OPEN TO FOUNDER & VC CONVERSATIONS
I build AI agents that hold up in production.
I'm Pavan Ghantasala, a forward deployed engineer and AI product leader in Dallas. I've shipped agents that served 120,000 festival fans in a single weekend, unlocked ~$195M in annual business value, and powered AI used by 200,000+ enterprise employees. I've also been the CTO in the room when an AI product had to go from demo to something customers depend on.
hi@pavanghantasala.com LinkedIn
3× O-1A EXTRAORDINARY ABILITY VISA RECIPIENT
2× U.S. PATENT HOLDER · AI & CYBERSECURITY
In production, at scale
Client names are shared only where the work is already public.
An agentic festival guide embedded in the BottleRock app that handled ~37,000 live AI interactions over one event weekend, at real-world scale and latency. Spotlighted by Salesforce's CEO, featured in a CMO keynote at Salesforce Connections, and now the blueprint for AI-first live events across Live Nation festivals.
A unified email agent spanning 6 global brands that reads live customer emails, reasons over intent, and replies directly into inboxes, plus web, SMS, and voice agents across 7 brand channels in two languages. Now the team's flagship production reference.
A concierge-grade shopping agent for a heritage luxury house, tuned to 95%+ response accuracy with latency cut ~3×, where brand voice, precision, and trust in every answer are non-negotiable.
Shaping the future of agentic commerce for one of the world's largest apparel companies. Took a shopper agent to a validated 95% pass rate and re-architected its orchestration to cut response times nearly in half, carrying shoppers from discovery to purchase inside the storefronts they already use.
A guest-facing agent handling questions and dining workflows, designed for high-volume, time-sensitive interactions.
The path here
The company's first Senior Expert Agent Builder hired globally, an embedded innovator-builder shipping bespoke agents inside strategic customers' environments across media, luxury retail, apparel, and hospitality. Built the Agent Growth Loop, an open-sourced self-improving agent framework that unlocked ~$195M in annual business value, and an innovation model adopted across the global FDE community.
Co-founded and owned product, engineering, and AI from 0 to 1, architecting the full stack across backend, mobile, and admin. Shipped vision-based food scanning, cut scan latency ~4×, and rolled out institutional access to 5,000 university users, with the platform deployed at Ivy League medical schools.
Led GenAI and agentic AI in the AI/ML Center of Excellence. Architected an agentic RAG employee assistant serving 200,000+ employees, shipped an agentic workflow that delivered ~$5M in incremental revenue, and led anomaly-detection programs that saved $16M+ and produced two awarded patents, all while managing a team of 7 in one of the most regulated environments in the world.
MS from Purdue University (Dean's List, Beta Gamma Sigma), MBA from IIT Madras, B.Tech from Andhra University. Founding Chair of ACM SIGKDD Dallas and startup advisor at the DEC Network.
Talks, writing & the newsletter
What I'm reading each week at the frontier of agents and applied AI, curated for technical founders and CTOs building with it. Recent issues covered HBR's "Beware the AI Experimentation Trap" and LangChain's work on deep agents. Subscribe on LinkedIn.
"Is Machine Learning Still Relevant in the World of Generative AI?", on why foundational ML remains essential to robust, interpretable generative systems.
Predictive customer lifetime value modeling for player retention in mobile gaming, using BG/NBD models.
Sales forecasting with high-performance computing, achieving a 90% reduction in mean absolute error across a 6,500-store network. Published in the Midwest DSI Conference Proceedings.
Demos are easy. Durability is the job.
Most agent projects die between the impressive demo and the second month of real traffic. My work lives in that gap.
Extreme listening first
Before a line of code, I sit inside the client's actual workflows, vocabulary, and edge cases. The best architecture decisions come from cross-domain pattern recognition, what luxury retail can teach hospitality, and what festivals can teach banking.
Eval-driven from day one
Every agent ships with an evaluation harness, observability, and a definition of good that the business signed off on. If you can't measure the agent, you can't trust it, and you definitely can't scale it.
Built for the second year
Production agents outlive their launch team. I design for handoff: taxonomies, guardrails, and growth loops that let the client's own people extend the system without calling me back for every change.
Building an agent product? Backing one?
I talk regularly with startup founders who need their agents to survive contact with real users, and with venture partners doing technical diligence on agentic products. If that's you, my inbox is open, and I respond fast.
Email hi@pavanghantasala.com LinkedIn in/pavanghantasala Newsletter Curiosity Curated Calendar Book 30 minutes