un-transcribed videos; 03 team resources fragmented across Slack chats and email.
Looking beyond the qualitative data
To better understand how teams manage and share knowledge, I conducted 10 in-depth interviews with professionals across product, engineering, design, and operations. Rather than asking about documentation alone, I focused on how people found information, shared context, and collaborated throughout their daily work.
As I mapped the interviews, it became clear that the issue wasn't a lack of knowledge, it was a lack of accessibility. Four consistent patterns emerged across participants, and these insights became the foundation for every major design decision that followed.
Synthesis of 10 user interviews mapping structural inefficiencies in daily knowledge consumption.
Kodex vs Options already in market
The following five capabilities were chosen because each one maps to a real pain point from the research, and not because they made Kodex look good in isolation:
User Personas
Two personas synthesized from the interviews above
Designing a closed-loop knowledge ecosystem
The research made one thing clear: capturing knowledge and finding it couldn't be treated as separate problems. I began by sketching the complete experience to understand how information would move through the system, from recording a meeting to becoming something anyone could search and learn from.
These early concepts helped shape the core structure of Kodex and guided later interface decisions around uploading, AI summaries, transcripts, and search.
From insights to interface
Capture Knowledge Instantly
Most participants shared that they prefer video recording over writing and updating long documentation. Hence in Kodex, we made video recording the easiest way to share knowledge.
Turn Conversations into searchable transcripts
Documentation quickly becomes outdated and requires ongoing effort to keep accurate. Kodex reduces this effort by automatically generating transcripts and summaries from recorded knowledge.
AI Summaries that drive clarity & Action
Summaries highlight what matters so teams can quickly understand key decisions and next steps.
Organizing knowledge across teams
Knowledge is automatically organized by teams and departments, helping employees quickly find relevant information while maintaining clear ownership and access.
Structure Knowledge with Categories & Tags
Instead of recordings getting buried in different tools, custom categories and tags keep knowledge organized so teams can find it instantly.
Product design and strategy at Kodex
A B2B SaaS platform that helps companies transform their scattered team knowledge into a fully searchable, AI-summarized, and transcribed video repository.
Making organizational knowledge easy
to capture, find, and reuse
As organizations grow, so does the knowledge their teams create. Yet much of that stays confined to a few team members, ends up deep in Slack threads, or in some shared Google Doc.
To address this, I led the end-to-end design and development of Kodex. Starting with qualitative user research, I worked closely with cross-functional teams to build an enterprise platform that provides institutional knowledge with a permanent, searchable home.
Industry
AI knowledge Platform, SAAS Product
Timeline
September 2024- January 2026
My Role
Lead Developer and Designer
Accessing team expertise felt slow and fragmented
Research showed that employees weren't struggling because information didn't exist; they struggled because it was scattered.
Finding information often meant messaging coworkers, searching multiple tools, or rewatching long recordings for a single detail. The larger the company became, the more time people spent looking for knowledge instead of using it.
01 text-heavy documentation; 02 Long, un-transcribed videos; 03 team resources fragmented across Slack chats and email.
Synthesis of 10 user interviews, mapping out structural inefficiencies in daily knowledge consumption.
Looking beyond the qualitative data
To better understand how teams manage and share knowledge, I conducted 10 in-depth interviews with professionals across product, engineering, design, and operations. Rather than asking about documentation alone, I focused on how people found information, shared context, and collaborated throughout their daily work.
As I mapped the interviews, it became clear that the issue wasn't a lack of knowledge, it was a lack of accessibility. Four consistent patterns emerged across participants, and these insights became the foundation for every major design decision that followed.
Kodex vs Options already in market
The following five capabilities were chosen because each one maps to a real pain point from the research, and not because they made Kodex look good in isolation:
User Personas
Two personas synthesized from the interviews above
Designing a closed-loop knowledge ecosystem
The research made one thing clear: capturing knowledge and finding it couldn't be treated as separate problems. I began by sketching the complete experience to understand how information would move through the system, from recording a meeting to becoming something anyone could search and learn from.
These early concepts helped shape the core structure of Kodex and guided later interface decisions around uploading, AI summaries, transcripts, and search.
Capture Knowledge Instantly
Most participants shared that they prefer video recording over writing and updating long documentation. Hence in Kodex, we made video recording the easiest way to share knowledge.
Turn Conversations into searchable transcripts
Documentation quickly becomes outdated and requires ongoing effort to keep accurate. Kodex reduces this effort by automatically generating transcripts and summaries from recorded knowledge.
AI Summaries that drive clarity & Action
Summaries highlight what matters so teams can quickly understand key decisions and next steps.
Organizing knowledge across teams
Knowledge is automatically organized by teams and departments, helping employees quickly find relevant information while maintaining clear ownership and access.
Structure Knowledge with Categories & Tags
Instead of recordings getting buried in different tools, custom categories and tags keep knowledge organized so teams can find it instantly.
