AI Launch Profile
Replit Agent 3 adds browser self-testing, longer autonomous runs, and agent generation
Replit launched Agent 3 with app testing in a real browser, autonomous work up to 200 minutes, and the ability to build agents and automations.
Launch Context
Use these links to move from this record into the broader Launch Intelligence database.
Verification & Sources
- Status
- Verified
- Source links
- 2
- Freshness
- Verified June 8, 2026
- Last verified
- June 8, 2026
- Last updated
- June 8, 2026
Key source checks
Suggest a correction
Kingy Scores
- Launch Score
- 10.0 / 10
- Demo Quality
- 10.0 / 10
- YouTube Potential
- High
Creator Coverage Next Steps
This launch has signals that may support demos, reviews, creator education, founder storytelling, or practical product explainers.
Kingy AI Take
This was a meaningful autonomy jump because Replit paired generation with real browser self-testing and longer run time.
Who it is for
Builders who want Replit Agent to move beyond code generation into testing, repair loops, and scheduled or messaging-based automations.
What feels promising
The new testing loop and automation builder made Replit more useful for non-specialists trying to ship working apps.
What feels unproven
Long autonomous runs still require review, especially for security, data handling, and production deployment choices.
Source Links
Replit changelog https://docs.replit.com/updates/2025/09/12/changelog
Replit Agent product page https://replit.com/agent
