PromptLayer
for LuumenAI
Read prompt versions, request logs, and eval tables from PromptLayer
Ask what changed in a prompt before you debug the output. Luumen connects to PromptLayer with an API key and reads your registry: PROMPTLAYER_GET_PROMPT_TEMPLATE for a specific version or release label, PROMPTLAYER_GET_REQUEST_LOG for one call's input, output, timing, and scores, PROMPTLAYER_LIST_TABLE_ROWS for eval data. Read-only, so nothing runs and nothing changes.
The PromptLayer toolbox
16 tools, all read-only. They answer instantly, and every call is logged.
- ReadGet Prompt TemplateRetrieve a prompt template version, release label, messages, model metadata, snippets, and optionally provider-ready kwargs without executing it.
- ReadGet Registered ToolRetrieve a PromptLayer registered tool definition by ID or name at a selected version or release label without test execution.
- ReadGet Request LogRetrieve one PromptLayer request log with its recorded input, output, timing, usage, metadata, tags, and scores.
- ReadGet Skill CollectionRetrieve a PromptLayer skill collection and its files as JSON at a selected version or release label.
- ReadGet TableRetrieve one PromptLayer Table's metadata and per-sheet row counts by UUID.
- ReadGet WorkflowRetrieve a PromptLayer workflow definition by ID or name at a specific version or release label without running it.
- ReadList Folder EntitiesBrowse or search PromptLayer folders and registry entities in the API-key workspace, optionally recursively and with metadata.
- ReadList Prompt TemplatesSearch and page through PromptLayer prompt templates and snippets without executing a model.
- ReadList Registered ToolsList and filter tools defined in PromptLayer's tool registry without executing them.
- ReadList Skill CollectionsList and filter PromptLayer skill collections available in the API-key workspace.
- ReadList Table ColumnsList one page of user and optionally system columns for a PromptLayer Table sheet.
- ReadList Table RowsRead one page of rows and cells from a PromptLayer Table sheet, with optional schema and execution aggregates.
- ReadList TablesSearch and page through PromptLayer Tables by folder, name, or referenced prompt.
- ReadList Table SheetsList one page of sheets in a PromptLayer Table, optionally filtering by referenced prompt.
- ReadList WorkflowsSearch and page through PromptLayer workflows without running them.
- ReadSearch Request LogsSearch PromptLayer request logs by text or structured filters and return one rate-limited page sorted by operational fields.
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 16 tools LuumenAI has for PromptLayer is read-only, so it can answer questions from PromptLayer 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 PromptLayer 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 PromptLayer to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.