Files

111 lines
1.5 KiB
JSON

[
[
{
"a": "Cloud",
"href": "/products"
},
{
"h1": "Evals"
},
{
"p": "Measure model and agent quality."
},
{
"a": "Talk to us",
"href": "/contact-sales"
},
{
"a": "Source",
"href": "https://github.com/hanzoai/cloud"
},
{
"a": "Evals",
"href": "/cloud/evals"
},
{
"a": "Benchmark",
"href": "/cloud/benchmark"
},
{
"a": "Research",
"href": "/cloud/research"
},
{
"a": "Datasets",
"href": "/cloud/datasets"
},
{
"a": "Experiments",
"href": "/cloud/experiments"
},
{
"a": "Scores",
"href": "/cloud/scores"
},
{
"a": "Score Configs",
"href": "/cloud/score-configs"
},
{
"li": "gateway Ready"
},
{
"li": "payments-api Ready"
},
{
"li": "checkout-web Building"
},
{
"li": "docs-site Ready"
},
{
"p": "Every request enters here, so the limiter does too."
},
{
"code": "api.hanzo.ai /v1/eval"
},
{
"a": "Open in the console",
"href": "/home"
}
],
[
{
"p": "Paste and ship"
},
{
"p": "Paste this into any agent. It reads the skill manifest and calls Evals from there."
},
{
"button": "Copy"
},
{
"code": "Read https://hanzo.ai/skill.md and use Hanzo Evals in my project. Start with: hanzo eval runs create"
}
],
[
{
"p": "Benchmark, grade, and regression-test models and agents. LLM-as-judge, golden sets, and drift detection with reproducible scorecards anchored on-chain."
},
{
"p": "A human signs a company into existence. After genesis, agents can run it."
}
],
[
{
"p": "Related capabilities"
},
{
"a": "Benchmark",
"href": "/cloud/benchmark"
},
{
"a": "Research",
"href": "/cloud/research"
},
{
"a": "Datasets",
"href": "/cloud/datasets"
}
]
]