Back/Engineering/Devin
IntermediateEngineeringDevin

How to Integrate a New Server into a Codebase with Devin AI and DeepWiki

Use Devin AI as a junior engineer to integrate a new server into an existing codebase. This workflow combines DeepWiki for codebase analysis and a detailed prompt to guide Devin, which then handles research, coding, and pull request generation asynchronously.

From How I AI

How I AI: Cognition Labs CEO Scott Wu & Devin AI, the junior engineer that never sleeps

with Claire Vo

How to Integrate a New Server into a Codebase with Devin AI and DeepWiki

Tools Used

Devin

AI software engineer by Cognition Labs

Step-by-Step Guide

1

Understand the Codebase with DeepWiki

Before tasking Devin, use an AI-powered tool like DeepWiki to generate documentation and natural language explanations of the relevant sections of your codebase. This helps you understand the system faster and provides context for the next step.

2

Craft a Context-Rich Prompt for Devin

Using the insights gained from DeepWiki, write a detailed prompt for Devin. Provide specific context, mention existing patterns to follow, define data structures, and list functions to look at. A clear prompt is crucial for a successful outcome.

Prompt:
Please go research the chat PRD-MCP server and add that to the list here. Follow the pattern of existing servers like Atlassian and HubSpot. Here's the exact type it structure that would be used here. Here are the functions that you should be looking at. And here's what you should check to make sure that it works.
3

Initiate Asynchronous Execution

Kick off the Devin session with your prompt. Devin will work in the background to research, write the necessary code, run tests, and ultimately open a pull request (PR) on GitHub for the new server integration.

4

Review and Merge the Pull Request

Once Devin has completed the task and submitted a PR, review the code changes as you would with a human junior engineer. Provide feedback if necessary, or merge the changes if they meet the requirements. This maintains quality control while leveraging AI for efficiency.

Become a 10x PM.
For just $5 / month.

We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.