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
Learn how to build a video analysis agent in Python that extracts key frames, detects scene changes, performs temporal analysis, and generates structured summaries using vision language models.
Build a screenshot analysis agent that detects UI elements, analyzes layouts, and generates accessibility descriptions. Learn techniques for button detection, form analysis, and hierarchical layout understanding.
Create an AI agent that classifies diagram types, extracts elements and relationships from flowcharts and architecture diagrams, and converts visual diagrams into structured data and code representations.
Build an audio analysis agent in Python that classifies music genres, identifies speakers through diarization, and detects sound events. Covers audio feature extraction, classification models, and structured audio understanding.
Build a multi-input AI agent that handles user text alongside uploaded files of any format. Learn file upload handling, automatic format detection, unified processing pipelines, and how to generate contextual responses from mixed inputs.
Learn how to build computer use agents that interact with browser and desktop applications by capturing screenshots, detecting UI elements, performing click and type actions, and verifying results through visual feedback loops.
Build AI agents that generate rich multimodal outputs including images with DALL-E, speech with TTS, PDF documents, and formatted reports. Learn how to orchestrate multiple generation APIs into cohesive, multi-format responses.
Learn how to build an AI agent that connects to your inbox via IMAP and the Gmail API, classifies incoming messages by intent, and generates context-aware draft responses automatically.
