Deep Knowledge: a Knowledge Graph from Your Documents
Entities and relationships from documents — searchable, traceable, permission-aware.
Create a knowledge graph from entities, relations and permissions
Deep Knowledge goes beyond full-text search: the AI recognises entities such as people, locations, contracts, invoices and deadlines and connects them into a graph. You can trace which person belongs to which project, which location hangs off which contract and where deadlines collide — across file boundaries and under strict respect for permissions.
Deep Knowledge surfaces relationships hidden across files
A knowledge graph is useful when relevant information is spread across many documents: counterparties, locations, projects, deadlines, invoices, policies, people and cases. Deep Knowledge extracts these entities and links them to the sources they came from.
This helps with contract landscapes, supplier files, project portfolios, quality evidence or support histories. Teams see more than a search hit; they see the context: which deadline belongs to which contract, where a person appears and which documents refer to the same entity.
The graph is not a permission bypass
The same permissions apply in the graph as in the source documents. If a person may not see a document, they may not see a node, edge or indirect hint derived from it.
For critical use cases, the graph can be combined with human approval, an audit trail and manual correction. It becomes a research and review tool, not a black box.
AI, data and approvals in Deep Knowledge: a Knowledge Graph from Your Documents
AI in this module is source-grounded. It does not search files indiscriminately; it uses approved documents, role permissions, metadata and business rules. Entities & relationships, Location linking, Hidden connections, Permission-aware graph become a controlled process: AI finds evidence, marks uncertainty, shows source passages and stops when human review is required.
Risky cases need explicit stop points: low model confidence, missing sources, permission conflicts, cost impact or customer-facing communication enter a review queue. That keeps speed high without giving up control, traceability or privacy.
Which data and integrations the module needs
For Deep Knowledge: a Knowledge Graph from Your Documents to work in daily operations, the data currently scattered across spreadsheets, email, business systems and file stores has to be modelled properly. The core inputs are roles, status values, deadlines, documents, comments, owners and the rules behind Entities & relationships and Location linking.
A custom build connects that data to existing systems instead of forcing teams to maintain it twice: ERP, accounting, DMS, Microsoft 365, email, ticketing systems or mobile apps can be connected depending on the process. The goal is not the longest integration list; it is a clear source of truth.
Why a custom build can beat standard software here
Standard software starts faster and can be the right choice for simple workflows. A custom solution becomes stronger when Deep Knowledge: a Knowledge Graph from Your Documents has to fit exact roles, data ownership, approval paths, hosting requirements and internal exceptions. Then process fit matters as much as feature count.
The honest downside: a custom build needs more discovery, rollout work and prioritisation at the beginning. The upside comes afterwards: fewer workarounds, no per-seat logic, controllable hosting, owned source code and modules that can grow as requirements change.
What this solution covers
-
Entities & relationships
People, locations, contracts and projects are captured as connected nodes.
-
Location linking
Locations from documents are detected and linked to contracts and projects.
-
Hidden connections
Relationships across files that full-text search never surfaces.
-
Permission-aware graph
Users see only nodes and edges they are entitled to.
Frequently asked questions
Which problem does Entities & relationships solve in Deep Knowledge: a Knowledge Graph from Your Documents?
Entities & relationships keeps important information from disappearing into chats, emails or spreadsheets. Ownership, status, deadlines and records stay in one place; Location linking can connect directly so the process does not break between tools.
Which data does Deep Knowledge: a Knowledge Graph from Your Documents need for the Location linking workflow?
The core inputs are project data, roles, status values and the rules that currently control Location linking and Hidden connections. Those inputs become a data model that remains searchable, exportable and extendable.
Can Deep Knowledge: a Knowledge Graph from Your Documents integrate the Hidden connections workflow with existing systems?
Yes. APIs, imports, exports and role models are planned so the Entities & relationships and Hidden connections workflows fit the existing process landscape. With a custom build, source code, data and hosting remain controllable.