The simplest way to think about IGL
Three stacks. The first stores records, the second generates answers, the third turns every interaction into organizational intelligence that stays with you.
Traditional Software
The application stores records. It does not understand relationships, decisions, outcomes, or context beyond what developers explicitly program.
Traditional AI
The AI generates an answer. The conversation has value in the moment, but very little becomes a permanent organizational asset. The intelligence largely remains inside the model provider.
Identity Governed Logic
Now every interaction expands organizational intelligence.
The same question, two very different answers
A compliance lead at an operator asks one question. Here is what happens in a conventional system, and what happens when the question enters the IGL runtime.
Traditional compliance software
What filings are due next month?
That's it.
IGL Compliance Intelligence
What filings are due next month?
Identity GET /identities/{identityId}
IGL understands who is asking.
- Who is asking
- Their responsibilities
- Their assets
- Their role
- Their authority
Authority POST /authority/evaluate
IGL determines the boundary of the answer before looking anything up.
- What the user can see
- What actions they can take
- What approvals are required
Knowledge POST /query
IGL retrieves the governed facts, not a keyword match.
- Wells
- Permits
- Reports
- Prior filings
- Regulatory obligations
Policy POST /policies/evaluate
IGL applies the rules that govern the recommendation.
- Company policy
- State regulations
- Internal controls
Evidence POST /evidence
Every recommendation is linked to what supports it.
- Source document
- Filing requirement
- Regulation
- Previous submission
Outcome POST /outcomes POST /outcomes/{outcomeId}/measurements
When the filing is completed, the result goes back into the graph.
- Result is captured
- Success is measured
- Future recommendations improve
The next compliance decision is better informed.
Most AI systems answer questions.IGL answers questions and learns from the results.
From search to a governed graph
Current tools are mostly search systems
IGL introduces a governed graph
Now one answer can expose hundreds of related facts. Not because the model memorized them. Because IGL already organized them.
From a conversation that ends to a user who becomes understood
Most AI remembers almost nothing
Ricorsa
The user becomes more understandable over time. The system develops continuity. The intelligence compounds. And the person keeps the controls: learning can be paused, any node can be forgotten, the graph can be reset or exported with its provenance, each a governed action with a signed receipt (the Subject service, v0.3).
Five kinds of logic before any AI response is generated
Most platforms have
IGL introduces
The result is explainable and auditable intelligence.
Five things the graph gives the organization
Model independence
The contract names a model per request and no vendor in its schema:
- the hosted service runs Anthropic models today
- the open-source runtime runs open models on your machine
- GET /capabilities reports the providers in use
Tomorrow: something else.
The model is interchangeable. The intelligence stays with the customer.
Institutional memory
Organizations stop losing knowledge when:
- employees leave
- projects end
- systems change
- conversations disappear
The graph preserves context.
Explainability
Every answer can be linked to:
- sources
- evidence
- policies
- decisions
You can explain why an answer exists.
Governance
Every action can be governed by:
- permissions
- roles
- regulations
- approvals
- policies
Before execution occurs.
Cross-domain intelligence
The same architecture works for:
- Ricorsa
- WellSite
- LeaseXPlorer
- VDRPros
- TortGraph
- RealEChat
- RealStar
- Higher Education
Because the core problem is identical.
Organizations do not suffer from a lack of information.Organizations suffer from a lack of governed intelligence.
IGL is not really an AI platform.It is an Intelligence Infrastructure Platform.
SMEs, universities, energy operators, law firms, brokerages, and enterprises can continuously accumulate intelligence that remains theirs regardless of which AI model powers the reasoning layer.