#AI Agent
1115 related articles
The Core Principle of AI Agents: One Loop to Explain Codex and Claude Code
A ~20-line JavaScript mini-agent experiment dissects how Codex, Claude Code, and DeepSeek Harness work — they're all one loop: call model, run tools, repeat until done.
Models Update Every Week — How Do You Know Which One Fits Your Product? Notion AI's Head Shares the Case for Building Your Own Evals
Notion AI Head Sarah Sachs argues that instead of chasing weekly model releases, product teams should build custom evaluation systems (evals) to drive data-based model selection and monitor quality.
AI Assistant Sends Banking Info to Company Slack: A Wake-Up Call on Agent Privacy Risks
A Hacker News post reveals real risks of AI Agents leaking banking info to company Slack. Analysis of context isolation failures, over-permission, and practical safety tips.
Connecting Claude and ChatGPT to Paper Trading via MCP: A New Approach to AI-Assisted Market Analysis
See how MCP servers let Claude, ChatGPT, and Gemini connect to the slushy.trade paper trading platform, enabling AI Agents to access real-time data and analyze charts with computer vision.
Grokbot Hands-On: Building an AI Bookkeeping Agent Team in 5 Minutes
Grokbot claims to deploy a 7-agent AI bookkeeping team in 5 minutes using MCP and profession templates. We break down the architecture, workflow, and real-world caveats.
The Enterprise AI Implementation Gap: The Real Distance Between Technology and Business Value
Most enterprises are told to adopt AI but don't know how. Discover the implementation gap between AI technology and real business value — and the opportunity it creates.
AI Agent Tool Calling in ~12 Lines of Code: Function Calling with Claude and OpenAI
Deep dive into Claude and OpenAI Function Calling: implement an Agent loop in ~12 lines of Python with no framework. Covers tool_use vs function_call, Pydantic structured output, and common ID errors.
Grokbot Hands-On: Building 8 Board-Level AI Assistants in 5 Minutes
Grokbot shows how to deploy 8 AI agents plus a coordinator in 5 minutes for board-level financial review, strategy, and risk assessment. A breakdown of its setup, orchestration, and template design.
One MCP URL, 100+ Tools for Your AI Agent: A Hands-On Guide to API Stack
A hands-on guide to connecting AI Agents to 100+ tools via a single MCP URL. Replace hundreds of tool definitions with just three meta-tools. Works with Claude Code, Cursor, VS Code, and more.
AI Agents in Production: The Multi-Agent Architecture Behind Spotify's 650+ Monthly PR Merges
Spotify's Agent SDK-based coding agent merges 650+ PRs/month and saves 90% migration time. This article breaks down multi-agent architecture, least-privilege tool design, and real production challenges.
MCP Resources Explained: How AI Applications Read Context Instead of Calling Tools
What are MCP Resources? This article uses a refund policy example to explain how MCP Resources work, URI addressing, and the key difference from MCP Tools: application-driven context reading vs. model-driven tool execution.
When To-Do Apps Meet AI Agents: A Task Manager Built to Be Called by Intelligent Agents
A to-do app for iPhone, Mac, and AI agents debuts on Hacker News. We analyze its agent-first design, the role of MCP, and what this means for the future of task management.
Anthropic AI Agent's Intrusion into U.S. State Department Visa System Raises Alarm
An Anthropic AI agent was reportedly caught auto-filling U.S. State Department visa forms, sparking debate over accountability, security, and compliance when AI agents operate government systems.
Hermes Agent Getting Started Guide: A Better AI Agent Framework Than OpenClaude
Hermes Agent beginner's guide: VMware Ubuntu setup, installation, Tools & Skills, memory/context, and WeChat/QQ/Feishu integration. A better, safer AI agent framework than OpenClaude.
AI + SRC Automated Vulnerability Hunting: Rebuilding the Three-Step Method with AI Agents
A complete guide to AI+SRC automated vulnerability hunting — comparing traditional methods with AI Agent-powered workflows covering asset recon, false positive filtering, and report generation.
AI Agent Development for Absolute Beginners: A 3-Step Learning Path to Get Started Fast
Intimidated by Python, LLMs, and LangChain? This beginner's guide offers a 3-step path to AI Agent development: basic Python in days, hands-on LLM practice, and your first LangChain Agent.
Breaking Down a 30K-Star Open Source Project: How AI Agents Work in Database Management
Dissecting a 30K-star open source project to reveal how AI Agents work in database management: natural language queries, SQL generation, MCP tool calls, and the FDE skill progression path.
Kamatera Launches One-Click Deployment for 3 AI Agents: Up to $100 Free Trial for 30 Days
Kamatera launches one-click deployment for Hermes Agent, Ruflo, and Paperclip — three open-source AI Agent apps. Starting at $12/month with a 30-day, $100 trial.
A Panoramic Map of 381 AI Agent Projects: An Ecosystem Navigator Organized by Use Case
A curated Roadmap of 381 AI Agent projects organized by primary use case — not GitHub stars — helping developers navigate the fragmented agent ecosystem and make faster technology decisions.
Why Token Blocking Cannot Revoke an AI Agent's Tool Permissions
Token blocking only constrains an AI Agent's text output — it cannot revoke tool permissions. Learn why compliant wording can still trigger dangerous actions, and how scoped credentials and service-boundary enforcement provide real security.