How we scale models. Without scaling the harm.
Scaling model capability has to be paired with scaling our ability to red-team, disprove, and govern. We scale only when the safety posture scales with the capability. This page is the public framework.
Four safety levels. Each with required controls.
SL-1 — Bounded inline
Lion-class (15B)Served through Safeguard's API over TLS, scoped to your tenant. No exfiltration paths beyond the selected code sent for analysis. Deployable from the IDE extension and CLI with no model weights installed.
SL-2 — Multi-tenant cloud
Eagle 70BMulti-tenant inference; structured trace contract; per-tenant audit log; standard adversarial-resistance gate (≥0.94 prompt-injection block-rate).
SL-3 — Dedicated reasoning
Griffin 750B · single-tenant clusterSingle-tenant inference cluster; advanced adversarial-resistance gate (≥0.97); coordinated-disclosure obligations; quarterly red-team rotation; structured-trace human audit on 300 samples per release.
SL-4 — Sovereign deep reasoning
Griffin 750B · air-gapped or VPC-isolatedAir-gapped or VPC-isolated. Full red-team + manual trace audit per release. Customer-controlled key material. ITAR/export-control review. Adversarial-resistance ≥0.99.
What triggers a re-tier.
If safety regresses, the tier ceiling lowers. The model continues to ship — but at the lower safety level — until the posture catches up. The triggers:
- Adversarial-resistance regression > 0.5% on the held-out suite
- Hallucination-rate regression > 0.1% on the security-Q&A eval
- Refusal-rate regression > 5% on legitimate-research prompts
- Novel jailbreak class observed in MCP-server traffic or red-team logs
- Customer-facing safety incident attributed to model behaviour
- External regulatory or sectoral requirement change affecting deployment posture
How we govern this.
Internal safety review board
Weekly review of red-team findings, eval regressions, and customer safety reports. Membership rotates across engineering, research, and security.
External red-team partners
Quarterly rotation of independent red teams with sector-specific specialisations (offensive security, prompt injection, AI safety).
Public RSP commitments
This page is the public commitment. Updated quarterly. Material changes flagged on the changelog.
Independent audit
Annual third-party audit of the eval methodology, the corpus curation, and the release pipeline. Summary published in the transparency report.
Talk to us about the safety posture.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.