Product — technical view
The machinery behindinstitutional intelligence.
Three mechanisms, one compounding system. The Context Graph supplies structure, the Correlation Engine supplies relationships, and Change Observability keeps both honest over time.
Architecture
Sits between your systems and your AI.
Context Graph
Organizational context, structured
A living, queryable model of the entities, systems, workflows, decisions, and relationships that define how your organization operates.
How it works
- 01
Ingests structure and metadata from the systems where work already happens — ERP, CRM, data platforms, collaboration and documentation tools.
- 02
Resolves entities across sources: people, teams, systems, processes, assets, and decisions are unified into one coherent graph.
- 03
Captures decision history alongside the context that shaped it — who owned it, what informed it, what it changed.
- 04
Exposes context as a reusable layer for AI systems, copilots, and human operators through APIs and query interfaces.
What you get
Correlation Engine
Signals, connected
An analytical layer that finds meaningful relationships across events, workflows, decisions, and outcomes — the patterns isolated dashboards never show.
How it works
- 01
Consumes operational signals across the Context Graph: deployments, incidents, spend, adoption, org changes, workflow events.
- 02
Identifies statistically and semantically meaningful relationships — leading indicators, co-movements, and causal candidates.
- 03
Ranks patterns by business relevance so teams see the few connections that matter, not a wall of correlations.
- 04
Feeds validated patterns back into the graph, where they become permanent institutional knowledge.
What you get
Change Observability
Drift, made visible
Continuous monitoring of how systems, workflows, knowledge, and ownership evolve — so drift is detected while it is still cheap to correct.
How it works
- 01
Baselines expected behavior for processes, systems, and knowledge domains derived from the Context Graph.
- 02
Detects drift across three dimensions: process drift, knowledge and decision drift, and system change.
- 03
Traces blast radius through the graph — which teams, decisions, and AI systems a change actually touches.
- 04
Alerts with context: not just that something changed, but why it matters and who should care.
What you get
Provenance
Trustworthy AI, made tangible.
Every DotIQ recommendation carries its full evidence chain — from the originating source system, through the relationship and reasoning, to the recommended action. Leaders inspect the why, not just the what.
Deployment
Runs inside your perimeter. Answers to your governance.
DotIQ deploys within your security boundary, respects your data-residency requirements, and never trains shared models on your data. SSO, role-based access, and full audit trails are table stakes — not roadmap items.
Permissions
Inherits access controls from source systems — users only see what they're already allowed to see.
Provenance
Every insight traces back to the systems, records, and decisions it came from.
Confidence
Recommendations carry explicit confidence scores — never black-box answers.
Temporal context
Knows when something was true, not just that it was — stale knowledge is flagged, not served.
Explainability
Evidence, timeline, and reasoning behind every conclusion, inspectable on demand.