Automatic Ontologies
Turning policies, SOPs, API schemas, workflow logs, and evaluated agent traces into explicit, versioned rule layers.
Research
Rippletide started as deep research and still runs on it. This page gathers the technical work underneath every risk review, Safety Case, and decision preview.
Long-term direction
Rippletide's long-term product direction is Runtime Reinforcement: using guarded actions, approvals, blocks, corrections, and traces to suggest stronger explicit policies over time. Enforcement remains deterministic, auditable, and human-governed: the system proposes guard improvements and regression scenarios, humans accept, edit, or reject them.
Turning policies, SOPs, API schemas, workflow logs, and evaluated agent traces into explicit, versioned rule layers.
The hypergraph decision database that combines memory (facts, context, provenance) with reasoning (plans, rules, constraints).
Evaluating agent behavior against ground-truth outcomes, the discipline underneath unsafe scenario testing.
Deep explainers
Long-form technical pages written along the research. They use the research vocabulary and go deeper than the product pages.
Also see the whitepaper and The Decision Layer podcast.
The research above is packaged into Safety Packs: risky write-actions, evidence checks, approval rules, unsafe scenarios, and audit traces, proven on your agent in 10 working days.