Can an agent use your product?
A real coding agent reads your docs and tries one onboarding task in a fresh sandbox. An independent judge verifies the evidence. You get a verdict and, on graded runs, an agent experience score.
Try
Sorted by experience score. Experience measures friction in the tested task. Completion says whether it succeeded.
| # | Product | ScoreExperience score | ||
|---|---|---|---|---|
| Loading benchmark results... | ||||
| 01 | Open-MeteoWeather APIopen-meteo.com100% passed | 100 | ||
| 02 | context.devSearchcontext.dev100% passed | 100 | ||
| 03 | FirecrawlSearchfirecrawl.dev100% passed | 100 | ||
| 04 | ParallelSearchparallel.ai75% passed · 1 blocked | 100 | ||
| 05 | tinyfish.aiBrowser Automationtinyfish.ai67% passed · 1 blocked | 100 | ||
| 06 | ExaSearchexa.ai88% passed · 1 blocked | 82 | ||
| 07 | struct.aiAI production monitoringstruct.ai0% passed · 1 blocked | 26 | ||
| 08 | apollo.ioSales intelligenceapollo.io0% passed · 2 blocked | Not graded | ||
| 09 | AI SDKAI SDKai-sdk.dev0% passed · 1 blocked | Not graded | ||
| 10 | StripePaymentsstripe.com0% passed · 1 blocked | Not graded | ||
| 11 | tinyfish.comBrowser Automationtinyfish.com0% passed · 1 blocked | Not graded | ||
11 products
Page 1