Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Learn how Microsoft UFO's experience learning system stores successful task executions, retrieves relevant past patterns for new tasks, and optimizes performance through memory-based action prediction.
Explore how UFO captures, annotates, and sends Windows application screenshots to GPT-4V for UI element detection, control identification, and intelligent action mapping at each automation step.
Understand when to use Microsoft UFO for Windows desktop automation versus browser tools like Playwright or Selenium, with use cases for legacy apps, native software, and hybrid approaches.
Learn how to build a video analysis agent that samples frames intelligently, detects and tracks objects across time, classifies events, and generates structured timelines for surveillance, sports, and content analysis applications.
Build a complete screenshot-action loop where GPT-4V analyzes web pages, decides where to click, and navigates autonomously. Learn coordinate extraction, click targeting, and navigation decision-making.
Implement visual regression testing using GPT Vision to detect UI changes, classify their severity, and generate human-readable reports. Move beyond pixel-diff tools to semantic understanding of visual changes.
Anthropic shipped persistent memory to every Claude tier in March 2026, with siloed Projects memory and a public-beta Managed Agents memory tool.
LiveKit Cloud is the most-deployed managed SFU for AI voice in 2026. Here is what we learned shipping it next to OpenAI Realtime across CallSphere's six verticals.
Stream microphone audio from a browser to FastAPI, fan out to OpenAI Realtime over WebSocket, and play model audio back — full Python tutorial with PCM16 24kHz.
