Drishti Shah

Drishti Shah @drishti_portkey

Joined:
Jun 23, 2025

Drishti Shah
articles - 60 total

Claude Code agents: what they are, how they work, and how to scale them

Claude Code is now the most widely used AI coding agent. We all know what it does. The harder...

Learn More 0 0Mar 10

LLM Deployment Pipeline Explained Step by Step

LLM deployment is the process of taking a trained language model and converting it into a...

Learn More 0 0Mar 10

The best approach to compare LLM outputs

Once LLMs are in production, output quality stops being a subjective question and becomes an...

Learn More 0 0Mar 10

Open AI Responses API vs. Chat Completions vs. Anthropic Messages API

The LLM API landscape has never been more fragmented, or more consequential. As teams move from...

Learn More 0 0Mar 10

Introducing the MCP Gateway!

Your interns need three approvals to touch production. Your AI agents? Zero. With MCP, agents can...

Learn More 0 0Jan 22

MCP tool discovery for autonomous LLM agents

Large language model agents are increasingly expected to work with real systems like files, APIs,...

Learn More 0 0Dec 29 '25

Enterprise MCP access control: managing tools, servers, and agents

MCP has moved fast. Source What started as a convenient way to plug tools into an AI workflow is...

Learn More 0 0Dec 29 '25

What is a virtual MCP server: Need, benefits, use cases

MCP adoption inside organizations has moved quickly beyond single-developer setups. What started...

Learn More 0 0Dec 29 '25

Understanding MCP Authorization

MCP makes it possible for AI models and agents to interact with external tools, APIs, and data...

Learn More 0 0Dec 29 '25

LLM routing techniques for high-volume applications

High-volume AI applications don't depend on a single model or provider. Routing steps in as the...

Learn More 0 0Dec 31 '25

LLM access control in multi-provider environments

Most organizations have already adopted a mix of AI providers and open source models. This...

Learn More 0 0Dec 29 '25

Buyer’s guide to LLM observability tools

Observability for LLM systems has evolved from a debugging utility to a business function. When AI...

Learn More 0 0Dec 29 '25

AI cost observability: A practical guide to understanding and managing LLM spend

In most organizations, model access has scaled faster than cost visibility. Teams know their total...

Learn More 0 0Dec 29 '25

Gemini 3.0 vs GPT-5.1: a clear comparison for builders

Frontier models continue to shape how teams build AI apps, agents, and multimodal systems. As...

Learn More 0 0Nov 20 '25

From standard to ecosystem: the new MCP updates, Nov 2025

When the MCP was first introduced, it aimed to solve a clear problem: LLMs, tools, and agents all...

Learn More 0 0Nov 20 '25

Claude Skills: definition, use cases, and limitations

Over the past year, we’ve seen AI assistants evolve from generic chat interfaces into structured,...

Learn More 0 0Nov 6 '25

How Snorkel evaluates and trains top AI models

When Agents go off the rails <!--kg-card-begin: html-->Examine this chart and...

Learn More 0 0Nov 17 '25

The complete guide to LLM observability for 2026

Large language models are now critical to how organizations build products, automate workflows, and...

Learn More 0 0Nov 6 '25

Portkey Named a Cool Vendor in the 2025 Gartner® Cool Vendors™ in LLM Observability Report

As AI adoption moves from experiments to production, observability has become a core part of...

Learn More 0 0Nov 6 '25

What we think of the Opentelemetry semantic conventions for GenAI traces

Portkey view of Langgraph agent traces At Portkey, observability for your applications is something...

Learn More 0 0Nov 6 '25

Comparing lean LLMs: GPT-5 Nano and Claude Haiku 4.5

Large language models are getting faster, smaller, and more specialized. The industry is no longer...

Learn More 0 0Nov 6 '25

Using OpenAI AgentKit with Anthropic, Gemini and other providers

AgentKit is OpenAI’s new framework for building and running AI agents. It includes 3 parts: *Agent...

Learn More 0 0Oct 14 '25

The most reliable AI gateway for production systems

The conversation around AI infrastructure has evolved. For teams building AI-powered products, the...

Learn More 0 0Nov 6 '25

Claude Sonnet 4.5 vs GPT-5: performance, efficiency, and pricing compared.

Claude Sonnet 4.5 and GPT-5 are the newest flagship models from Anthropic and OpenAI. Both were...

Learn More 0 1Oct 14 '25

Securing enterprise AI with gateways and guardrails

Enterprises are accelerating their adoption of generative AI, but alongside the opportunity comes...

Learn More 0 0Oct 14 '25

MCP Message Types: Complete MCP JSON-RPC Reference Guide

The Model Context Protocol (MCP) uses JSON-RPC 2.0 for all communication between clients and servers....

Learn More 0 0Sep 29 '25

Failover routing strategies for LLMs in production

If you’re running LLMs in production, you’ve seen them fail. Providers go down, rate limits kick...

Learn More 0 0Oct 14 '25

Architecting for Trust: A Strategic Perspective on the MCP Registry for the Enterprise

The recent announcement of the official MCP Registry is a significant milestone, signaling a new...

Learn More 0 0Nov 17 '25

GPT 5 vs Claude 4

When it comes to frontier AI models, two names dominate the conversation today: GPT-5 from OpenAI and...

Learn More 0 0Sep 29 '25

Simplifying MCP server authentication for enterprises

Model Context Protocol (MCP) is quickly becoming the standard way to connect AI agents with the...

Learn More 0 0Sep 29 '25