Blog

Insights on AI retrieval security, RAG authorization, and data governance.

All posts security rag industry architecture engineering performance transparency okta scim identity-provider announcement comparison enterprise compliance legal reference-architecture policy product eu-ai-act regulation gcp getting-started rebac agents authorization ai-security postgres api-keys multi-cloud azure aws vertex-ai identity retrieval search launch technical integration tutorial financial-services healthcare saas

LatestAugust 23, 20268 min read

Our Site Said "<25ms Overhead." We Could Not Prove It. Measuring Found Three Bugs.

We looked for the benchmark behind our own latency figure and found none. Measuring properly started at 302ms p95 and ended at a public 16ms p50 / 21ms p95.

engineering performance transparency

Read full article →

Ready to secure your AI retrievals?

Get started with Gateco on the Free tier: 1,000 secured retrievals per month.

Get started Read the docs