Sign in Subscribe

Drishti Shah

MCP primitives: the mental model behind the protocol

If you’ve looked at MCP servers or examples, you’ve probably seen terms like resources, tools, prompts, and roots show up repeatedly. Those aren’t implementation details. They’re the primitives MCP is built around. Understanding these primitives makes it easier to design MCP servers, reason about agent behavior,

AI audit checklist for internal AI platform & enablement teams

AI audit checklist for internal AI platform & enablement teams

A practical AI audit checklist for platform teams to evaluate access controls, governance, routing, guardrails, performance, and provider dependencies in multi-team, multi-model environments.

LLM routing techniques for high-volume applications

LLM routing techniques for high-volume applications

High-volume AI systems can’t rely on a single model or provider. This guide breaks down the most effective LLM routing techniques and explains how they improve latency, reliability, and cost at scale.

Tracking LLM token usage across providers, teams and workloads

Tracking LLM token usage across providers, teams and workloads

Learn how organizations track, attribute, and control LLM token usage across teams, workloads, and providers and why visibility is key to governance and efficiency.

LLM access control in multi-provider environments

LLM access control in multi-provider environments

Learn how LLM access control works across multi-provider AI setups, including roles, permissions, budgets, rate limits, and guardrails for safe, predictable usage.

Agent observability: measuring tools, plans, and outcomes

Agent observability:what to measure, how to trace reasoning and tool calls, and how Portkey helps teams debug and optimize multi-step AI agents in production.

Buyer’s guide to LLM observability tools 2026

A complete guide to evaluating LLM observability tools for 2026; from critical metrics and integration depth to governance, cost, and the build-vs-buy decision for modern AI teams.