# Three important things to get right for successful AI Coding

DevFeed: [Three important things to get right for successful AI Coding](<https://devfeed.tech/articles/three-important-things-to-get-right-for-successful-ai-coding-25348.md>)

Original publisher: [Read original article](<https://kau.sh/blog/three-req-ai-coding/>)

Author: Kaushik Gopal

Published: 2025-10-05T16:54:46Z

Content type: tutorial

Language: en

Sources: [Kaushik Gopal's Site](<https://devfeed.tech/sources/kaushik-gopal-s-site.md>)

Topics: [ai-coding](<https://devfeed.tech/topics/ai-coding.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [context](<https://devfeed.tech/topics/context.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [MCP](<https://devfeed.tech/topics/mcp.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [context](<https://devfeed.tech/tags/context.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

## AI overview

This article presents three practices for improving AI coding results: provide focused context, write prompts as detailed specifications, and execute work in manageable chunks. It discusses project instructions, tooling, MCP connections, reusable command templates, and the limits of AI agents' context windows.

## Source excerpt

I often hear AI coding feels inconsistent or underwhelming. I'm surprised by this because more often than not, I get good results. When working with any AI agent (or any LLM tool), there are really just three things that drive your results: the context you provide the prompt you write executing in chunks This may sound discouragingly obvious, but being deliberate about these three (every time you send a request to Claude Code, ChatGPT etc.) makes a noticeable difference. ...and it's straightforward to get 80% of this right. Context # LLMs are pocket-sized world knowledge machines. Every time you work on a task, you need to trim that machine to a surgical one that's only focused on the task at hand. You do this by seeding context. The simplest way to do this, especially for AI Coding: System rules & agent instructions: This is basically your AGENTS.md file where you briefly explain what the project is, the architecture, conventions used in the repository, and navigation the project.1 Tooling: Lot of folks miss this, but in your AGENTS.md, explicitly point to the commands you use yourself to build, test and verify. I'm a big fan of maintaining a single Makefile with the most important commands, that the assistant can invoke easily from the command line. Real-time data (MCP): when you need real-time data or connect to external tools, use MCPs. People love to go on about complex MCP setup but don't over index on this. For e.g. instead of a github MCP just install the gh cli command let the agent run these directly. You can burn tokens if you're not careful with MCPs. But of course, for things like Figma/JIRA where there's no other obvious connection path, use it liberally. There are many other ways, and engineering better context delivery is fast becoming the next frontier in AI development.2 Prompt # Think of prompts as specs, not search queries. For example: 'Write me a unit test for this authentication class' 🙅♂. Instead of that one-liner, here's how I would start th