What if an agent breaks?
The Builder who built it fixes it. If they don't, the agent gets removed from the marketplace. You only pay for runs that actually work.
Written By pvdyck
Last updated 2 minutes ago
Who's Responsible
Builders own their agents. That means they're on the hook when something goes wrong.
This isn't a "sell and forget" marketplace. Builders have skin in the game because their reputation and revenue depend on their agents working.
Incentive Structure:
Builder fixes agent → Agent works well → More runs → More revenue
Quality = Earnings correlation. The better the agent works, the more the Builder earns.
What Happens When a Run Fails
If an agent fails mid-execution, you don't pay the full price. The system only charges for resources actually consumed.
Failure Example:
- Authorized: $0.20
- Agent makes 1 API call ($0.03)
- Crashes!
- Charged: $0.03 (only for completed work)
- Refunded: $0.17 (instantly back to balance)
You never pay for work that wasn't done.
Quality Control
The marketplace tracks performance. Success rates. Run times. Error frequencies. This data is visible.
Quality Metrics:
- Performance Tracking → Every run logged
- Success Rate calculated
- Status assigned:
- 98%+ success → Featured
- 80-98% success → Normal
- < 80% success → Flagged ⚠️
- Consistently bad → Delisted ❌
Agents that consistently fail get flagged. Agents that stay broken get delisted. Builders who abandon their work lose their listings.
Evolution of the Marketplace:
- New agents launch
- Tested by users
- Performance data emerges
- Good agents rise (featured)
- Bad agents sink (delisted)
- Quality improves (self-cleaning)
Good agents rise. Bad agents disappear. The marketplace self-cleans over time.
Before You Buy
Every agent shows its track record. You can see how many times it's been run, how often it succeeds, and what other Producers think.
Due Diligence Checklist:
Don't buy blind. Check the stats. Read the reviews. Test with a few runs before going heavy.