CognitiveEstimator
Early access, on request. Turn your data into predictive models without a data-science specialist: a web interface for everyone, a Python API for developers.
Development
Engineering tools for spec-driven development (SDD), predictive modelling, optimisation and active learning.
Spec-driven development frames AI agents with verifiable specifications; predictive modelling, optimisation and active learning cut the simulations and tests needed to converge. CognitiveSand turns both into concrete tools for software projects and Model-Based Systems Engineering.
Software
Explore CognitiveSand's specialized tools for systems engineering and automated predictive modeling.
Engineering models
In development. Engineering calculation models, starting with thermo-fluid systems, notably hydrogen and cryogenic systems, and any calculation that needs real-gas properties.
CognitiveSDD
Phase-gated workflow orchestrator that walks AI agents through software projects (Python, TypeScript, C/C++, Go, Rust) and engineering projects (SysML v2 MBSE) inside firewalled containers.
Need AI that can be audited?
CognitiveSand can build the harness around the model so the output is traceable and integrated into your workflow.
CognitiveEstimator: Automated predictive modeling
CognitiveEstimator is CognitiveSand's predictive modelling library, designed for applied engineering: it learns from your data or simulations a fast model that stands in for them to make predictions, what engineers call a surrogate model. It turns tabular in-memory data tables (such as simulation runs, time-series data, or cost parameters) into calibrated, deterministic, dict-in/dict-out predictors under a strict execution budget, providing honest conformal uncertainty intervals and bit-identical reproducibility.
Engineering models: in development
CognitiveSand is developing engineering calculation models, starting with thermo-fluid systems, notably hydrogen and cryogenic systems, and any calculation that needs real-gas properties. They are not yet available; get in touch if this is relevant to you.
CognitiveSDD: From requirements to verified artefacts
CognitiveSDD is a specs-driven workflow orchestrator that walks AI coding agents and AI modelling agents through phase-gated projects — from user stories or system needs to verified, traceable artefacts — inside network-firewalled containers. A single workflow engine, INCOSE-compliant requirements discipline, ADR-backed architecture, end-to-end @req / @story traceability, and a defense-in-depth security model apply to both project categories.
Software Projects (Python, TypeScript, C/C++, Go, Rust)
For software developers, CognitiveSDD orchestrates a structured workflow through user story discovery, requirements derivation, architecture design with ADRs, test specification with traceability markers, autonomous implementation inside firewalled containers, and full verification — producing source code, automated test suites, and a traceable build where every test links back to its requirement.
Engineering Projects (SysML v2 MBSE)
For systems engineers, CognitiveSDD applies the same phase-gated discipline to Model-Based Systems Engineering. The orchestrator guides the AI through stakeholder needs elicitation, INCOSE-compliant requirements, structural architecture, verification specs, and behavioural modelling — producing a complete SysML v2 model with end-to-end requirement-to-verification traceability.