I'm Vasavi. I've spent the last few years on the founder side of the table, talking to users, shaping products from 0→1, making product decisions, building businesses, and figuring things out when there wasn't a playbook.
Some things worked. Some didn't. All of them taught me something.
This is where I keep the products, decisions, experiments, and lessons that came out of it.
This is how I think, build, and learn.
An AI product exploring how marketing teams can create and manage multi-channel content from a single source of truth.
Product strategy work for an emerging mobility platform, spanning customer journeys, competitive research, pricing, and go-to-market.
Building and scaling a business from the ground up
Explored how different deep learning architectures perform when classifying malware at scale. I benchmarked CNN, RNN, and other architectures across a 200GB dataset, achieving 95%+ accuracy and learning how representation and data quality affect model performance.
Built a computer-vision attendance system to replace manual classroom attendance, using OpenCV and Django to detect and record students in real time.
An ongoing experiment into how prompt structure changes the quality, consistency, and failure modes of LLM outputs. I test different prompting strategies and evaluate where small changes in instructions meaningfully change outcomes.