
SIID Technologies
An AI-empowered evidence tool that introduced me to machine-learning in AWS and setting realistic expectations with founders.
Context
SIID Technologies leveraged the power of AWS to transcribe audio & video files and produce insights to aid in the legal evidence discovery process. Historically, this is a very lengthy, diligent, and manual process for legal aides.
As my first project as the Development Lead at Platform, all aspects of the SIID product timeline, feature prioritization, and build were my responsibility. The level of fidelity that we achieved in an 8-week development window was impressive, but that was not without its obstacles.
The original mockups were very high fidelity. To aid collaboration within law offices, I wanted all of the necessary information visible at one time. Given that case files are often quite large, I realized quickly that it was not in the users' best interests. Thus, we opted for a tab-based right-hand column and increased emphasis on the descriptive iconography.
Warning: Strong Language


Basic Features Overview
The biggest mistake made during this build was weak expectation-setting. We created a beautiful wireframe prototype in Figma and did not communicate proper expectations to the founder regarding feasibility. Since Platform used experimental development frameworks such as Bubble.io, and this was my first time experimenting with AWS, we could not validate all of the designs right away. In the end, the product resembled the prototype pixel for pixel; however we did not create the machine-learning pipeline that the founder had expected at launch.
With the understanding that our smart analysis would be simplified for launch, I focused on organizing data and improving the speed and collaborative power of the tool. We wanted this to be the best budget evidence discovery option on the market. However, there are many ways to skin a cat. I found myself frequently saying "just because we can do this does not mean we should". One of our experiments was generating a wordcloud for users based on commonly repeated words or phrases in the inputted video footage.
Furthermore, we designed the collaboration settings to mimic Google Drive file sharing, comments, edit history and tagging.



Digging Deep on Transcript Edit History
Originally, our transcript editing was tracked via manual project notes—a temporary fix for a tight launch window. Post-launch, I overhauled this into a robust version history system. By leveraging an open-source API from Google search history, I moved beyond simple 'change notifications' to a comprehensive audit trail. This allowed users to view a comprehensive history of edits, navigate instantly to modified sections, and manage versioning directly within the transcript blocks, significantly improving a legal team's collaboration and transparency.




Results & Impact
As one of the most advanced MVPs of my career, the mistakes I made during the development process were critical to my growth and success with subsequent builds. I learned to prioritize my relationship with the founder and to properly set expectations. As a young developer, I tried to bite off more than I could chew, but I am a better product leader as a result.
200+ businesses using the platform.
Average 30% increase in decision-making speed.
99.9% uptime over 12 months.
Named "Best Analytics Tool" by E-Commerce Weekly.