What is LLM tool calling, and how does it work?
Explore how LLM tool calling works, with real examples and common challenges. Learn how Portkey helps tool calling in production.
Latest
Geo-location based LLM routing: Why it matters and how to do it right
As LLM-powered applications scale across global markets, user expectations around performance, reliability, and data compliance are higher than ever. Enterprises now prefer geo-location-based routing. Whether it's reducing latency, staying compliant with regional data laws, or optimizing infrastructure costs, geo-routing ensures your AI workloads are not just smart, but
LLMOps
Task-Based LLM Routing: Optimizing LLM Performance for the Right Job
Learn how task-based LLM routing improves performance, reduces costs, and scales your AI workloads
Production Guides
Beyond the Hype: The Enterprise AI Blueprint You Need Now (And Why Your AI Gateway is Non-Negotiable)
The Gen AI wave isn't just approaching—it's already crashed over every industry, leaving enterprises to navigate the aftermath. As a CTO or CIO, you've moved past the demos and proofs-of-concept. The questions keeping you up at night are now existential: How do we
LLMOps
Canary Testing for LLM Apps
Learn how to safely deploy LLM updates using canary testing - a phased rollout approach that lets you monitor real-world performance with a small user group before full deployment.
AI ethics
Ethical considerations and bias mitigation in AI
Discover how to address ethical issues through better data practices, algorithm adjustments, and system-wide governance to build AI that works fairly for everyone.
AI FinOps
FinOps chargeback and how it can help GenAI platforms
Learn how FinOps chargeback helps AI teams control GenAI platform costs by linking expenses to specific teams.
prompting
Prompting Claude 3.5 vs 3.7
Claude models continue to evolve, and with the release of Claude 3.7 Sonnet, Anthropic has introduced several refinements over Claude 3.5 Sonnet. This comparison evaluates their differences across key aspects like accuracy, reasoning, creativity, and industry-specific applications to help users determine which model best fits their needs. đź’ˇPrompt
MCP
Benefits of using MCP over traditional integration methods
​Discover how the Model Context Protocol (MCP) enhances AI integration by enabling real-time data access, reducing computational overhead, and improving security.
prompting
Basic AI Prompts for Developers: Practical Examples for Everyday Tasks
Ready-to-use prompts that developers can integrate into their daily workflows, tested using Portkey's Prompt Engineering Studio
prompting
Accelerating LLMs with Skeleton-of-Thought Prompting
A comprehensive guide to Skeleton-of-Thought (SoT), an innovative approach that accelerates LLM generation by up to 2.39Ă— without model modifications. Learn how this parallel processing technique improves both speed and response quality through better content structuring.
design
Portkey Prompt Engineering Studio User-Centered Design Case Study
Crafted with thoughtful design, our Prompt Engineering Studio empowers users to create, refine, and optimize prompts effortlessly, blending usability with innovation.