AI agents
Working with AI coding agents that run real commands: context, permissions, review, safety rails, and where they should run.
117 posts · page 2 of 5
What Is Prompt Engineering? A Practical Guide With Examples
Prompt engineering is writing instructions that get reliable results from an AI model. The techniques that actually work — clear tasks, context, examples (few-shot), structure, letting the model think, and testing — with before-and-after examples, and how it differs from context engineering.
What Is OpenAI Codex? The Coding Agent Explained
Codex is OpenAI's coding agent: a desktop app, a command-line tool, IDE extensions and cloud tasks that read your code, make changes and run commands. What it does, how it differs from the old 2021 Codex model, what it costs with ChatGPT plans, and how it compares with Claude Code.
What Is GitHub Copilot? A Beginner's Guide to the AI Pair Programmer
GitHub Copilot is an AI assistant from GitHub that suggests code as you type, answers questions in chat, edits files in agent mode, and can even take a GitHub issue and open a pull request. What it does, where it works, what it costs and when to use it.
What Is Gemini CLI? And What Happened When It Became Antigravity CLI
Gemini CLI was Google's open-source AI coding agent for the terminal, with a famously generous free tier. In June 2026 Google replaced it for individual users with Antigravity CLI. What Gemini CLI does, who can still use it, and what to use now.
What Is Cursor? The AI Code Editor Explained for Beginners
Cursor is a code editor with AI built in: autocomplete that predicts your next edit, a chat that knows your codebase, and an agent that changes many files at once. What it is, how it works, whether it's free, and how it compares with Copilot and Claude Code.
What Is an AI Agent? (And How It's Different From a Chatbot)
An AI agent is a model in a loop: it decides on an action, uses a tool, looks at the result, and repeats until the job is done. How agents work, real examples, what makes them useful and risky, and how to tell a real agent from a renamed chatbot.
Test-Driven Development With Claude Code
Tests first is the single best way to make an AI coding agent reliable: it gives Claude a pass/fail signal to iterate against. A red-green-refactor workflow for Claude Code, prompts that stop it cheating the tests, enforcing it with hooks and /goal, and where TDD with agents falls short.
The Supabase MCP Server: Let AI Work With Your Database (Safely)
Supabase's MCP server lets Claude Code, Cursor and other AI tools inspect your tables, run SQL, apply migrations and read logs. How to connect it, why you should scope it to one project in read-only mode, and the risks of giving an AI database access.
The Principle of Least Privilege, Explained for App Builders
Give every user, service, key and AI agent only the access it needs — nothing more. What least privilege means, and practical examples for databases, API keys, cloud accounts, servers, team members and AI coding agents, so one mistake or breach can't take everything down.
Playwright MCP: Let Claude Code Use a Real Browser
The Playwright MCP server lets AI tools open pages, click, type and read a live browser through accessibility snapshots instead of screenshots. How to add it to Claude Code, useful prompts for testing and debugging, key options like headless and isolated, and its limits.
Pair Programming With AI: How to Work With an AI as Your Partner
Pair programming means two people on one problem — a driver and a navigator. With AI, you can take either role. When to let the AI drive and when to drive yourself, a workflow that keeps you in control, prompts for each role, and the habits that make you better, not lazier.
MCP vs API: What's the Difference, and Do You Need Both?
An API is how programs talk to a service. MCP (Model Context Protocol) is a standard way for AI tools to discover and use those services. How they relate, why MCP servers usually wrap APIs, when to use each, and what MCP adds and costs.
How Coding Agents Work: The Loop, the Tools, and the Context Behind Them
Under the hood, Claude Code, Codex and similar agents are a model in a loop with tools and a carefully managed context. The agent loop, tools, file editing, search, context compaction, subagents, permissions and sandboxing — and what it means for you.
The GitHub MCP Server: Setup With Claude Code and What It Can Do
GitHub's official MCP server lets AI tools read and act on your repositories: issues, pull requests, Actions runs, code search and security alerts. How to connect it to Claude Code (remote or Docker), choose toolsets, use read-only mode, and keep your token safe.
Figma to Code: How to Turn Designs Into a Working App
The ways to get from a Figma design to real code: hand-building from Dev Mode, Figma's own code features, plugins, AI tools that read Figma via MCP or screenshots, and AI app builders. What each produces, and how to prepare a Figma file so the result is actually usable.
Cursor vs GitHub Copilot: Which AI Coding Assistant Is Better for You?
Cursor is a standalone AI code editor; GitHub Copilot is an AI assistant that plugs into the editor you already use and into GitHub itself. How they compare on autocomplete, agents, models, GitHub integration and pricing — and how to pick.
Cursor Rules Explained: .cursor/rules, AGENTS.md, and CLAUDE.md
Rules files tell an AI coding tool how your project works so you don't repeat yourself every chat. How Cursor's project rules work, the rule types, what to put in them, how they compare with AGENTS.md and CLAUDE.md, and how to share one set of rules across tools.
Claude Code vs Windsurf (Now Devin Desktop): What Changed and Which to Use
Windsurf was renamed Devin Desktop in June 2026 after Cognition bought it. How the AI code editor compares with Claude Code on workflow, models, pricing and where it runs — and what Windsurf users should know about the change.
Claude Code vs OpenCode: Closed Agent or Open-Source Agent?
OpenCode is an open-source AI coding agent that works with almost any model provider; Claude Code is Anthropic's agent built around Claude. How they compare on models, cost, features, privacy and workflow — and when each makes sense.
Claude Code vs Gemini CLI: Which Terminal Coding Agent Should You Use?
Claude Code and Google's Gemini CLI are both AI coding agents that live in your terminal. How they compare on models, cost, free tiers, extensibility, safety controls and day-to-day workflow — and how to pick.
Claude Code vs Google Antigravity: Which AI Coding Agent Should You Use?
Google Antigravity is an agent-first IDE and CLI built around Gemini; Claude Code is Anthropic's agent for the terminal, IDEs, desktop and web. How they compare on workflow, models, pricing, free tiers and where they run — and how to choose.
Claude Code Plugins: Install, Manage and Build Your Own
A Claude Code plugin bundles skills, subagents, hooks and MCP servers into one installable unit, distributed through marketplaces. How to install plugins and choose a scope, what an enabled plugin costs you in context, the official marketplace, sharing a team setup, and building your own with plugin.json.
Claude Code Memory Explained: CLAUDE.md, Auto Memory, and /memory
Claude Code starts every session with a blank context window. Two things carry knowledge across: CLAUDE.md files you write, and auto memory Claude writes itself. Where each lives, what loads when, how to view and edit them with /memory, and why Claude sometimes ignores them.
Claude Code Best Practices: 12 Habits That Make the Biggest Difference
The habits that separate good Claude Code sessions from frustrating ones: give it a way to check its work, plan before coding, keep context clean with /clear, correct early, use subagents for research, and review the diff with fresh eyes. Practical, with example prompts.