AI systems · product engineering · field deployment
I'm Vrishn Viswa — a computer science student, AI builder, and operator working between Penn State and IIT Madras.
Building where AI capability meets real human use.
STATE COLLEGE · SHARJAH · CHENNAI01 / EXPERIENCE LOG
I like the messy middle: taking capable technology out of the demo, understanding the human system around it, and shipping the thing that sticks.
Perplexity AI
Deploying Perplexity Computer with local businesses: finding operational bottlenecks, connecting tools and data, automating recurring work, and training owners to run the workflows independently.
Program detailsPerplexity AI
Led demos, workshops, and campus outreach for 500+ Penn State students, translating Perplexity into practical coursework, coding, and research workflows with 20%+ attendee activation.
KreupAI Technologies LLC
Built on DaftarAI, an LLM copilot for accounting workflows—tracing request flow across the codebase and improving prompts, tool execution, integration reliability, and failure handling.
Independent E-commerce Venture
Built an independent operation past $30K in revenue while managing sourcing, supplier relationships, pricing, fulfillment, and 35%+ profit margins.
02 / SELECTED WORK
Four systems from the current résumé: agent authorization, editor-native AI, weather intelligence, and inspectable model routing.
Runtime authorization for AI agents
A protocol for scoped user mandates, bound tokens, service metadata, and signed execution receipts—designed against impersonation, replay, excessive permissions, spoofing, and payment escalation.
Better prompts and voice inside the editor
Published extensions for structured prompt rewriting and Whisper-powered speech-to-text across VS Code and Cursor. Verified marketplace activity: 1,258 Prompt Enhancer downloads, 1,093 Speech downloads on Open VSX, and 1,496 Speech installs on VS Marketplace.
Extreme-weather early warning
A multi-model AI dashboard that turns live weather signals into severity-ranked, source-linked alerts across Pennsylvania cities.
Making mixture-of-experts routing inspectable
An inspectable MoE routing pipeline with invariant validation and deterministic expert histograms, including a real OLMoE routing event and an open systems journal.
03 / OPERATING EVIDENCE
Computer Science at Penn State and Data Science at IIT Madras.
Built through independent e-commerce, supplier strategy, fulfillment, and margin discipline.
Verified downloads and installs across the three extension listings linked above.
AI demos, workshops, and activations across the Penn State community.