⚡ TL;DR Subagents start fresh, investigate a focused question and report back; only the main agent edits files. Lovable decides when to use them, on every plan, and their work uses model credits.
Big projects need research. Subagents do it while the main agent builds.
🕵️ What They Are
Temporary read-only helpers. Generic subagents return comparisons, checklists or recommendations; Explore gives traceable evidence using the most capable model.
⚙️ How They Run
They only get the briefing Lovable writes, can run in parallel and do not coordinate. The activity card shows files read, searches and findings.
🎯 When They Help
Good cases:
- ✅ Exploring an unfamiliar project
- ✅ Researching before building
- ✅ Investigating performance
- ✅ Planning large changes
💳 Cost
They use model credits; in Plan mode, messages with subagents cost more than one credit.
💡 Pro tip Mention subagents explicitly when you want a deep investigation.
Want an architecture audit? Lord of the Wix can help. ✨
❓ Lovable subagents FAQ
Can subagents edit files?
No, they are read-only.
Do I configure them?
No.
Are they on every plan?
Yes.
Do they cost credits?
Yes, as model usage.
What is Explore?
A subagent for evidence-backed answers.
🙏 Credit: Based on public information from the Lovable documentation. Lovable is a product of Lovable. Source: docs.lovable.dev. Lord of the Wix is an independent agency and is not affiliated with Lovable.