Lovable supports referencing app connectors via @ in chat messages
TL;DR
Lovable now allows typing @ in the chat input to reference app connectors directly. A picker displays popular connectors and filters results as users type.
What changed
Lovable added support for typing "@" directly in the chat input so Vibe Builders, Basic Users, and Developers can reference an app connector while describing a build. A picker surfaces popular connectors and filters matches as text is entered.
Why it matters
This change helps Developers move faster when wiring services into new apps because they stay inside one chat flow instead of switching panels. Basic Users and Vibe Builders gain the same direct access when they describe needs involving connectors such as databases during a single session.
What to watch for
Compare the flow against Cursor chat behavior to see how each handles connector mentions. Verify the update by opening a new Lovable chat, typing "@" and confirming the picker appears with live filtering.
Who this matters for
- Vibe Builders: Type @ in Lovable chat to instantly link databases and APIs without leaving your design flow.
- Basic Users: Use the @ shortcut in chat to connect external tools to your app by selecting from the menu.
Harsh’s take
Lovable bringing the @-mention pattern to app connectors is a smart UX consolidation. It mimics the developer-native experience found in Cursor or Slack, reducing the friction of connecting external databases and APIs. Instead of hunting through sidebar menus, builders can now declare integrations inline as they describe their application logic.
This update shows that low-code platforms are maturing past rigid drag-and-drop interfaces. By centering the entire creation workflow inside a single chat input, Lovable keeps builders in flow state. Teams should test this inline referencing to see if it speeds up initial prototyping cycles compared to manual API configuration.
by Harsh Desai
About Lovable
View the full Lovable page →All Lovable updatesGo deeper
More AI news
- Daily RoundupGemini 3.5 Transcribe and Muse Image on AI Gateway, Qwen 3.8 Flash, and agent deployment tools
New transcription and image models landed on Vercel AI Gateway alongside Qwen variants and infrastructure for running coding agents at scale.
- Daily RoundupVercel Connect GA and Run SDK, Wan 3.0 on AI Gateway, and agent tools for production
Vercel expanded agent connectors and security tools while new video models and debugging platforms rolled out, giving builders more ways to ship reliable agents without managing credentials or long timeouts.
- Daily RoundupAudio8 TTS and Wan 3 video model launch, plus agent efficiency benchmarks (sandbox tools to test today)
Hugging Face and Replicate added new text-to-speech, video, and image models while NVIDIA and Vercel released efficiency and sandbox updates that affect how agents run in production.