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

#llm

3 posts tagged llm.

Aug 22, 2026·11 min read

MCP's 2026-07-28 spec broke my tool-calling setup

Model Context Protocol's 2026-07-28 spec ships a stateless core, drops Roots, Sampling, and Logging, and hardens auth to OAuth 2.0 — what to migrate first.

Aug 21, 2026·5 min read

Chunking strategies for RAG, and when each one bites you

Fixed-size, semantic, and structure-aware chunking all look fine in a demo. Here's how each one actually fails once real documents hit your production pipeline.

Apr 22, 2026·3 min read

A production RAG checklist (the boring half)

What separates a working RAG demo from a production RAG system isn't the retrieval — it's the evaluation, observability, and failure-mode handling around it.

Shanker Dhand.

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

shankerdhand@gmail.com
LinkedInGithub

Let's connect.

Tell me about what you're building — a problem, a project, or a role. I read everything and respond within 48 hours.

© 2026 Shanker Dhand. All rights reserved.