Sato Hub

Glossary

Preflight verdict

One of four answers — go, caution, no, unknown — returned before an agent installs, connects, pays or trades, with every reading and the field it came from.

Preflight is a single free call an agent makes before acting on something it did not write: a GitHub repository, an npm package, an https endpoint, an ERC-8004 agent reference, or an ERC-20 token. It returns one verdict plus the readings behind it, each naming the field it came from and the date that field was written.

The verdict is a summary of evidence, not a judgment of the thing. "go" means the listing is active, sits in the High Sato Score tier and carries at least one earned check such as a reproduced install. "unknown" means Sato Hub holds no record and nothing was probed — an honest absence returned instead of a low-confidence guess.

It is not a security review, a code audit, or a statement about returns. The same engine answers over HTTP and over MCP, so the two lanes cannot disagree about what was read.

Where Sato Hub measures it

Numbers live on those pages and refresh on their own schedule; this definition does not restate them.

Related terms

Sources

Cite this page

Sato Hub. "Preflight verdict (glossary)." Sato Hub, updated 2026-09-14, accessed 2026-09-14. https://satohub.ai/glossary/preflight-verdict

Data last refreshed 2026-09-14; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.