Blog

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

All posts engineering performance transparency okta scim identity-provider announcement comparison security rag enterprise industry compliance legal reference-architecture 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 went looking for the benchmark behind our own published latency figure and could not find one. Measuring properly started at 302ms p95, surfaced three product bugs, and ended at a public, reproducible 16ms p50 / 21ms p95.

engineering performance transparency

Read full article →

Ready to secure your AI retrievals?

Get started with Gateco in minutes. Free tier includes 1,000 secured retrievals per month.

Get started Read the docs