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 to build an AI agent that recognizes hand-drawn diagrams on whiteboards, classifies shapes and connections, and generates working code including Mermaid diagrams, database schemas, and API stubs.
Learn how to build AI agents that perform causal reasoning using causal graphs, interventions, and counterfactual analysis — moving beyond pattern matching to genuine understanding of cause and effect.
Understand how Claude's computer use tool works under the hood — the screenshot-action feedback loop, the coordinate system, supported actions, and how to integrate it via the Anthropic API.
Build a Claude-powered form automation agent that detects fields, maps data intelligently, handles validation errors, and navigates multi-step form wizards — all through visual understanding instead of DOM selectors.
A detailed comparison of Claude Computer Use and Playwright for browser automation — covering reliability, speed, cost, maintenance burden, and when to use a hybrid approach combining both.
Use Claude Computer Use to read PDFs rendered in browser viewers — navigating pages, extracting text and tables, detecting annotations, and converting visual PDF content to structured data without file downloads.
Build an end-to-end code generation pipeline using five specialized AI agents — Planner, Coder, Reviewer, Tester, and Deployer — with complete handoff data structures and orchestration logic in Python.
Reduce GPT Vision API costs by 60-80% through image resizing, compression, region cropping, intelligent caching, and token-aware strategies. Essential techniques for production vision-based browser automation.
Build a multi-agent debate system where pro and con agents construct opposing arguments while a judge agent evaluates quality, driving convergence toward more accurate and nuanced answers.
