Agentic AI Persona Chat (Replit)
Agentic AI Persona Chat (Replit) is an interactive AI chat application built on Replit that enables users to converse with specialized AI personas—such as a Helpful Assistant or Socratic guide—designed to reason, guide, and act autonomously based on user intent. The project showcases agentic behavior, modular personas, and real-time conversational intelligence in a developer-friendly environment.
2
305
Agentic AI Persona Chat (Replit)
Agentic AI Persona Chat (Replit) is an interactive AI chat application built on Replit that enables users to converse with specialized AI personas—such as a Helpful Assistant or Socratic guide—designed to reason, guide, and act autonomously based on user intent. The project showcases agentic behavior, modular personas, and real-time conversational intelligence in a developer-friendly environment.
Command-line tool in Node.js that checks Transport Fever 3 mods without opening the game. It is open source and published on npm. It checks that each mod is well formed and that a set of mods can run together without conflicts: duplicate IDs, files overwriting each other, dependency cycles or badly declared incompatibilities. Every finding points to the exact file and field. It also works as a library and inside GitHub Actions, where errors show up on each pull request. Automated tests, continuous integration for releases and documentation in English and Spanish. Tech: Node.js, npm, GitHub Actions, node:test. Package: npmjs.com/package/tf3-mod-validator
My own method for building software with AI agents without losing control over quality. I use it on my own projects and in my day-to-day work as a developer. The idea is simple: AI speeds up writing code a lot, but without a process behind it, it also speeds up mistakes. So every change goes through phases: define what has to be done and how to check it, split it into small tasks, let the agents build it, and then run everything through tests, automated reviews and a human review before it is delivered. The result: faster delivery without the client paying for that speed with bugs in production. Tech: AI agents, LLMs, automated testing and continuous integration.