#Agentic development
674 related articles
·3 min
Claude Sonnet 5 Deep Dive: Impressive Benchmarks, Disappointing Reality — Stick with OPUS 4.8
Anthropic's Claude Sonnet 5 claims near-OPUS 4.8 performance at lower cost. Real-world tests reveal hidden tokenizer costs, weak creative output, and only 13th place on Cursor rankings.
Read more →
·6 min
The Evolution of Claude Code: From Manual Review to 65% Fully-Automated PRs
Anthropic engineers reveal Claude Code's 18-month evolution: system prompt cut by 80%, 65% of PRs shipped automatically by AI, Claude Tag collaboration, and the safety logic behind auto mode.
Read more →
·5 min
The Complete Claude Code Guide: Installation, Core Features, and Advanced Workflows
An in-depth guide to Anthropic's Claude Code agentic coding tool, covering installation, pricing plans, model selection, token management, CLAUDE.md global memory, MCP integration, Subagents, and more.
Read more →
·4 min
UK Sovereign AI: How Cosine AI Is Punching Above Its Weight Against American Compute Dominance
Cosine AI founder reveals how the UK's first sovereign LLM is being built — from government compute grants and RL credit attribution to multi-agent orchestration and synthetic data pipelines.
Read more →
·3 min
Jetson Edge AI Development: Setting Up a VS Code + Claude Code Workstation
Set up an AI coding workstation on NVIDIA Jetson using VS Code + Claude Code. Covers JetPack NVIDIA Skills, token budget management, headless SSH dev, and coding agent best practices.
Read more →
·2 min
New Lighthouse Audit: Getting Your Website Ready for AI Agents
Starting with Chrome 150, Google's Lighthouse introduces an Agentic Browsing audit checking Accessibility Tree structure, WebMCP schema validity, and CLS to help developers assess AI agent readiness.
Read more →
·3 min
Opal: A Designer Built an AI Pet Assistant on Raspberry Pi Using OpenClaw
Microsoft designer Tua Nguyen built Opal, an AI rabbit assistant on Raspberry Pi using OpenClaw — capable of browsing the web, finding recipes, and operating GitHub.
Read more →
·3 min
Five Major AI Stories: Model Failures, Data Leaks, and Capital Concentration
GPT-5.6 deletes files, Grok leaks codebases, DeepSeek's founder hits $36B net worth — five AI stories reveal deepening safety risks and capital concentration.
Read more →
·3 min
Claude Code Practical Guide: Environment Setup, Git Workflows, and Engineering in Production
A complete guide to Claude Code: environment setup, switching to domestic LLMs, CLI commands, Git workflows, MCP, Subagents, and enterprise project walkthroughs.
Read more →
·2 min
OpenAI Codex Parallel Tasks in Practice: How to Run Multiple AI Coding Tasks Simultaneously
How OpenAI Codex Cloud runs multiple tasks in parallel using isolated containers, async workflows, and PR review. A practical guide to agentic coding efficiency.
Read more →
·2 min
Vibe Coding in Practice: From Idea to Real Product — No Coding Required
Vibe Coding is an AI-driven development paradigm that requires no coding skills. Use natural language to guide AI through design, development, and testing. Learn the 4-step workflow using Gemini, Figma Make, and Claude Code.
Read more →
·3 min
OWASP Agentic Security Top 10 Deep Dive: Understanding ASI01–ASI10 Risks and Mitigations
A comprehensive breakdown of the OWASP Agentic Security Top 10 framework, covering ASI01–ASI10 risks including goal hijacking, tool misuse, identity abuse, supply chain vulnerabilities, and cascading failures — with practical mitigations for AI agent systems.
Read more →
·4 min
Complete Guide to Running Claude Code on Amazon Bedrock
Complete guide to deploying Claude Code on Amazon Bedrock: environment setup, cross-region inference, prompt caching, cost attribution, Guardrails, and the Mantle endpoint for enterprise compliance.
Read more →
·3 min
GPT-5.6 Sol Deep Dive: Capability Breakthroughs and Alignment Risks
OpenAI previews GPT-5.6 with three variants — Sol, Terra, and Luna. Sol leads in agentic coding at 750 tokens/sec but is OpenAI's most misaligned model yet.
Read more →
·2 min
Claude Sonnet 5 Deep Dive: Near-Opus Performance but Higher Costs — Is It Worth the Upgrade?
Claude Sonnet 5 benchmarked: near-Opus 4.8 performance but poor token efficiency makes it pricier than the flagship. Full analysis of pricing, safety tradeoffs, and real-world results.
Read more →
·2 min
Agent Loop Explained: Core Principles and Implementation of the Agentic Cycle
A deep dive into the Agent Loop: how agents autonomously cycle through think→act→think, the difference from regular LLMs, ReAct paradigm origins, and how to implement one from a while loop.
Read more →
·3 min
Java Developers Pivoting to AI: Why RAG Knowledge Bases Are the Best Entry Point
Traditional Java roles are shrinking while AI demand surges. Learn the three paths into AI for developers, and why RAG knowledge bases are the highest-ROI entry point for Java engineers.
Read more →
·3 min
GPT-5.6 Sol In-Depth Review: Can It Really Challenge Claude Sonnet on Cost Efficiency?
A deep dive into OpenAI GPT-5.6 Sol: benchmark scores rival Claude, coding agent performance leads competitors, yet costs a fraction. But model cheating risks, access limits, and real-world gaps deserve attention.
Read more →
Claude Hit by Prompt Injection Attacks…
·2 min
Claude Hit by Prompt Injection Attacks: AI Security Blind Spots and a Defense Guide
A viral Hacker News post reveals how prompt injection attacks can trick AI assistants like Claude into leaking user data. Learn how indirect injection works and how to defend against it.
Read more →
·4 min
WebMCP in Practice: A Complete Guide to Making Your Website AI Agent-Ready
A deep dive into the WebMCP proposal: how AI agents read websites, how to expose structured tools via imperative and declarative APIs, and how to audit agentic readiness with Lighthouse.
Read more →