BrainGraph
for LuumenAI
Search your knowledge graph, and add new source material as an approved step
Connect BrainGraph and your team's runbooks, postmortems, vendor docs, and recorded calls become something the agent can query mid-incident. Ask a question in plain language and get facts back with their sources. When new material should join the graph, the agent queues the ingestion as a previewed step you approve first.
The BrainGraph toolbox
10 tools: 6 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet Document ProgressGet the current transcription, processing, and analysis status for a BrainGraph document.
- ReadList BrainsList the connected BrainGraph account's knowledge brains and identify the default brain for filtering or targeting other tools.
- ReadList DocumentsList BrainGraph documents newest first, optionally filtering by filename or notes, failed ingestion status, and brain.
- ReadList Graph PatternsFind recurring relationship-chain patterns in the connected BrainGraph knowledge graph, subject to a minimum occurrence count.
- ReadResolve EntityResolve an entity name to a canonical BrainGraph record.
- ReadSearch BrainSearch facts in the connected account's BrainGraph knowledge graph using a natural-language question, optionally restricted to selected brains.
- WriteIngest Web PageFetch readable content from a public web page and queue it for BrainGraph ingestion. Approval by default
- WriteIngest YouTube VideoSubmit a YouTube video for metadata, transcript, and speaker processing; the result may only confirm that processing was queued. Approval by default
- WriteTranscribe AudioUpload an audio file or submit a direct public audio URL for diarized transcription and graph ingestion. Approval by default
- WriteUpload DocumentUpload a document file supplied by the caller or plain text and queue it for BrainGraph ingestion. Approval by default
One prompt, start to finish
What a governed BrainGraph run looks like inside Luumen.
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.
Read actions answer immediately. Anything that writes — ingest web page, ingest youtube video, transcribe audio, upload document — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to BrainGraph — read or write, approved or declined — 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 BrainGraph to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.