Layer 02
Data & Context
Give AI the context to understand the organisation.
Models know the world. They do not know your organisation. This layer connects your documents, databases and operational data to AI as governed context, so answers and actions are grounded in what your organisation actually knows.
What the data and context layer includes
- Enterprise data
- Documents
- Databases
- Knowledge bases
- Operational data
- Customer data
- RAG
- Vector databases
- Knowledge graphs
- Memory
- Context
- Data lineage
From raw data to governed context
- 01
Connect
Bring in documents, databases, knowledge bases and operational and customer data from where they already live.
- 02
Ground
Index content for retrieval with RAG, vector databases and knowledge graphs, so AI answers from your sources.
- 03
Remember
Keep memory and context across conversations and tasks, scoped to the user, team or process it belongs to.
- 04
Trace
Record data lineage, so every answer and action can be followed back to the sources it used.
Data controls apply before AI sees anything
Context is only safe if access is checked first.
Classification
Content carries a classification that policy can act on.
Permission-aware retrieval
Retrieval respects who is asking, so AI does not surface what the person could not open themselves.
Residency and boundaries
Data location and processing boundaries are set per source and per deployment.
Retention
How long context and memory are kept is a policy, not an accident.
Intelligence you own
Proprietary knowledge, memory and derived insight are assets. This layer is built so they stay yours: portable, governed and independent of any single model provider. That is intelligence sovereignty, one of the seven kinds of sovereignty on this platform.
Where this sits in the closed intelligence loop
Control, then intelligence, then agency, then execution, then outcomes. Outcomes and their evidence flow back into data and context, so the loop closes.
- 01 · Layer 01ControlDecide where and how AI runs.
- 02 · Layers 02 and 03IntelligenceTurn data and knowledge into useful intelligence.(this page)
- 03 · Layer 04AgencyLet AI act within defined authority.
- 04 · Layer 05ExecutionEmbed that action in how the organisation operates.
- 05 · Layer 06OutcomesMeasure business results, and feed evidence back into data and context.
This layer is the first half of the Intelligence stage. Outcomes flow back here as new context, which closes the loop.
Where Swfte products sit in this layer
Product names are kept. Each is an entry point into the platform.
Cortex
Answers from your files and meetings, runs on the laptop by default, and puts engineers’ AI agents under one policy and one audit trail.
What this means for your team
- CDO
- Turn enterprise data into organisational intelligence.
- Legal / Compliance
- Make AI activity traceable, governed and evidential.
- CISO
- Give AI identity, permissions, policies and auditable controls.
Frequently asked questions
What is data and context for AI?
It is the layer that gives AI knowledge of your organisation: enterprise data, documents, databases, knowledge bases and memory, retrieved under access controls and traceable through lineage.
Do you train models on our data?
This page describes how the platform is designed to ground AI in your data without moving ownership of it. For the current, contractually backed position on training and retention, read the trust centre.
How does retrieval respect permissions?
Retrieval is designed to check the requesting identity against source permissions and data classification before content reaches a model.
What is data lineage for AI?
Lineage records which sources contributed to an answer or action. It is the first link in the traceability chain from data to model to agent to decision to action to outcome.
Which Swfte product handles this layer?
Cortex answers from your company’s files and meetings. The other products read from and write to this layer through their own integrations.
Across every layer
These ideas apply to every layer of the platform.
Controlled autonomy
Five levels, from AI that recommends to AI that adapts within limits.
Trust Profile
The record that describes what each AI system is and may do.
AI sovereignty
Seven kinds of control over your AI estate.
AI governance
Governance that runs inside AI, not beside it.
Swfte Intelligence Platform
Analyse and visualise your data, usage, agents and outcomes, then build from what you see.
Company brain
One governed place for everything your organisation knows, for every product to read from.
Custom models
Models adapted on your own data, evaluated before release and deployed under your control.
How Swfte builds with Cortex
An honest first-party account of how we build, review and approve work, labelled by status.
Governed agents
Identity, permissions, policy, approvals and audit for agents, with ten templates.
Compliance-approved workflows
Workflows with approval gates and evidence built in, with twelve templates.
Build on Data & Context with Swfte
Start with one entry point. Add intelligence, agents, workflows and infrastructure as you prove value.