AI agents
Working with AI coding agents that run real commands: context, permissions, review, safety rails, and where they should run.
69 posts · page 1 of 3
Why Does AI Hallucinate? And How to Reduce It in Your App
AI models sometimes state false things with complete confidence. Why it happens — they predict plausible text rather than look up facts — the kinds of hallucination you'll meet in coding and apps, and practical ways to reduce it: grounding, tools, structure, checks and room to say 'I don't know'.
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.
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.
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 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.
The Claude Agent SDK: Building Your Own Agents on Claude Code's Engine
The Claude Agent SDK gives you the agent loop behind Claude Code as a library: file and shell tools, permissions, MCP, subagents and sessions. When to use it instead of the plain API or claude -p, a minimal TypeScript example, custom tools, permissions, and running it safely.
The Best AI Coding Tools in 2026, by What You're Trying to Do
Terminal agents, AI editors, IDE assistants and app builders — the AI coding landscape sorted by job rather than hype. Claude Code, Codex, Cursor, Copilot, Gemini CLI, Lovable, Bolt, v0 and Replit: who each is for, and how to choose without trying them all.
Who Owns AI-Generated Code? Copyright, Licences, and What It Means for Your App
If an AI wrote your app's code, who owns it? What AI providers' terms say, why copyright law cares about human authorship, the risk of code that resembles open-source projects, and practical steps to protect a product built with AI.
What Is Function Calling (Tool Calling) in AI? Explained With Examples
Function calling — also called tool calling or tool use — lets an AI model ask your code to do things: look up an order, check the weather, query a database. How it works step by step, a Claude example, why the model never runs your code itself, and how to keep it safe.
Spec-Driven Development With Claude Code: Write the Spec, Then Let the Agent Build
Spec-driven development means agreeing on a written specification before an AI agent writes code. What a good spec contains, a practical workflow with Claude Code (spec → plan → tasks → implement → verify), templates, and when it's overkill.
Context Engineering for Coding Agents: Beyond Prompt Engineering
Context engineering is designing everything an agent sees — instructions, tools, files, history — not just the prompt. Why context is a finite budget, context rot, just-in-time retrieval, progressive disclosure with skills, note-taking and compaction, subagents, and how to apply it to Claude Code.
Claude Code vs GitHub Copilot: What's the Difference?
GitHub Copilot started as autocomplete and grew into agents; Claude Code started as an agent. How they compare on workflow, models, GitHub integration and pricing — and why Copilot can even run Claude for you.
Claude Code vs Cursor: Which Should You Use in 2026?
Cursor is an AI code editor; Claude Code is an AI agent that runs in your terminal, IDE, desktop app or browser. How they differ in workflow, models, pricing and where they run — and why plenty of people use both.
Claude Code vs OpenAI Codex: An Honest Comparison
Claude Code and OpenAI's Codex are the two big terminal-first coding agents. How they compare on where they run, which plans include them, models, cloud tasks and day-to-day workflow — without picking a winner for you.
Claude Code GitHub Actions: Set Up @claude on Issues and Pull Requests
How to set up the Claude Code GitHub Action so you can mention @claude on issues and PRs: quick setup with /install-github-app, manual setup, API key vs subscription token, interactive vs automation mode, scheduled runs, cost controls, and security.
Claude Code /compact vs /clear: Managing Context Without Losing Your Place
When to compact, when to clear, and when to let auto-compaction handle it. What /compact actually does, custom compaction instructions, the auto-compact window and /autocompact, why compacting a huge session is itself expensive, and a workflow that keeps sessions sharp.
Getting AI to Write Tests That Actually Catch Bugs
Ask an AI for tests and you'll get plenty: tests that mock everything, assert nothing useful, and pass no matter what the code does. How to get tests that fail when behaviour breaks — what to test, how to prompt, how to check a test is real, and how tests become the agent's safety net.
How to Write a Good Bug Report (for Humans and AI Tools)
'It's broken' can't be fixed. 'On /checkout, clicking Pay with an empty cart returns a 500' can. The five parts of a useful bug report, how to find reproduction steps, what evidence to attach, and a template you can paste into GitHub issues or your AI coding tool.
What Is Vibe Coding? What It's Great For, and Where It Breaks
Vibe coding means building software by describing what you want to an AI and accepting what it produces, often without reading the code. It's genuinely powerful for some things and genuinely risky for others. An honest guide to where the line is.
What Is MCP? The Model Context Protocol for Beginners
MCP is a standard way to plug tools and data into AI apps — a USB-C port for AI. What the Model Context Protocol is, what servers and clients are, what tools, resources, and prompts do, real examples, and the safety questions to ask before connecting one.
What Is Claude Code? A Beginner's Guide
Claude Code is Anthropic's AI coding agent: instead of just suggesting code in a chat, it reads your project, edits files, runs commands, and checks its own work. What it is, where you can use it, what it costs, and how to get started without getting into trouble.
What Is an LLM? Large Language Models Explained Without the Hype
Claude, GPT, and Gemini are large language models. What an LLM actually is, how it's trained, why it's good at code, why it confidently makes things up, what 'model', 'prompt', and 'temperature' mean, and what that means for building apps with AI.
What Is an AI Coding Agent? (And How It's Different From a Chatbot)
AI coding tools come in three flavours: chatbots that answer, assistants that autocomplete, and agents that take actions — editing files, running commands, and checking their own work. What makes something an agent, why it matters, and what agents need to work well and safely.
What Is a Pull Request? A Beginner's Guide
A pull request is how a change gets proposed, checked, and merged into a project — and it's the single best safety net when an AI agent is writing your code. What PRs are, how they work on GitHub, what to look at before you click Merge, and why you want one for every change.