Ask Jev structured questions about a state and read the answers back
Connect Jev and your agent can put a piece of shared state — an incident summary, a change request, a config snapshot — in front of TypeSafe AI's System One and get structured answers back. JEV_EVALUATE_STATE runs one or more named Noul, Choice, or Score questions against that state in parallel, and each call is usage-priced inference. JEV_LIST_MODELS shows which model names and aliases your account can use. Luumen authenticates with an API key. Both tools are read-only, so answers come back right away.
2 tools, all read-only. They answer instantly, and every call is logged.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
No. Every one of the 2 tools LuumenAI has for Jev is read-only, so it can answer questions from Jev but cannot change anything in it. Reads are not gated — they answer immediately, and each one is recorded on the audit trail with the actor and the result.
You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.
Every call to Jev is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.