Supabase will das Backend für eine Milliarde KI-erstellter Apps rüsten
KI-Agents erstellen immer mehr Software, was die Anforderungen an Backends verändert. Supabase-Gründer Paul Copplestone und Ant Wilson sprechen über langlebige Workloads neben der Datenbank und Schemata, die für Agents leichter verständlich sind.
AI agents are creating more software—and that changes what a backend needs to do. Supabase co-founders Paul Copplestone and Ant Wilson join swyx to discuss running long-lived workloads alongside the database, making schemas easier for agents to understand, and designing infrastructure for a world with many more applications.
The conversation also covers Postgres reliability and scaling, Turso, open source, community-led distribution, and how Supabase uses AI internally. Recorded ahead of Supabase Select 2026.
Supabase Compute — run workloads alongside the database.
Multigres — highly available Postgres infrastructure, in private alpha.
Supabase acquires Turso — the scale-out opportunity.
Supabase Select — the event discussed in the interview.
Latent Space is read by the people shipping agents, models and infrastructure. Enquire about sponsoring this slot.
00:00 Six years in the making 00:51 Supabase Compute 02:01 OrioleDB and the Postgres storage engine 03:27 Multigres and Postgres reliability 07:06 Scaling out and Turso 23:10 From prototype to petabyte 25:10 AI and Supabase’s growth 27:40 Agent-driven activation 30:00 Community and crowdfunding 36:00 Open source and enterprise sales 40:50 Will the application builder or database be stickier? 48:10 Durable workflows 50:52 Company priorities 53:24 Code-first infrastructure and declarative schemas 56:30 Will AI-generated software converge? 1:06:01 How Supabase teams use AI 1:09:45 Hiring for a remote-first company