CDE — Causal Dynamics Engine
From raw data to governing structure.
CDE discovers governing equations, causal relationships, and interpretable system behavior from observational and experimental data. These docs show how to connect that workflow from code or from an operator-facing process.
- MCP integrations
- Human guides & references
Quick links
What is CDE?
CDE (Causal Dynamics Engine) discovers governing structure, causal relationships, and interpretable behavior from observational and experimental data. It combines four discovery modes — Symbolic, Neural, Neuro-Symbolic, and Causal — so teams can move from raw observations to equations, causal structure, and system models without switching tools mid-project.
The engine serves two audiences with equal depth. Integration builders connect through MCP, REST, the Python SDK, or the CLI. Researchers and operators use the same underlying engine through guided workflows, campaign management, and review surfaces that keep evidence attached from exploration through publication.
Every interaction runs through the same underlying discovery workflow. The Truth Dial, Evidence Ledger, and Negative Controls appear after the value story lands: they help teams review, compare, and reproduce findings instead of trusting them blindly.
Discovery architecture
Four discovery modes, one pipeline
CDE does not prescribe one method. Instead, it offers four complementary modes that map to different discovery problems: closed-form laws, messy high-dimensional systems, hybrid explanation, and intervention questions.
Symbolic
Use Symbolic when the team needs a closed-form law it can read and test. It excels when domain expertise can be encoded as explicit constraints and the search space is well-defined.
Neural
Use Neural when the data is high-dimensional, heterogeneous, or too irregular for a compact law on day one. It is the right starting point when flexibility matters before distillation.
Neuro-Symbolic
Use Neuro-Symbolic when the data is messy but the result still needs to end as an interpretable law. The neural component proposes structure and the symbolic component distills it into something a team can inspect.
Causal Dynamics
Use Causal Dynamics when the question is directed influence and intervention: what drives what, what changes if you perturb it, and what experiment should come next. It discovers governing causal structure that correlation alone cannot resolve.
How CDE makes findings reviewable
Once CDE finds something worth considering, these surfaces help a team decide whether to trust it, compare it, or promote it. They exist to support review, not to replace the discovery value itself.
Truth Dial
The Truth Dial classifies every claim into maturity tiers: Explore, Validate, and Publish. Claims begin in the Explore tier, where they represent preliminary observations. As evidence accumulates and validation checks pass, claims can be promoted through tiers. Each promotion event is recorded with its rationale, reviewer identity, and the evidence snapshot that justified it. The Publish tier represents claims that have met your organization's bar for external communication.
Evidence Ledger
The Evidence Ledger is an append-only record of every significant event in a discovery session: data ingestion, mode selection, parameter choices, intermediate results, promotion decisions, and negative control outcomes. Entries are content-addressed, meaning any tampering with historical records is detectable. The ledger serves both compliance and reproducibility—an auditor can reconstruct the path from raw data to published claim without access to the original runtime.
Negative Controls
Negative Controls are falsification checks that run alongside or after discovery passes. They test whether the observed patterns survive when key assumptions are relaxed, when data subsets are permuted, or when alternative explanations are fed into the same pipeline. A claim that has passed negative controls carries stronger evidence than one that has only been confirmed positively. The platform records which controls were run, their outcomes, and whether any controls were skipped along with the reason for the omission.
Access surfaces
Four ways to connect
CDE exposes the same governed operations through multiple access surfaces. The choice depends on your integration pattern, not on feature availability—every surface reaches the same engine.
REST API
Resource-oriented HTTP endpoints for services, legacy orchestrators, and any client that speaks HTTP. Predictable pagination, filtering, and typed claim payloads.
Python SDK
Ergonomic sync and async clients with typed models for notebooks, pipelines, and services. Handles retries, pagination, and idempotency patterns internally.
MCP
Model Context Protocol integration for external services that need discoverable tool surfaces, structured invocations, and session-aware research continuity.
CLI
Terminal-first access for operators in clusters, CI environments, and HPC systems. Structured output formats and scriptable exit codes for automation.
For Integrations
Use these docs when CDE is inside an agent, service, or orchestration layer and the job is to turn observations into equations, causal structure, or system models programmatically.
For Humans
Use these docs when people choose datasets, pick discovery modes, review findings, and decide what is worth acting on.
How to use these docs
If you are building an integration
Start with the Agent Integration overview to understand sessions, policies, and manifests. Then choose your access surface: MCP for interactive tool use and session-aware research, or the REST API for service-to-service calls. The Python SDK wraps the REST layer with typed models and retry logic for pipeline use cases.
Review the policy and review surfaces only after the core integration path is clear, so your team knows how CDE will be called before deciding how much autonomy it gets.
If you are a researcher or operator
Start with Human documentation for guided paths through your first run, campaign setup, and claim review workflow. When you are ready to automate, the CLI guide covers terminal workflows and the SDK reference covers notebook and pipeline integration.
Teams that need to explain review rigor to external partners should pay particular attention to the sections on Truth Dial tiers, controls, and evidence provenance.