Ignite · 2026-07-20 · 36 min
A multi-turn prompt attack convinced one of the biggest providers’ voice agents to issue a $150 discount code. Tarush Agarwal is the co-founder and CEO of Cekura.ai, which builds testing and verification infrastructure for voice agents. Before founding Cekura, he studied computer science at IIT Bombay and worked on low-latency quantitative trading systems in London and Chicago, where teams optimized performance at roughly seven to nine nanoseconds. Cekura entered Y Combinator after pivoting from a legal voice-agent product, later raised a $2.5 million seed round, and now works with more than 200 customers while running millions of simulations. Voice agents can perform well in controlled tests and still fail during real conversations. Interruptions, background noise, mixed languages, transcription errors, emotional callers, and multi-turn manipulation can expose problems that never appear in a text-based evaluation. Tarush’s most counterintuitive claim is that better models do not automatically produce better voice agents. Around half of Cekura’s customers still use GPT-4.1 because newer reasoning-heavy models can introduce delays that do not work in live calls.
Ignite Startups: Passive Sensors, Drone Swarms, and the Future of Air Defense with Deo Arlo | Ep28569 / 100
Ignite Startups: How Adam Nash Built Daffy Into a $1B Donor-Advised Fund Platform | Ep28187 / 100
Ignite VC: How Jeffrey Becker Bets on Founders Before Product, Revenue, or Traction | Ep28071 / 100
Ignite VC: The Capital Markets Hack Founders Are Missing with Jonathan David Nelson | Ep27986 / 100
Ignite AI: Dennis Mortensen on Startup Failure, AI Agents, and Why Boring SaaS Problems Win | Ep27880 / 100