Two different jobs that both say 'AI': using a coding agent to build and maintain a repo, and building AI into the product itself. How to drive Claude efficiently, what agents and MCPs actually are (with Figma/Linear/GitHub examples and the gh-vs-MCP call), and—when you want a feature that talks to a model—how to structure an AI service and wire it into the frontend and backend templates from the last few articles. The condensed version of everything I've learned shipping both.

GraphQL has different libraries that enhances the experience of the developer and helps us produce code easier. We can add Prisma as an ORM that enhances our connection with the client by adding resolvers to the queries.

In these series of posts we will learn how to build a social network from scratch, we can login using JSON web token, create a user profile, edit it, delete it, post comments in a feed, delete your comments, you can comment other people comments. This will provide for a complete experience of the stack.