Is Scality ADI fully autonomous?

No. Scality is explicit that ADI is not completely autonomous. Its Guardian agents surface insights and recommend actions, but a human operator or the customer's own AI tooling must approve consequential transitions, and the platform then executes within auditable policy bounds rather than acting unsupervised.

How does ADI differ from AWS S3 Intelligent-Tiering?

AWS S3 Intelligent-Tiering moves objects between access tiers automatically with no per-transition approval, optimizing for hands-off operation. ADI keeps a human-in-the-loop approval gate before transitions, trading slightly slower reaction on transient events for protection against an agent misclassifying active workloads as cold.

What is the 5/30/65 distribution Scality recommends?

Scality suggests placing roughly 5 percent of data on the top performance tiers, 30 percent on the warm tier, and 65 percent on the cold tier, framed around power sustainability. It ties placement to real datacenter power draw via telemetry rather than to abstract per-gigabyte cost rules.

How does ADI protect backups against ransomware?

Through CORE5 cyber-resilience and standard S3 object lock. In the Somerville deployment, Veeam writes backup data to Scality RING over the S3 API and it is protected with object lock on write, so the object cannot be modified or deleted for its retention window. Riding the native S3 API avoids a proprietary gateway becoming a restore bottleneck.

Does ADI support Nvidia's STX KV Cache scheme?

Not at launch. Blocks & Files notes ADI does not currently support Nvidia's STX KV Cache, though Scality is expected to add support later. If KV-cache offload is on your roadmap, treat its arrival as a timeline question to raise with Scality directly before committing.

Scality ADI Keeps a Human in the Loop, and That Is the Point

Tue, 12 May 2026 00:00:00 +0000

The last time a tiering policy ran fully autonomous on a cluster I managed, it did exactly what it was told: it saw a feature store go cold over a quiet weekend and moved 4 TB of it to the archive class. Monday morning, a training job that expected that data on fast storage stalled for forty minutes while it rehydrated. The policy was not wrong. It was just unsupervised. That stall is why I read past the headline when Scality launched its Autonomous Data Infrastructure platform on 12 May 2026.

Four on StorageNews

Scality ADI Keeps a Human in the Loop, and That Is the Point