Satyawan Singh

Satyawan Singh

ML ENGINEER · FOUNDER · LEICESTER, UK

I build systems that prove things. Currently: Velkron, the verification layer for AI in regulated industries. Before and around that: a formally tested blockchain, a clinical speech model trained from scratch, and a set of open-source libraries that all circle one conviction — machine output should be provable, not trusted.

Everything below is real, dated, and checkable. That is the point of this page.

PROJECTS

VelkronFounder · 2026 · LIVE

The verification layer for AI in regulated industries. Deterministic compliance checks, tamper-evident receipts, proof of inference.

cargo-vouchCreator · 2026 · LIVE

Rust tool that proves a function can't panic, built on Kani. Four honest verdicts; INCONCLUSIVE is never a false pass.

certain · groundkit · disco · stigmaAuthor · 2026 · OPEN SOURCE

Four zero-dependency Python libraries, one idea: check the output, don't trust it. Conformal abstention, grounding, verifier-gated search, agent consensus.

PRAXISMSc dissertation, University of Leicester · 2026 · RESEARCH

Trust-scoring for clinical AI: when should a medical model's output be believed, and when should it abstain?

ZovoNotesBuilder · 2025–26 · PRE-PILOT

NHS GP scribe with a 119M-parameter Conformer ASR model trained from scratch for UK clinical audio.

FINGAURDBuilder · 2026 · PRE-REVENUE

RegTech retrieval for FCA-regulated firms, with provenance-gated citations and a refusal-first answer gate.

EvaporChainCreator · 2026 · PAUSED

A 140-crate Rust L1 blockchain with 25,000+ passing tests and novel consensus-verification primitives. Great training, wrong company. The verification instinct survived it.

WRITING

SHIP LOG

VERIFY