Shanker Dhand.
aboutexpertiseworkwriting
LinkedInGithubX
Let's talk
← All posts

#security

4 posts tagged security.

Sep 22, 2026·5 min read

Prompt injection: defenses that work

Chunk-level allowlisting, output filtering, privilege separation for agents. Concrete defenses against retrieved-content injection, not the theory.

Sep 17, 2026·6 min read

Authentication vs authorization

Authentication is a fact you establish once. Authorization is a decision you make on every request — and that gap is where most access-control bugs live.

Sep 2, 2026·6 min read

Multi-tenant RAG: relevance is not access control

Vector search ranks by similarity, not permission. Why multi-tenant RAG leaks across tenants by default, and where the authorization check actually has to sit.

Aug 31, 2026·7 min read

Next.js 16.3 and the upgrade I stopped deferring

turbopackUseSystemTlsCerts was removed in Next.js 16.2: Turbopack now trusts OS certificates by default. Plus the two 16.3.3 security fixes: patch or migrate?

Let's talk

Hiring for AI, or building with it?

Send a message with the form or email me. Tell me what you're working on — I read everything and reply within 48 hours.

shankerdhand@gmail.com
Message me on LinkedIn

Saved to my Google Sheet so I can reply. Privacy

Shanker Dhand.

AI Engineer & Technical Lead — building AI agents, RAG pipelines, and production-grade full-stack systems.

LinkedInGithubX
© 2026 Shanker Dhand. All rights reserved.Privacy