AI Runtime Assurance
See what your AI is doing.
Stop the bad stuff. Prove it.
Benchmark your AI systems with autoredteam for free. Enforce safety policies at runtime with Glacis Enforce.
autoredteam
Point at any AI endpoint. You don’t need to know what good looks like — autoredteam discovers your baseline, you refine it. Behavioral assessment in minutes.
pip install glacis-autoredteam
- • Toxicity, hallucination, prompt injection, PII leakage, jailbreak resistance
- • Version-pinned scores — compare across runs and models
- • OVERT-compatible evidence receipts from day one
- • Apache 2.0 · CLI + Python SDK
Enforce — AI Safety Guardrails
Runtime monitoring, enforcement, and evidence for every AI system you deploy.
Continuous drift detection
A purpose-built Small Language Model runs locally, producing version-pinned behavioral scores on every sampled inference. CUSUM-based statistical analysis detects when behavior is changing — before it crosses a policy boundary. This isn’t an LLM-as-judge. It’s a calibrated measurement instrument.
Runtime enforcement
Deployed in your environment. Every AI request is evaluated against your safety policies — permit, deny, or escalate. Detects prompt injection, PHI/PII exposure, and encoding attacks. Single-digit millisecond latency. Start in observe mode, switch to enforcement when ready.
Fleet visibility
One dashboard for every AI system you’re running. Centralized policy management, drift alerts, incident integration. See which AI systems are behaving, which are drifting, which triggered enforcement actions.
Zero egress
Everything runs inside your environment. Protected content never leaves your cluster. Only cryptographic hashes cross the wire. This is architectural, not contractual — even a full compromise of GLACIS infrastructure cannot expose your data.
Evidence accumulates
While you use Enforce for operational security, OVERT-format attestation receipts build up in your environment. When compliance frameworks become relevant — NIST AI RMF, ISO 42001, EU AI Act, Colorado AI Act — the evidence trail is already there. No retroactive scramble.
Transparent pricing, built for scale
autoredteam
Open-source behavioral assessment. Point at any AI system, get a report in minutes.
Starter
Real-time safety enforcement, basic attestation logging, drift alerts. Up to 10K events/mo.
See what your AI is doing and stop the bad stuff. Today.
Pro
Full custom safety policies, advanced behavioral analysis, Glacis Score, fleet dashboard, compliance framework mapping, evidence exports. 100K events/mo.
Prove it to your board. Every interaction attested.
Enterprise
Unlimited volume, custom policies, advanced drift analysis, fleet-wide threat sharing, dedicated support.
Your defenses improve overnight. Automatically.
Every paid tier includes: local deployment, behavioral evaluation, drift detection, observe-first mode, verifiable evidence receipts, and direct engineering support during onboarding.
Not sure which tier fits? Grab 25 minutes with us — no pitch, just scoping.
Notary — Cryptographic Proof
Every decision on GLACIS infrastructure gets a cryptographic receipt — by default, not by upgrade. Third-party witnessed, tamper-evident, independently verifiable. Proof builds itself while you work. The paid layer is turning those receipts into regulator-, auditor-, and carrier-ready Evidence Packs.
- • OVERT-conformant attestation receipts
- • Compliance evidence exports: NIST AI RMF, ISO 42001, EU AI Act, OSCAL
- • Audit-ready Evidence Packs & Glacis Score
- • Enterprise: dedicated account engineering, SLA, BAA
See full feature comparison
| autoredteam Free |
Starter $49/mo |
Pro $499/mo |
Enterprise Custom |
|
|---|---|---|---|---|
| Visibility | ||||
| Scan any AI endpoint | ✓ | ✓ | ✓ | ✓ |
| Standard adversarial probes | ✓ | ✓ | ✓ | ✓ |
| Risk scoring | ✓ | ✓ | ✓ | ✓ |
| Zero data egress | ✓ | ✓ | ✓ | ✓ |
| Enforcement | ||||
| Basic policy controls | — | ✓ | ✓ | ✓ |
| Drift detection & alerts | — | ✓ | ✓ | ✓ |
| Real-time enforcement (permit/deny/escalate) | — | ✓ | ✓ | ✓ |
| Standard safety evaluation | — | ✓ | ✓ | ✓ |
| Advanced behavioral drift analysis | — | — | ✓ | ✓ |
| Deep drift replay & root cause | — | — | — | ✓ |
| Full custom policy definition | — | — | ✓ | ✓ |
| Fleet dashboard | — | — | ✓ | ✓ |
| Events/mo | — | 10K | 100K | Unlimited |
| Single-digit ms latency | — | ✓ | ✓ | ✓ |
| Evidence & Proof | ||||
| OVERT-format receipts | ✓ | ✓ | ✓ | ✓ |
| Notary receipts (every decision witnessed) | — | ✓ | ✓ | ✓ |
| Framework mapping (NIST, ISO 42001, EU AI Act) | — | — | ✓ | ✓ |
| Glacis Score | — | — | ✓ | ✓ |
| OSCAL export / evidence bundles | — | — | ✓ | ✓ |
| Independent witness verification | — | — | — | ✓ |
| Herd Immunity overnight hardening | — | — | — | ✓ |
| Dedicated support & BAA | — | — | — | ✓ |
Where do I start?
“Is my AI doing what I think it’s doing?”
Find out in five minutes. autoredteam discovers your baseline — no setup, no assumptions, no commitment. pip install glacis-autoredteam
“Is it still doing it — and can I control it?”
That’s Enforce. Continuous drift detection and runtime enforcement for every AI system in production. Starts at $49/mo. Explore Enforce
“Can I prove it — to someone who doesn’t trust me?”
That’s Notary. Every decision on GLACIS is witnessed and receipted by default. Turn those receipts into regulator-, auditor-, and carrier-ready Evidence Packs with any paid plan. See Evidence Packs
Pricing FAQ
Is autoredteam really free?
Yes — fully open-source under the Apache 2.0 license. Clone the repo, run it against your models, and keep the results. No sign-up, no usage limits, no catch. It’s the front door to the GLACIS ecosystem.
How is Enforce priced?
Monthly, based on event volume. Starter begins at $49/mo for up to 10K events — low enough for a CTO to expense without procurement. Pro begins at $499/mo for up to 100K events with full Notary attestation and Glacis Score. Enterprise is custom for unlimited volume. Grab a quick call — we’ll help you figure it out.
What is OVERT?
OVERT — Observable Verification Evidence for Runtime Trust — is our open evidence standard: a machine-readable format for AI governance receipts. Every GLACIS tool, from autoredteam to Notary, emits OVERT-compatible evidence. Compliance proof starts accumulating from the moment you start using any tool.
We already use Vanta/Drata. Do we need GLACIS?
Vanta and Drata document that you have policies. GLACIS proves you followed them at runtime. They’re complementary — together they close the AI evidence gap. See the Drata comparison →
Ready to protect your AI systems?
25 minutes, no pitch deck. We’ll map your AI systems and tell you what we’d monitor.