Causal discovery that finds real cause-and-effect relationships in your data — no LLMs, no black boxes, no external libraries. Every finding is fully auditable.
Our Approach
While others race to wrap LLMs around everything, we took a fundamentally different path — one that prioritizes transparency, reproducibility, and trust.
Our causal discovery engine is 100% Python with zero external libraries. No neural networks, no API calls, no opaque model weights. Just clean, deterministic logic you can read and verify.
Every causal claim traces back to specific observations with confidence scores, preconditions, and exclusion criteria. No hallucinations — just evidence-backed findings you can verify against your source data.
We don't find patterns — we discover cause-and-effect relationships. Our engine identifies what drives outcomes, what blocks them, and under which specific conditions, structured as queryable knowledge.
Process
Our engine observes your data, builds causal models, and distills them into structured knowledge you can query, compare, and act on.
Point our engine at your dataset — clinical trials, operational data, event logs. No preprocessing required.
The engine processes every record as an observation, building a cognitive model of actions, effects, and context over multiple epochs.
Causal rules emerge with preconditions and blockers. Claims are tested, consolidated, and scored for confidence across the full dataset.
Ask questions of the knowledge base — what works, for whom, and why. Get structured answers with full evidence trails.
In Practice
1,836 consensus causal claims extracted from 1,584 patients across 2 clinical trials — 47 nodes, 99 edges. Click to enlarge.
Causal network generated from oncology clinical trial data accessed via Project Data Sphere. Project Data Sphere and the data provider(s) have not contributed to, approved, or are responsible for these research results.
Applications
The same engine, the same process. Point it at any structured dataset and extract causal knowledge.
Discover which treatments work for which patient subgroups, identify hidden risk factors, and run counterfactual analyses across trials.
Extract signal selection rules from market data. Identify which conditions cause specific outcomes and which are noise.
Find causal drivers of match outcomes beyond correlation. Identify which tactical and contextual factors actually change results.
Understand what causes defects, delays, or failures in your processes — and the specific conditions under which they occur.
In a world of black-box AI, we believe every insight should come with a receipt. Our engine produces structured, traceable causal claims — not predictions you have to take on faith.
Get Started
Have a dataset that needs deeper understanding? We'd love to hear from you.
research@mindinsert.com