Developer tools, frameworks, APIs, and tutorials — 2359 articles
MarkTechPost · May 24
Complete walkthrough for setting up Langfuse tracing, prompt management, scoring, and experimentation with mock or real LLMs. Covers RAG pipeline instrumentation, evaluation scoring, and dataset-drive
Analytics Vidhya · May 24
Guide to building a Claude-based browser agent using Playwright MCP in Claude Desktop that automates form filling, data extraction, and UI interaction without relying on screenshots. Shifts from chat-
MarkTechPost · May 24
Microsoft Research released Webwright, an open-source web agent framework that replaces click-trace automation with Playwright code generation. The agent writes and refines scripts in a terminal envir
Dev.to · May 24
Engineering team replaced hand-tuned prompts with an eval harness that autonomously tested 25 algorithm variants and shipped the best one. The pattern flips the usual prompt-engineering workflow: defi
Dev.to · May 24
A runtime silently failed while dashboards reported green, exposing gaps between what monitoring shows and what's actually running. The author walks through the failure chain and what signals they sho
Brave Discovery · May 24
Claude Code v2.1.149–v2.1.150 shipped with a new `/usage` command that breaks down token consumption by sub-agent, plugin, and MCP server; a critical PowerShell permission bypass fix; and a macOS find
Dev.to · May 24
Frontend engineer shares his Cursor + Claude workflow for shipping React 3x faster, mixing IDE shortcuts with Claude for design decisions and debugging.
Brave Discovery · May 24
Sundar Pichai told Hard Fork that Google's models trail Claude Code and Cursor in agentic coding and tool use because Google lacked the right product surface to gather feedback loops. Google is now us
Towards Data Science · May 24
Step-by-step walkthrough for building AI agents in Python from scratch—useful for engineers getting started with agentic workflows but lacks specific framework details or real-world complexity pattern
Brave Discovery · May 24
Over a six-week stretch in spring 2026, OpenAI rebuilt what its Codex product actually is. On April 16, the company released a major Codex update titled “Codex for (almost) everything,”
MarkTechPost · May 23
Tutorial walks through building a SuperClaude Framework wrapper on top of Anthropic's API to create stateful multi-agent workflows with role-specific system prompts, session memory, and chained develo