What breaks in voice AI at scale, production patterns, real numbers

​'Gradient Descending' is a series of roundtables on AI: curated deep dives with technical builders. Past roundtables discussions covered RL Environments, Evals, Fine-Tuning, Agent Frameworks, Open Source Models, and Knowledge Graphs with companies like OpenAI, Anthropic, Cursor, Scale AI and many more.

​For our first Barcelona session this autumn, we’re joined by Sergio Espeja, co-founder of HeyDiga, and Ismael Ordaz, co-founder of SLNG, for an honest discussion about what happens when voice AI moves beyond the demo and into real production environments.

​We’ll talk about what starts to break as usage grows, which production patterns actually hold up and how teams think about latency, reliability, orchestration, monitoring and unit economics. Most importantly, we’ll look at the gap between an impressive demo and a voice product people can genuinely depend on every day.

​Agenda:

• ​Arrivals: 17:30–18:30

• ​Roundtable discussion: 18:30–19:30

• ​Drinks at the rooftop: 19:30–21:30

​See past roundtables here:

​https://www.akashbajwa.co/t/ai-roundtables

​I agree that photographs and/or video may be taken during the event and used by the hosts on social media and in future promotional materials.