Production Guides
LLMs in Prod 2025: Insights from 2 Trillion+ Tokens
Real-world analysis of 2Trillion+ production tokens across 90+ regions on Portkey's AI Gateway. Get the full LLMs in Prod'25 report today.
Latest
AI Agents
What are AI agents?
AI agents are software programs designed to sense their environment, make decisions, and take actions independently. They can operate and adapt in various settings - from physical spaces to digital environments. Unlike AI models that simply process inputs to generate outputs, agents continuously interact with their surroundings through an ongoing
Conversations
Jamming on Event-Driven Architecture and MCP for Multi-Agentic Systems
Insights from Portkey's AI Practitioners Meetup on building scalable multi-agent systems. Learn about Event-Driven Architecture patterns, Model Context Protocol implementation, and real-world experiences building multi-agents system.
ai guardrails
Reducing AI hallucinations with guardrails
Your chatbot just told a user that Einstein published his Theory of Relativity in 1920. Sounds plausible, right? Except it happened in 1915. This isn't a rare glitch - A recent study revealed 46% of users regularly catch their AI systems making up facts like these, even with
ai guardrails
What are AI guardrails?
Learn how to implement AI guardrails to protect your enterprise systems. Explore key safety measures, real-world applications, and practical steps for responsible AI deployment.
LLM Gateway
The real cost of building an LLM gateway
When your AI apps start to scale, managing multiple LLM integrations can get messy fast. That's when teams usually realize they need an LLM gateway. Many developers jump straight to building their own solution, often without seeing the full picture of what's involved. Drawing from what
observability
LLM observability vs monitoring
Your team just launched a customer service AI that handles thousands of support tickets daily. Everything seems fine until you start getting reports that the AI occasionally provides customers with outdated policy information. The dashboard shows the model is running smoothly - good latency, no errors, high uptime - yet
paper summaries
Multi-LLM Text Summarization
The paper introduces a novel framework called Multi-LLM for text summarization, which leverages multiple large language models (LLMs) to generate better summaries, especially for long documents. This framework is designed to overcome the limitations of using a single LLM, which might fail to captur
paper summaries
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference - Summary
<p>The research paper introduces <strong>ModernBERT</strong>, an updated version of the original BERT model, which is an encoder-only transformer designed to improve retrieval and classification tasks. Despite the original BERT's widespread use, until now, there have been limited improvements in te
prompt engineering
What is tree of thought prompting?
Large language models (LLMs) keep getting better, and so do the ways we work with them. Tree of thought prompting is a new technique that helps LLMs solve complex problems. It works by breaking down the model's thinking into clear steps, similar to how humans work through difficult
chain-of-thought prompting
Prompt engineering techniques for effective AI outputs
Remember when prompt engineering meant just asking ChatGPT to write your blog posts or answer a basic question? Those days are long gone. We're seeing companies hire dedicated prompt engineers now - it's become a real skill in getting large language models (LLMs) to do exactly
Top 10 MCP Servers
Anthropic recently launched Model Context Protocol - a standardized protocol that governs how models can interact with local and remote sources Here's a list of production-ready and experimental MCP servers you can access for database connections, cloud, and infra, Content, productivity tools, etc. Data and storage MCP server