Step-by-step tutorials on building voice and chat AI agents using OpenAI Agents SDK, Realtime API, function calling, multi-agent orchestration, and production deployment patterns.
9 of 1313 articles
Build multi-modal agents that process images, PDFs, and diagrams using Claude's vision capabilities. Learn how to send image data via the API, analyze documents, and combine vision with tool use.
Implement real-time streaming with Claude for responsive agent UIs. Learn how to handle stream events, process content_block_delta tokens, manage partial tool calls, and build streaming agent loops.
Cut Claude API costs by up to 90% with prompt caching. Learn how to use cache_control breakpoints, design cache-friendly prompts, and measure cost savings in production agent systems.
Build multi-agent systems using the raw Anthropic API without any framework. Learn patterns for routing, delegation, result aggregation, and inter-agent communication using plain Python and Claude.
Compare Claude and GPT-4 for building AI agents. Understand API differences, capability trade-offs, cost structures, and get a practical migration guide for switching between platforms.
Use Claude's Batch API to process thousands of agent tasks at 50% reduced cost. Learn how to create batches, poll for completion, retrieve results, and design batch-friendly agent workflows.
Learn how to install Ollama, pull Llama models, serve them through OpenAI-compatible endpoints, and integrate local LLMs into your AI agent pipelines for private, cost-free inference.
Set up vLLM for production-grade LLM inference with PagedAttention, continuous batching, and OpenAI-compatible APIs. Learn performance tuning for serving open-source models at scale.
