← Back to the wire

JioStar’s chief architect on AI discovery at 500M-user scale

AnnouncementProductNov 12, 2026

JioStar used the OpenAI API to build a conversational video and cricket-statistics discovery assistant into JioHotstar, launched in about eight weeks across more than 15 languages. In an interview with Chief Architect Vijay Seshadri, JioStar—whose platforms serve over 500 million consumers—describes balancing accuracy, latency, and cost, with over 60% of users choosing voice. The team relied on evaluation frameworks, domain experts, and a model-as-judge validation layer; Codex helped accelerate generating eval cases.

Receipt № 28451 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01high
openai.comOfficialhttps://openai.com/index/jiostar-vijay-seshadri/This OpenAI-published interview with JioStar's Chief Architect details the company's evaluation methodology—domain-expert seeding, a maker-checker validation pattern, and an LLM judge—behind its voice-visual discovery assistant.
PRIMARY
OpenAICompanyCodexModelJioStarCompanyVijay SeshadriPerson
Canonical: https://openai.com/index/jiostar-vijay-seshadri/