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
Posts Tagged → anthropic
How Cloudflare Cut Its Inference Cost by 68%
TL;DR 30 sec6 min coredeep dive optional Cloudflare cut the inference cost of AI code review from $2.43 to $0.77 per review by moving one prompt cache breakpoint, deleting model calls nobody needed, and stepping models and effort down only where quality held. The cache fix alone lifted first-request cache hit rates from 14 to… Continue reading
Claude Code Changelog: September 2026 Updates That Matter
TL;DR 30 sec3 min coredeep dive optional Anthropic shipped 23 Claude Code releases in three weeks (2.1.243 through 2.1.273, August 24 to September 15 2026), and the month belongs to three stories: Fable 5.1 became the default Fable model, prompt-cache stability work touched at least ten releases, and permission deny rules were extended twice and… Continue reading
Claude Fable 5.1: What Changes for Developers
Fable 5.1 is Anthropic’s successor to Fable 5, aimed at agents that run for hours: code fixes, research passes, long knowledge work. It shipped on September 1, 2026 with the same $10 and $50 per million token list prices and one big change underneath: cache reads cost $0.25 instead of $1. This guide covers the… Continue reading
Anthropic’s Prompt Engineering Tutorial, Mapped
TL;DR 30 sec7 min coredeep dive optional Anthropic’s prompt engineering tutorial is a free 9-chapter interactive Jupyter course from the maker of Claude itself, teaching prompt structure through exercises with an example playground under every lesson, and this guide maps how to work through it in 2026. Nine chapters from basic prompt structure to industry-grade… Continue reading
MCP Course: Free Hugging Face Anthropic Track
MCP Course by Hugging Face is the official Model Context Protocol curriculum, built in partnership with Anthropic. Alex Notov, Anthropic Technical Partner Enablement Lead, co authored Unit 3. Four units plus bonus. Free. Two certificates, Fundamentals for completing Unit 1, Completion for completing Units 2 and 3. Capstone is a PR Agent Workflow Server that… Continue reading
Claude Certification Explained: The Four Exams Compared
TL;DR 30 sec5 min coredeep dive optional Claude certification is Anthropic’s paid, proctored exam program: four credentials across the Associate, Developer, and Architect tracks, priced from $99 to $175, and each one valid for 12 months. Associate Foundations costs $99 with 60 questions; Developer and Architect Foundations cost $125 with 53 and 60 questions; Architect… Continue reading
Claude API Course: Powerful Anthropic Notebooks
Claude API Course is Anthropic’s official code first curriculum at github.com/anthropics/courses, with twenty two thousand stars as of mid 2026. Five Jupyter notebook sub courses covering the Claude API fundamentals, prompt engineering interactive tutorial, real world prompting, prompt evaluations, and tool use. Free, CC BY NC 4.0 license, no certificate. Python only. Default model is… Continue reading
Anthropic Python SDK 1.0: 2026 Migration Guide
Python SDK 1.0 shipped on August 20, 2026, moving the anthropic package out of its 0.x prefix and into a stable 1.x line. This guide covers every breaking change that can touch real code, reproduces the exact errors you will hit, and walks one project through the complete upgrade from 0.125 to 1.0. Python SDK:… Continue reading