JioStar’s chief architect on AI discovery at 500M-user scale
What happened
Vijay Seshadri, chief architect at JioStar, discussed how the company built a conversational video and cricket‑stat discovery assistant for its JioHotstar platform using the OpenAI API. The system lets users speak naturally in over 15 languages to find movies, shows, highlights, live‑match moments or detailed cricket statistics, returning results in a visual, conversational format. Development began in October‑November and was launched in about eight weeks for a major cricket tournament, handling both entertainment and sports audiences. Design decisions balanced accuracy, latency and cost, especially for voice interactions at a scale of over 500 million users and up to 72.5 million concurrent viewers.
Why it matters
For everyday viewers, the new voice‑visual interface makes finding personalized content faster and more natural, especially during live sports events. It also shows how large‑scale services can quickly turn AI experiments into production features.
Reality check
An automated, sceptical read of the sourceIncremental. The article describes applying existing conversational AI technology to a specific, large‑scale content discovery use case rather than introducing fundamentally new AI methods.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from OpenAI
Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026OpenAI launches ChatGPT Wallet, AI agents pay for purchaseOpenAI · 13 Nov 2026OpenAI disbands its robotics team as its general models start running robotsOpenAI · 13 Nov 2026Yang-Mills, OpenAI proof, and the mass gap problemOpenAI · 13 Nov 2026This page was collected from openai.com and summarised automatically by AIPulsee's pipeline. See how it runs.