Satyawan Singh
ML ENGINEER · FOUNDER · LEICESTER, UK
> currently building velkron

Satyawan Singh

I build systems that prove things: verification for AI output, formal checks for code, receipts for machine decisions.

AI generatesoutputVerification layerchecks itTamper-evidentreceipt
loading…✓ VERIFIED
scroll ↓

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.

AI safety audits

Independent review of where a model's output is trusted without being checked, and what a real verification layer would look like.

Formal verification

Rust and z3-based proofs: panic-freedom, safety envelopes, and other properties that should be proven, not tested for.

Regulatory compliance

EU AI Act and FCA-adjacent work: provenance-gated systems, refusal-first design, and audit-ready documentation.

For teams building AI in healthcare, finance, or other regulated industries. Building Velkron full-time, so this is a small number of engagements alongside that, not a full-time practice.

Currently open to new advisory engagementsContact for scope →Browse by specialization →
See a live safety proof ↓

SIGNED CLAIMS

click verify on any card
2026
LIVE
Founder

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

sha256 —
2026
LIVE
Creator

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

RustKani
last commit 47 days ago · 61 downloads · 1 starstar on GitHub →
sha256 —
2026
OPEN SOURCE
Author

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

Python
sha256 —
2026
OPEN SOURCE
verified-safety-shieldview details →
Author

A formally-verified runtime shield that proves a robot control policy stays inside a safety envelope. Every action is checked by the z3 solver, demonstrated on a MuJoCo arm.

Pythonz3MuJoCo
sha256 —
2026
RESEARCH
MSc dissertation, University of Leicester

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

PyTorch
sha256 —
2025-26
COMPLETE
Builder

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

PyTorch
sha256 —
2026
COMPLETE
Builder

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

Python
sha256 —
2026
COMPLETE
EvaporChainview details →
Creator

A 140-crate Rust L1 blockchain with 12,950 passing tests and novel consensus-verification primitives. Build complete; research continues.

Rust
sha256 —

RUNNING DEMOS

merkle proofbuilding…

Fig. 1 — Each leaf is a claim; the root changes if any one of them does.

verified safety shieldz3 · unsat

Fig. 2 — Drag the red zone onto the path, then prove the shield keeps the arm clear.

  • Why AI needs receipts↗ velkron.xyz

    In a world where models produce confident-sounding output, the only real defense is proof, not trust. On what a tamper-evident receipt for machine output actually requires.

  • The most important sentence in the EU AI Act↗ velkron.xyz

    One requirement buried in the regulation will reshape how compliant AI systems get built. Most teams haven't read it yet.

  • Refusal is a feature↗ velkron.xyz

    When a system says it doesn't know, that's not a failure state. It's one of the few honest safety mechanisms available, and most designs actively train it out.

SHIP LOG

  • 2026-07-23Launched velkron.xyz and console.velkron.xyz. Applied to Hub71. Shipped verified-safety-shield.
  • 2026-07-21Launched cargo-vouch on crates.io.
  • 2026-07-13Published the open-source verification quartet.

CONTACT

Building Velkron full-time. I advise a small number of teams on AI verification, LLM systems and applied ML.

intent

from

message

· intent schema selected· email syntax valid· non-empty payload

manifest

timestamp
intent
payload_length
0
payload_hash

[UNSAT — incomplete]

payload_hash is a real SHA-256 of what you type, computed in your browser via crypto.subtle — nothing is sent until you commit, which opens a pre-filled email to satyawansinghinuk@gmail.com.

CONSOLE

A command-driven way to browse the same real data above. Type help to see what's available.

$