Strategies for managing multi-agent collaboration and communication. — agents, Agents SDK, agentic, tool calling
A guide on best practices for running AI applications in production, with tips on cost management, latency optimization, security and compliance.
Prompt engineering with few-shot prompting, message formatting, and more.
Introduces the process and benefits of distilling larger models into smaller ones. — distillation
Provides techniques to speed up API calls and model execution. — latency, cost, performance
Covers techniques like RAG to improve model reliability. — latency, cost, performance
Shows how evaluations can guide successful product launches. — evals
Outlines approaches to ensure safe and reliable agent behavior. — agents, Agents SDK, agentic, tool calling, guardrails, safety
Explains grader types and how to score model outputs. — evals
Offers strategies to reduce expenses without sacrificing quality. — latency, cost, performance
Shows how agents can call tools to accomplish tasks. — Responses API, function calling, Agents SDK, agentic, tool calling
Explains how to configure and run evaluations with the Evals API. — evals
Guidance on planning, running, and iterating on evaluations. — evals
Shows how agents can call tools to accomplish tasks. — Responses API, function calling, Agents SDK, agentic, tool calling
Shares strategies for achieving the right trade-offs between quality, performance, and expenses. — latency, cost
Walkthrough for configuring and running your first agent. — agents, Agents SDK, agentic, tool calling
Human in the loop demo of a customer service support agent built with Responses API.
Building realtime (speech to speech voice) agents with OpenAI, for example for customer service use cases.
Steps and best practices for model fine-tuning.
Explains architecture and setup for realtime voice agents. — Agents SDK, agentic, tool calling, streaming, low latency, speech, audio