Beta · Early Access

For AI deployments in clinical and healthcare settings

Clinical AI needs evidence, not promises.

Clinical AI needs FDA-mappable evidence packages, HIPAA-compliant memory minimization, deterministic structural safety checks, and deterministic replay for any adverse event review. Most AI vendors hand-wave the compliance story.

The compliance suite ships today, including Convergence Proof PDF generation. Memory Time Machine for clinical incident review is in Beta. Healthcare design partners shape the clinical workflow.

Important — compliance evidence: /v1/check verdicts are not included in the audit trail and do not generate W3C Verifiable Credentials. For compliance-grade evidence (HIPAA, GDPR, EU AI Act, FDA 510(k), NIST AI RMF), use /v1/preflight, which produces full audit-log entries and signed W3C VCs per verdict. The /v1/check endpoint is suitable for experimentation and high-frequency agent gating only.

What works today

The compliance substrate is production-grade.

Every one of these features is in active use by Sgraal customers today.

medication

FDA 510(k) mapping

Live

/v1/compliance/fda-510k generates evidence packages mapped to the relevant FDA submission sections. Pre-Sub, traditional 510(k), and De Novo pathways all supported.

verified

Policy-rule consistency checks

Live

Our healing-policy rules pass automated logical consistency checks (e.g. no rule both allows and blocks the same case; the healing counter is monotonic). These verify policy-rule invariants — not a formal proof of each live decision.

history_edu

Deterministic clinical replay

Live

Bit-perfect replay of any historical decision with pg_override_disabled + cfg_checksum. Adverse event review reconstructs exactly what the agent knew and when.

description

W3C Verifiable Credentials

Live

Court-admissible signed compliance artefacts, returned per call for you to retain in your own audit-log system. Pairs cleanly with hospital legal review and EHR audit logging requirements.

delete_sweep

MVMem (HIPAA + GDPR)

Live

Minimum Viable Memory reduction proves the agent operated with the minimum necessary patient data. Article 5(1)(c) of GDPR plus HIPAA Minimum Necessary Rule, automated.

functions

CTL / PCTL probabilistic verification

Live

Probabilistic Computation Tree Logic for stating safety guarantees ("with probability ≥ 0.999, the agent will not recommend a contraindicated medication").

picture_as_pdf

Convergence Proof PDF

Live

Auto-generated FDA submission artefact via POST /v1/proofs/convergence: Lyapunov stability visualisation and healing trajectory plots. Output is signed and includes the engine config checksum.

⭐ See it in action

info Pre-generated sample · No signup

Download a sample Convergence Proof PDF

4-page FDA-style artefact: title page + executive summary + mathematical proof (Lyapunov V̇(x) ≤ 0) + 20-step trajectory plot + signature block. Generated by the live POST /v1/proofs/convergence endpoint with agent_id=demo.

download Download sample PDF
About this sample ▾

The PDF demonstrates Lyapunov asymptotic stability of the Sgraal heal loop for a fictitious agent_id=demo. It shows:

  • Worst-case initial state ω = 100 (theoretical maximum risk)
  • Per-step heal trajectory across 20 actions, decay rate δ = 0.35 (REFETCH)
  • Monotonic V(x) = ω²/200 decreasing to V < 0.5
  • Lyapunov exponent λ < 0 (converging trajectory)
  • Tenant signing-key fingerprint block — empty in this sample; your tenant fills it from PASSPORT_SIGNING_KEY_V1

The mathematical primitive (scoring_engine.lyapunov.compute_lyapunov) is unchanged across tenants — only the agent context and signing fingerprint vary.

What is in active development

One Beta feature for healthcare design partners.

In active development with design partner input. Not yet GA — but real, not vaporware.

history

Memory Time Machine — clinical incident review

Beta

Deterministic replay of the full decision chain leading to an adverse event, with counterfactual branching to test alternative timelines ("if memory X had been refreshed at T-3, would the harm at T have occurred?").

Status: core replay works on the test corpus. The clinical-workflow integration (EHR cross-reference, incident review export) is being shaped with design partners.

Design Partner Program

First 5–10 clinical AI teams shape the roadmap.

Early Access is not a feature flag — it is a structured program. Design partners get founder-direct access, priority on roadmap input, and locked-in pricing through the Beta period.

connect_without_contact Founder-direct access

Slack channel with the founder. No ticket queue, no AE filter. You hit a wall, you hear back same day.

route Roadmap input

Beta features ship based on what design partners actually use. The next Beta milestone is decided by the first 5–10 customers, not a marketing committee.

lock Locked-in pricing

Your Beta-period pricing is locked through general availability. If the GA tier list moves up, you stay on the partner rate for 24 months.

handshake Honest reciprocity

In return: candid feedback when something does not work, a written case study at GA (with your approval and disclosure terms), and a willingness to live with Beta-grade rough edges.

Apply to the program →

No NDA required to apply. We respond within 48 hours.

Beyond Beta

Where this is heading.

Autonomy Graduation Certificate

Concept

A formal safety case (Concept) that a clinical AI agent is safe enough to operate at a higher autonomy tier (e.g., move from human-in-the-loop to human-on-the-loop). Combines Lyapunov stability, policy-consistency checks, and outcome statistics.

More on the long-term direction →
info

Honest disclosure: what works today, what is beta.

  • Today (Live): FDA mapping, policy-consistency checks, deterministic replay, W3C VCs, MVMem (HIPAA + GDPR), PCTL probabilistic verification, Convergence Proof PDF generation — all in production.
  • Beta: Memory Time Machine for adverse event review. Works in test environments. Clinical-workflow integration shaped with design partners.
  • Concept: Autonomy Graduation Certificate. Long-horizon — research direction, not committed roadmap.

Tier badges across the page surface this distinction. No category was glossed over.

Five to ten design partners. That is the cohort.

If you are a clinical AI teams and want to shape what comes next, write us. If you would rather wait for GA, the page is here when you are ready.