Category: tech > ai > agents
115 insights in this category - page 6 of 6. View all insights
Non-Coder Ships iOS Apps Using Dual-Agent Claude Code Workflow
LinkedIn's editor shipped iOS apps to the App Store with zero coding experience, using a dual-agent Claude Code workflow for building and review.
How coding agents work - Agentic Engineering Patterns
Simon Willison breaks down how coding agents work: an LLM in a loop with tools, token caching, and reasoning modes. Simpler than you think.
How to Build a Production-Ready Claude Code Skill
Most Claude Code Skills fail at triggering, not execution. Writing a specific description with explicit trigger keywords matters most.
OpenViking Cuts Agent Tokens 11x With Filesystem Retrieval
OpenViking organizes AI agent context as a virtual filesystem with tiered loading, cutting tokens 11x while raising task completion by 15 points.
What is agentic engineering? - Agentic Engineering Patterns
Simon Willison defines agentic engineering as building software with coding agents in a loop, distinct from unreviewed vibe coding.
Context Mode: 94-100% Context Reduction in Claude Code
Context Mode achieves 94-100% context reduction per tool call, extending typical Claude Code sessions from 30 minutes to about 3 hours.
CoPaw: Self-Hosted AI Assistant With Local LLMs and Multi-Chat
CoPaw is a self-hostable AI assistant from Alibaba that connects to messaging platforms and supports local LLMs via Ollama with no API key needed.
How I write software with LLMs
A multi-agent LLM workflow uses Opus for architecture, Sonnet for coding, and Codex/Gemini for review. Different models catch different failures.
NanoClaw Replaces OpenClaw's 500k Lines With Container Isolation
NanoClaw replaces OpenClaw's 500k lines of code with a handful of files and hypervisor-level container isolation per AI agent.
AI agent workflow orchestration rules for reliable coding
A concise ruleset for AI agent workflow orchestration covering plan mode, subtask strategy, self-improvement loops, and verification discipline.
Playwright CLI Uses 500% Fewer Tokens Than the MCP
The Playwright CLI is roughly 500% more token-efficient than the Playwright MCP for browser automation in Claude Code, with the same capabilities.
CLI Anything: Replacing MCP Servers with Direct CLI Tool Access
A promotional TikTok claims CLI tools will replace MCP servers for Claude Code, but provides no evidence. The actual repo may have more substance.
Nano Banana Pro 2: Web-Search-Grounded Image Generation via Claude
Google's Nano Banana Pro 2 integrates web search into image generation, producing grounded outputs with accurate text from live data.
VS Code Agent Kanban: Task Management for AI Developers
VS Code Agent Kanban stores every AI coding task as a markdown file with YAML frontmatter, solving context loss between sessions.
Perplexity Personal Computer: cloud AI agent on Mac mini
Perplexity's Personal Computer is a cloud-based AI agent running on Mac mini