Inside Chats: How Lovable's Agents Work Together
How Lovable's agents work together through trajectories, inboxes, and activations—the Git-inspired event log and Agent Control Plane behind Chats, streaming, forking, and agents that survive deploys.
7 stories
How Lovable's agents work together through trajectories, inboxes, and activations—the Git-inspired event log and Agent Control Plane behind Chats, streaming, forking, and agents that survive deploys.
How Lovable went from no formal integrations to nearly 100 app connectors in six months, and what's next for OAuth, permissions, and app user connections.
42M monthly visitors, 400 routes and 850K lines of code moved from Next.js on Vercel to TanStack Start on Lovable—route by route, mostly by agents, with one 11-minute incident along the way.
Open almost any AI product and you will find the same dropdown in the corner. Before you can get anything done, you have a job: pick a model. Maybe decide how hard it should think too.
How per-user connections let each person use their own access, and the credential, gateway, and storage design that keeps connected data safe.
How Lovable built an internal offensive security program around verifiable results, and how we orchestrate a swarm of AI hacking agents to find real vulnerabilities instead of noise.
How a year of unrestricted token spend reshaped my development process — from plan-mode PRs to agent swarms shipping 150+ PRs a week.
Showing 7 of 7 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts