Reading Series
Reading series for anyone who would rather follow a subject from start to finish than search the blog post by post. Each series grows as new posts are published.
Claude Code & Autonomous Coding Agents Guide
Terminal-based coding agents, subagent architecture, memory management and engineering workflows for teams.
Latest posts
- The Era of Automatic Setup in Claude Code Cloud Sessions: Dependencies and API Keys Are Now Managed Autonomously
- Anthropic Announces a New Analytics System to Measure the Return (ROI) on Claude Code Spending
- Anthropic Report: Junior Staff Share Falls While Time Spent in Meetings Rises
- Claude Code Mods Announced: A Customizable Agent Architecture with TypeScript
Model Context Protocol (MCP) & Tool Integration
A guide to the standard protocol that connects large language models to databases, APIs and local developer tools.
Latest posts
- Google AI Studio Is Preparing a New 'Managed Agents' Hub for Autonomous Workflows
- NVIDIA Makes the Run:ai Kubernetes GPU Orchestration Platform Fully Open Source
- xAI Announces Grok Voice 3.0: The Next-Generation Voice Model Handling Millions of Conversations at Tesla and Starlink
- Setting Up an OpenAI-Compatible Coding Agent With the Kimi API (Node.js / Python)
Autonomous AI Agents Architecture
Multi-agent orchestration, tool calling, safety boundaries and running agents in production.
Latest posts
- The Era of Automatic Setup in Claude Code Cloud Sessions: Dependencies and API Keys Are Now Managed Autonomously
- Neuralink Connects the Human Brain to AI: Grok Can Now Be Controlled by Thought
- Google Announces Gemini 4 Carbon: A New Peak in Cybersecurity and Autonomous Coding
- Google AI Studio Is Preparing a New 'Managed Agents' Hub for Autonomous Workflows
RAG & Vector Database (pgvector) Engineering
Document chunking, embedding models, hybrid search and Retrieval-Augmented Generation in practice.
Latest posts
Prompt Engineering & Context Optimization
System prompts, structured output, preventing hallucinations and prompt security techniques.
Latest posts
AI Model Comparisons & Benchmark Analyses
Coding, reasoning and cost/performance comparisons of Claude, GPT, Gemini, DeepSeek and open-weight models.
Latest posts
- DeepSeek V4.1-Flash Refreshed: How the Best Open Model Became Even Stronger and More Efficient
- DeepSeek V4.1-Flash-1017 Benchmarks and Agent Ecosystem: The Terminal-Bench 4.0 Leap
- Jev vs AWS Strands Decider 2B: Which Decision Model Should You Choose?
- Jev vs Traditional LLMs: Latency and Cost Comparison for Decision Models
This week’s posts, in your inbox every Monday
A short summary of the posts published that week on AI, Claude Code, MCP and web development. No new posts, no email.
- One email a week
- No ads
- One-click unsubscribe
Can't find your subject in a series? Browse all topics or the blog.