Hands-on tutorials for Claude Code, AI agents, cloud and system design
An MCP server is a program that provides context to an AI application through the Model Context Protocol. It exposes tools, data and prompt templates over a standard interface, so any client that speaks the protocol can use it without custom integration work on either side. MCP server: What You’ll Learn This guide defines what… Continue reading
TL;DR 30 sec3 min coredeep dive optional oncall-kit is Anthropic’s open starter kit that mines your team’s incident history into triage playbooks for a Claude-assisted on-call, with a human signing off at every phase before anything goes near production. Setup reads 30 to 90 days of pager history, alert threads, and postmortems, then drafts one… Continue reading
TL;DR 30 sec3 min coredeep dive optional The OpenAI Agents SDK turns a production-shaped agent into about six lines of Python, and version 0.22, released August 19, 2026, hardens the runtime bits you will care about in week one: guardrail redaction, error surfacing, and a cleaner provider config contract. Install is pip install openai-agents on… Continue reading
TL;DR 30 sec3 min coredeep dive optional Agentic Resource Discovery (ARD) is an open specification, at v0.91 as of August 26, 2026, that lets AI clients find agents, MCP servers, skills, and APIs by searching them the way a search engine finds pages, instead of hardcoding each one in advance. The spec comes from authors… Continue reading
TL;DR 30 sec5 min coredeep dive optional Agent Skills is Addy Osmani’s MIT-licensed pack of 25 production-grade engineering skills that make AI coding agents write specs, run tests, review changes, and check security instead of skipping all four. 100,390 stars and 10,547 forks since its first commit in February 2026, and the repo accepted a… Continue reading
TL;DR 30 sec6 min coredeep dive optional Computer-use tools now cover five practical control surfaces for an agent: a $7 hardware rig, a classifier loop at $0.0002 a step, disposable VM desktops, open weights trained for screens, and terminal control with no screen at all. A $7 ESP32-S3 board drives a real iPhone, with AirPlay… Continue reading
TL;DR 45 sec5 min coredeep dive optional Scion is the source-control system Anthropic built when agents pushed its monorepo past 30,000 merges a day. It trades git’s distributed design for one authoritative server, a write-ahead changeset log, and review tooling built for machine-scale concurrency. Merges grew from roughly 2,500 a day in May 2026 to… Continue reading
AI agents are one of the most transformative developments in modern technology. Unlike static chatbots that simply answer questions, AI agents can plan, reason, take actions, and complete multi-step tasks with minimal human intervention. In this beginner-friendly guide you will learn exactly what AI agents are, how they work, and how you can start using… Continue reading
TL;DR 30 sec6 min coredeep dive optional Loop engineering, graph engineering, and harness engineering name the three layers you can actually tune when an agent misbehaves: the loop the model drives turn by turn, the graph that constrains which paths exist, and the harness that keeps the whole thing fed, budgeted, and observable. Anthropic’s own… Continue reading