FutureAGI
for LuumenAI
Read your FutureAGI evals, datasets, and simulations from the terminal
Ask what FutureAGI already knows about your AI systems without leaving the terminal. Luumen lists evaluation tasks and custom eval configs, datasets, annotation queues and labels, agent definitions, personas, scenarios, and configured run tests. This integration is read-only: nine listing tools, no writes, and nothing is executed. Connected with an API key.
The FutureAGI toolbox
9 tools, all read-only. They answer instantly, and every call is logged.
- ReadList Agent DefinitionsList one page of agent definitions in the connected FutureAGI organization, optionally filtering by type, name, assistant ID, or agent ID.
- ReadList Annotation LabelsList one page of FutureAGI annotation labels by type, name, project, or dataset, optionally including usage counts.
- ReadList Annotation QueuesList one page of FutureAGI annotation queues by status or name, optionally including item counts.
- ReadList Custom Eval ConfigsList custom evaluation configurations, optionally restricted to a FutureAGI project or evaluation task.
- ReadList DatasetsList one page of datasets in the connected FutureAGI organization, optionally searching by name.
- ReadList Eval TasksList one page of FutureAGI evaluation tasks, optionally filtering by project ID or task name.
- ReadList PersonasList one page of built-in and workspace personas for FutureAGI simulations, with type, simulation-mode, and text filters.
- ReadList Run TestsList one page of configured FutureAGI run tests without executing them, optionally filtering by name, source type, or prompt template.
- ReadList ScenariosList one page of FutureAGI simulation scenarios, optionally filtering by agent definition, agent type, or search text.
Questions
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 9 tools LuumenAI has for FutureAGI is read-only, so it can answer questions from FutureAGI 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 FutureAGI is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut FutureAGI to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.