Connect knowledge
to its source.
Manage one organization per installation. Start with Agent Studio sign-in, then search documents, explore the Knowledge Graph, and connect Agents.
01 · Get started
Start with Agent Studio sign-in.
Verified Studio users join this installation automatically. Current Studio permissions and teams, and the document access rules, decide what you can use. There is no separate organization to create or choose.
Manage application permissions, members and teams in Agent Studio.
Choose a default sharing scope when saving.
Read · organization members
Manage · current Studio administrator
Read · team members and organization administrators
Manage · team manager or current Studio administrator
Read · you
Manage · you
Organization-wide writes and management require current Studio administrator permission. Members of a Studio team and administrators can access team content; personal content remains private to its owner. Studio guest permission denies writes.
02 · Context search
Choose the search surface that fits your question.
Choose All knowledge to search document chunks and Knowledge nodes together, or narrow the result type. Select a result to read its full content and sources without losing the list.
Search diagnostics are optional details. Relative relevance compares results within this search; it is not a confidence score. Archived and unprocessed documents are excluded.
When configured, reranking applies to All knowledge and MCP context_search. Documents and Graph searches use lexical and optional semantic scores. If reranking fails, results use hybrid ranking.
03 · Ingest documents
Preserve originals and search their chunks.
Upload text, PDF, Office, HTML, or EPUB files from Documents. Choose a sharing scope and inspect processing status and source text. Ready means document search is available; AI knowledge extraction and verification continue separately.
pendingprocessingreadyPending and processing documents refresh automatically while the page is visible, for up to two minutes. Use Refresh after polling pauses. For a failed document, inspect the error and choose Retry processing when you have write permission. Archiving requires manage permission.
04 · Explore Graph
Follow relationships without losing the evidence.
Open Knowledge Graph from the sidebar or explore relationships from a search result. Search for a node, select it in the map or node list, then inspect connected relationships and original sources. Use the selected node as a new exploration center.
Drag nodes to pin their positions, drag the background to pan, and scroll or pinch to zoom. Use fit, reset layout, or full screen; press Escape to leave full screen. Keyboard node navigation and readable source evidence remain available.
Graph progress tracks extraction, verification, and automatic processing, not completion of human review. Search prioritization targets unfinished candidates whose extracted names or aliases match. Refresh relationships to load new connections.
05 · Track work as objects
Keep decisions and work current with their sources.
Objects lists records such as decisions, action items, risks and open questions, and entities such as people and projects, by ontology type. Each object shows its properties, labeled links, source passages and activity. Members with write access change editable properties, such as an action item's status. Every change records who, when and why, and the latest edit can be reverted.
Organization administrators define object types, properties and link types in Settings → Ontology. Agents use knowledge_objects and knowledge_object_update over MCP.
06 · Review AI candidates
Automatically apply qualified knowledge and review uncertain items.
With a knowledge extraction model and document worker configured, a separate AI verification checks source quotations, usefulness, conflicts, and ontology rules. Repeated entities and relationships in the same scope are grouped with their sources. AI judgments and quotation checks do not guarantee factual accuracy.
Automatic acceptance
Apply explicit, useful items that pass source evidence and policy checks to the Graph, retaining their sources.
Needs review
Compare reasons and source text for uncertain, conflicting, or ontology-constrained items, then select which sources to apply.
Automatic exclusion
Leave unsupported or incidental items and relationships that do not identify a specific fact out of the Graph.
Accept or reject knowledge from selected sources. Accepting a relationship includes its required endpoints; rejecting an entity also rejects its unreviewed relationships. Other items remain pending, and rejection does not delete previously accepted Graph data.
Run AI curation queues unextracted chunks in manageable ready documents, unverified candidates, and unfinished automatic decisions. Use chunk review for remaining extraction batches. Curation history shows current and previous assessments and current processing outcomes for the 50 most recently updated extractions. Empty extractions stay out of the default review list.
07 · Connect Agents
Connect Agents to Context through MCP.
Connect to /api/mcp to ingest documents, check processing, and search documents and Graph with context_search. Agent connection shows the external system status and the MCP address.
/api/mcp
Connected services use the verified Studio issuer and subject, never a matching email, to retain the local owner. Current Studio administrators manage the organization Agent token in Settings → General; that token is limited to organization scope.
context_searchdocument_ingestdocument_ingest_statusdocument_ingest_retrydocument_searchknowledge_searchknowledge_neighborhoodknowledge_object_typesknowledge_objectsknowledge_objectknowledge_object_aggregateknowledge_metricknowledge_object_updateknowledge_ledger_importExplore real context now.
Upload a document, search it, and check the original evidence. Connect an Agent when the knowledge is ready.